diff --git a/README.md b/README.md
index 62593d8..80c209f 100644
--- a/README.md
+++ b/README.md
@@ -27,3 +27,29 @@ module "monitor" {
 ```
 
 ## About
+
+<!-- BEGIN_TF_DOCS -->
+## Requirements
+
+No requirements.
+
+## Providers
+
+No providers.
+
+## Modules
+
+No modules.
+
+## Resources
+
+No resources.
+
+## Inputs
+
+No inputs.
+
+## Outputs
+
+No outputs.
+<!-- END_TF_DOCS -->
diff --git a/aws/alb/README.md b/aws/alb/README.md
index ec3899f..039a2bb 100644
--- a/aws/alb/README.md
+++ b/aws/alb/README.md
@@ -20,7 +20,7 @@ Configures the following for ALBs based on tags matches:
 
 | Name | Version |
 |------|---------|
-| <a name="provider_datadog"></a> [datadog](#provider\_datadog) | >= 3.37 |
+| <a name="provider_datadog"></a> [datadog](#provider\_datadog) | 3.37.0 |
 
 ## Modules
 
@@ -46,23 +46,26 @@ No modules.
 | <a name="input_base_tags"></a> [base\_tags](#input\_base\_tags) | Base tags (key:value format) to add to this type of check (combined with `local.tags` and `var.additional_tags`, generally you should not change this) | `list(string)` | <pre>[<br>  "resource:alb"<br>]</pre> | no |
 | <a name="input_cost_center"></a> [cost\_center](#input\_cost\_center) | Cost Center of the monitored resource (leave blank to omit tag) | `string` | `null` | no |
 | <a name="input_dashboard_link"></a> [dashboard\_link](#input\_dashboard\_link) | Dashboard link to include in message | `string` | `null` | no |
-| <a name="input_env"></a> [env](#input\_env) | Environment the monitored resource is in (leave blank to omit tag) | `string` | n/a | yes |
+| <a name="input_env"></a> [env](#input\_env) | Environment the monitored resource is in (leave blank to omit tag) | `string` | `null` | no |
 | <a name="input_evaluation_delay"></a> [evaluation\_delay](#input\_evaluation\_delay) | Monitor evaluation delay (see [https://docs.datadoghq.com/monitors/configuration/?tab=thresholdalert#set-alert-conditions](Datadog Docs)) | `number` | `900` | no |
 | <a name="input_http_5xx_responses_enabled"></a> [http\_5xx\_responses\_enabled](#input\_http\_5xx\_responses\_enabled) | Enable HTTP 5xx response monitor | `bool` | `false` | no |
 | <a name="input_http_5xx_responses_evaluation_window"></a> [http\_5xx\_responses\_evaluation\_window](#input\_http\_5xx\_responses\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
 | <a name="input_http_5xx_responses_no_data_window"></a> [http\_5xx\_responses\_no\_data\_window](#input\_http\_5xx\_responses\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
 | <a name="input_http_5xx_responses_threshold_critical"></a> [http\_5xx\_responses\_threshold\_critical](#input\_http\_5xx\_responses\_threshold\_critical) | Critical threshold (percentage, 0-100) | `number` | `75` | no |
 | <a name="input_http_5xx_responses_threshold_warning"></a> [http\_5xx\_responses\_threshold\_warning](#input\_http\_5xx\_responses\_threshold\_warning) | Warning threshold (percentage, 0-100) | `number` | `25` | no |
+| <a name="input_http_5xx_responses_use_message"></a> [http\_5xx\_responses\_use\_message](#input\_http\_5xx\_responses\_use\_message) | Whether to use the query alert base message | `bool` | `false` | no |
 | <a name="input_http_5xx_tg_responses_enabled"></a> [http\_5xx\_tg\_responses\_enabled](#input\_http\_5xx\_tg\_responses\_enabled) | Enable HTTP 5xx response monitor (target group) | `bool` | `false` | no |
 | <a name="input_http_5xx_tg_responses_evaluation_window"></a> [http\_5xx\_tg\_responses\_evaluation\_window](#input\_http\_5xx\_tg\_responses\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
 | <a name="input_http_5xx_tg_responses_no_data_window"></a> [http\_5xx\_tg\_responses\_no\_data\_window](#input\_http\_5xx\_tg\_responses\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
 | <a name="input_http_5xx_tg_responses_threshold_critical"></a> [http\_5xx\_tg\_responses\_threshold\_critical](#input\_http\_5xx\_tg\_responses\_threshold\_critical) | Critical threshold (percentage, 0-100) | `number` | `75` | no |
 | <a name="input_http_5xx_tg_responses_threshold_warning"></a> [http\_5xx\_tg\_responses\_threshold\_warning](#input\_http\_5xx\_tg\_responses\_threshold\_warning) | Warning threshold (percentage, 0-100) | `number` | `25` | no |
+| <a name="input_http_5xx_tg_responses_use_message"></a> [http\_5xx\_tg\_responses\_use\_message](#input\_http\_5xx\_tg\_responses\_use\_message) | Whether to use the query alert base message | `bool` | `false` | no |
 | <a name="input_latency_enabled"></a> [latency\_enabled](#input\_latency\_enabled) | Enable latency monitor | `bool` | `false` | no |
 | <a name="input_latency_evaluation_window"></a> [latency\_evaluation\_window](#input\_latency\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
 | <a name="input_latency_no_data_window"></a> [latency\_no\_data\_window](#input\_latency\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
 | <a name="input_latency_threshold_critical"></a> [latency\_threshold\_critical](#input\_latency\_threshold\_critical) | Critical threshold (seconds) | `number` | `null` | no |
 | <a name="input_latency_threshold_warning"></a> [latency\_threshold\_warning](#input\_latency\_threshold\_warning) | Warning threshold (seconds) | `number` | `null` | no |
+| <a name="input_latency_use_message"></a> [latency\_use\_message](#input\_latency\_use\_message) | Whether to use the query alert base message | `bool` | `false` | no |
 | <a name="input_monitor_exclude_tags"></a> [monitor\_exclude\_tags](#input\_monitor\_exclude\_tags) | Tags to be excluded in the monitoring query. Specify in key:value format | `list(string)` | `[]` | no |
 | <a name="input_monitor_include_tags"></a> [monitor\_include\_tags](#input\_monitor\_include\_tags) | Tags to be included in the monitoring query. Specify in key:value format | `list(string)` | `[]` | no |
 | <a name="input_new_group_delay"></a> [new\_group\_delay](#input\_new\_group\_delay) | Delay in seconds before generating alerts for a new resource | `number` | `300` | no |
@@ -71,10 +74,14 @@ No modules.
 | <a name="input_no_healthy_instances_no_data_window"></a> [no\_healthy\_instances\_no\_data\_window](#input\_no\_healthy\_instances\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
 | <a name="input_no_healthy_instances_threshold_critical"></a> [no\_healthy\_instances\_threshold\_critical](#input\_no\_healthy\_instances\_threshold\_critical) | Critical threshold (percentage) | `number` | `0` | no |
 | <a name="input_no_healthy_instances_threshold_warning"></a> [no\_healthy\_instances\_threshold\_warning](#input\_no\_healthy\_instances\_threshold\_warning) | Warning threshold (percentage) | `number` | `null` | no |
+| <a name="input_no_healthy_instances_use_message"></a> [no\_healthy\_instances\_use\_message](#input\_no\_healthy\_instances\_use\_message) | Whether to use the query alert base message | `bool` | `true` | no |
 | <a name="input_notify_alert_override"></a> [notify\_alert\_override](#input\_notify\_alert\_override) | List of notifications for alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_crit_override"></a> [notify\_crit\_override](#input\_notify\_crit\_override) | List of notifications for 24x7 alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_default"></a> [notify\_default](#input\_notify\_default) | List of alert notifications (can be overridden based on alert type) | `list(string)` | n/a | yes |
 | <a name="input_notify_no_data"></a> [notify\_no\_data](#input\_notify\_no\_data) | Alert if no matching data is found | `bool` | `false` | no |
 | <a name="input_notify_nodata_override"></a> [notify\_nodata\_override](#input\_notify\_nodata\_override) | List of notifications for no data (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_nonprod_override"></a> [notify\_nonprod\_override](#input\_notify\_nonprod\_override) | List of notifications for non-prod alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_prod_override"></a> [notify\_prod\_override](#input\_notify\_prod\_override) | List of notifications for 12x5 prod alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_recovery_override"></a> [notify\_recovery\_override](#input\_notify\_recovery\_override) | List of notifications for alert recovery (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_warn_override"></a> [notify\_warn\_override](#input\_notify\_warn\_override) | List of notifications for alerts in warning threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_renotify_interval"></a> [renotify\_interval](#input\_renotify\_interval) | Interval in minutes to re-send notifications about an alert | `number` | `0` | no |
diff --git a/aws/alb/main.tf b/aws/alb/main.tf
index 30458f7..e5449ca 100644
--- a/aws/alb/main.tf
+++ b/aws/alb/main.tf
@@ -4,7 +4,7 @@ locals {
   monitor_warn_default_priority   = null
   monitor_nodata_default_priority = null
 
-  title_prefix = "${var.title_prefix == null ? "" : "[${var.title_prefix}]"}"
+  title_prefix = var.title_prefix == null ? "" : "[${var.title_prefix}]"
   title_suffix = var.title_suffix == null ? "" : " (${var.title_suffix})"
 }
 
@@ -12,8 +12,8 @@ resource "datadog_monitor" "http_5xx_responses" {
   count = var.http_5xx_responses_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "ALB 5xx Responses - {{loadbalancer.name}}", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.http_5xx_responses_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -27,8 +27,8 @@ resource "datadog_monitor" "http_5xx_responses" {
 
   query = <<END
     min(${var.http_5xx_responses_evaluation_window}):
-      default(avg:aws.applicationelb.httpcode_elb_5xx${local.query_filter} by {aws_account,env,loadbalancer,region}.as_rate(), 0) / (
-      default(avg:aws.applicationelb.request_count${local.query_filter} by {aws_account,env,loadbalancer,region}.as_rate(), 1)
+      default(avg:aws.applicationelb.httpcode_elb_5xx${local.query_filter} by {aws_account,env,datadog_managed,loadbalancer,region}.as_rate(), 0) / (
+      default(avg:aws.applicationelb.request_count${local.query_filter} by {aws_account,env,datadog_managed,loadbalancer,region}.as_rate(), 1)
     ) * 100 > ${var.http_5xx_responses_threshold_critical}
 END
 
@@ -42,8 +42,8 @@ resource "datadog_monitor" "http_5xx_tg_responses" {
   count = var.http_5xx_tg_responses_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "ALB Target Group 5xx Responses - {{loadbalancer.name}}", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.http_5xx_tg_responses_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -57,8 +57,8 @@ resource "datadog_monitor" "http_5xx_tg_responses" {
 
   query = <<END
     min(${var.http_5xx_tg_responses_evaluation_window}):
-      default(avg:aws.applicationelb.httpcode_elb_5xx${local.query_filter} by {loadbalancer,region,aws_account,targetgroup,env}.as_rate(), 0) / (
-      default(avg:aws.applicationelb.request_count${local.query_filter} by {loadbalancer,region,aws_account,targetgroup,env}.as_rate(), 1)
+      default(avg:aws.applicationelb.httpcode_elb_5xx${local.query_filter} by {loadbalancer,region,aws_account,targetgroup,env,datadog_managed}.as_rate(), 0) / (
+      default(avg:aws.applicationelb.request_count${local.query_filter} by {loadbalancer,region,aws_account,targetgroup,env,datadog_managed}.as_rate(), 1)
     ) * 100 > ${var.http_5xx_tg_responses_threshold_critical}
 END
 
@@ -72,9 +72,9 @@ END
 resource "datadog_monitor" "latency" {
   count = var.latency_enabled ? 1 : 0
 
-  name         = join("", [local.title_prefix, "{{loadbalancer.name}} ALB latency - {{value}}s ", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  name         = join("", [local.title_prefix, "ALB latency - {{loadbalancer.name}} {{value}}s", local.title_suffix])
+  include_tags = false
+  message      = var.latency_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -88,7 +88,7 @@ resource "datadog_monitor" "latency" {
 
   query = <<END
     avg(${var.latency_evaluation_window}):
-      default(avg:aws.applicationelb.target_response_time.average${local.query_filter} by {aws_account,env,loadbalancer,region}, 0
+      default(avg:aws.applicationelb.target_response_time.average${local.query_filter} by {aws_account,env,datadog_managed,loadbalancer,region}, 0
     ) > ${var.latency_threshold_critical}
 END
 
@@ -101,9 +101,9 @@ END
 resource "datadog_monitor" "no_healthy_instances" {
   count = var.no_healthy_instances_enabled ? 1 : 0
 
-  name         = join("", [local.title_prefix, "{{loadbalancer.name}} ALB healthy instances is at {{value}}%", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  name         = join("", [local.title_prefix, "ALB available healthy instances - {{loadbalancer.name}} {{value}}%", local.title_suffix])
+  include_tags = false
+  message      = var.no_healthy_instances_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -117,9 +117,9 @@ resource "datadog_monitor" "no_healthy_instances" {
 
   query = <<END
     min(${var.no_healthy_instances_evaluation_window}): (
-      sum:aws.applicationelb.healthy_host_count.minimum${local.query_filter} by {aws_account,env,region,loadbalancer} / (
-      sum:aws.applicationelb.healthy_host_count.minimum${local.query_filter} by {aws_account,env,region,loadbalancer} +
-      sum:aws.applicationelb.un_healthy_host_count.maximum${local.query_filter} by {aws_account,env,region,loadbalancer} )
+      sum:aws.applicationelb.healthy_host_count.minimum${local.query_filter} by {aws_account,env,datadog_managed,region,loadbalancer} / (
+      sum:aws.applicationelb.healthy_host_count.minimum${local.query_filter} by {aws_account,env,datadog_managed,region,loadbalancer} +
+      sum:aws.applicationelb.un_healthy_host_count.maximum${local.query_filter} by {aws_account,env,datadog_managed,region,loadbalancer} )
     ) * 100 <= ${var.no_healthy_instances_threshold_critical}
 END
 
diff --git a/aws/alb/variables.tf b/aws/alb/variables.tf
index 4d2eedf..e9e4912 100644
--- a/aws/alb/variables.tf
+++ b/aws/alb/variables.tf
@@ -17,7 +17,7 @@ variable "base_tags" {
 # HTTP 5xx Response Codes (ALB)
 ########################################
 variable "http_5xx_responses_enabled" {
-  default     = false
+  default     = true
   description = "Enable HTTP 5xx response monitor"
   type        = bool
 }
@@ -46,11 +46,17 @@ variable "http_5xx_responses_threshold_warning" {
   type        = number
 }
 
+variable "http_5xx_responses_use_message" {
+  description = "Whether to use the query alert base message"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # HTTP 5xx Response Codes (Target Group)
 ########################################
 variable "http_5xx_tg_responses_enabled" {
-  default     = false
+  default     = true
   description = "Enable HTTP 5xx response monitor (target group)"
   type        = bool
 }
@@ -79,11 +85,17 @@ variable "http_5xx_tg_responses_threshold_warning" {
   type        = number
 }
 
+variable "http_5xx_tg_responses_use_message" {
+  description = "Whether to use the query alert base message"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # Latency Instances
 ########################################
 variable "latency_enabled" {
-  default     = false
+  default     = true
   description = "Enable latency monitor"
   type        = bool
 }
@@ -101,7 +113,7 @@ variable "latency_no_data_window" {
 }
 
 variable "latency_threshold_critical" {
-  default     = null
+  default     = 3
   description = "Critical threshold (seconds)"
   type        = number
 }
@@ -112,6 +124,12 @@ variable "latency_threshold_warning" {
   type        = number
 }
 
+variable "latency_use_message" {
+  description = "Whether to use the query alert base message"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # No Healthy Instances
 ########################################
@@ -144,3 +162,9 @@ variable "no_healthy_instances_threshold_warning" {
   description = "Warning threshold (percentage)"
   type        = number
 }
+
+variable "no_healthy_instances_use_message" {
+  description = "Whether to use the query alert base message"
+  type        = bool
+  default     = true
+}
diff --git a/aws/apigateway/README.md b/aws/apigateway/README.md
index aaaf2f8..52cd15d 100644
--- a/aws/apigateway/README.md
+++ b/aws/apigateway/README.md
@@ -18,7 +18,7 @@ Configures the following for APIs based on tags matches:
 
 | Name | Version |
 |------|---------|
-| <a name="provider_datadog"></a> [datadog](#provider\_datadog) | >= 3.37 |
+| <a name="provider_datadog"></a> [datadog](#provider\_datadog) | 3.37.0 |
 
 ## Modules
 
@@ -42,25 +42,30 @@ No modules.
 | <a name="input_base_tags"></a> [base\_tags](#input\_base\_tags) | Base tags (key:value format) to add to this type of check (combined with `local.tags` and `var.additional_tags`, generally you should not change this) | `list(string)` | <pre>[<br>  "resource:apigateway"<br>]</pre> | no |
 | <a name="input_cost_center"></a> [cost\_center](#input\_cost\_center) | Cost Center of the monitored resource (leave blank to omit tag) | `string` | `null` | no |
 | <a name="input_dashboard_link"></a> [dashboard\_link](#input\_dashboard\_link) | Dashboard link to include in message | `string` | `null` | no |
-| <a name="input_env"></a> [env](#input\_env) | Environment the monitored resource is in (leave blank to omit tag) | `string` | n/a | yes |
+| <a name="input_env"></a> [env](#input\_env) | Environment the monitored resource is in (leave blank to omit tag) | `string` | `null` | no |
 | <a name="input_evaluation_delay"></a> [evaluation\_delay](#input\_evaluation\_delay) | Monitor evaluation delay (see [https://docs.datadoghq.com/monitors/configuration/?tab=thresholdalert#set-alert-conditions](Datadog Docs)) | `number` | `900` | no |
 | <a name="input_http_5xx_responses_enabled"></a> [http\_5xx\_responses\_enabled](#input\_http\_5xx\_responses\_enabled) | Enable HTTP 5xx response monitor | `bool` | `false` | no |
 | <a name="input_http_5xx_responses_evaluation_window"></a> [http\_5xx\_responses\_evaluation\_window](#input\_http\_5xx\_responses\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
 | <a name="input_http_5xx_responses_no_data_window"></a> [http\_5xx\_responses\_no\_data\_window](#input\_http\_5xx\_responses\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
 | <a name="input_http_5xx_responses_threshold_critical"></a> [http\_5xx\_responses\_threshold\_critical](#input\_http\_5xx\_responses\_threshold\_critical) | Critical threshold (percentage, 0-100) | `number` | `0.75` | no |
 | <a name="input_http_5xx_responses_threshold_warning"></a> [http\_5xx\_responses\_threshold\_warning](#input\_http\_5xx\_responses\_threshold\_warning) | Warning threshold (percentage, 0-100) | `number` | `0.25` | no |
+| <a name="input_http_5xx_responses_use_message"></a> [http\_5xx\_responses\_use\_message](#input\_http\_5xx\_responses\_use\_message) | Whether to use the query alert base message for HTTP 5xx responses monitor | `bool` | `false` | no |
 | <a name="input_latency_enabled"></a> [latency\_enabled](#input\_latency\_enabled) | Enable latency monitor | `bool` | `false` | no |
 | <a name="input_latency_evaluation_window"></a> [latency\_evaluation\_window](#input\_latency\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
 | <a name="input_latency_no_data_window"></a> [latency\_no\_data\_window](#input\_latency\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
 | <a name="input_latency_threshold_critical"></a> [latency\_threshold\_critical](#input\_latency\_threshold\_critical) | Critical threshold (seconds) | `number` | `null` | no |
 | <a name="input_latency_threshold_warning"></a> [latency\_threshold\_warning](#input\_latency\_threshold\_warning) | Warning threshold (seconds) | `number` | `null` | no |
+| <a name="input_latency_use_message"></a> [latency\_use\_message](#input\_latency\_use\_message) | Whether to use the query alert base message for the latency monitor | `bool` | `false` | no |
 | <a name="input_monitor_exclude_tags"></a> [monitor\_exclude\_tags](#input\_monitor\_exclude\_tags) | Tags to be excluded in the monitoring query. Specify in key:value format | `list(string)` | `[]` | no |
 | <a name="input_monitor_include_tags"></a> [monitor\_include\_tags](#input\_monitor\_include\_tags) | Tags to be included in the monitoring query. Specify in key:value format | `list(string)` | `[]` | no |
 | <a name="input_new_group_delay"></a> [new\_group\_delay](#input\_new\_group\_delay) | Delay in seconds before generating alerts for a new resource | `number` | `300` | no |
 | <a name="input_notify_alert_override"></a> [notify\_alert\_override](#input\_notify\_alert\_override) | List of notifications for alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_crit_override"></a> [notify\_crit\_override](#input\_notify\_crit\_override) | List of notifications for 24x7 alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_default"></a> [notify\_default](#input\_notify\_default) | List of alert notifications (can be overridden based on alert type) | `list(string)` | n/a | yes |
 | <a name="input_notify_no_data"></a> [notify\_no\_data](#input\_notify\_no\_data) | Alert if no matching data is found | `bool` | `false` | no |
 | <a name="input_notify_nodata_override"></a> [notify\_nodata\_override](#input\_notify\_nodata\_override) | List of notifications for no data (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_nonprod_override"></a> [notify\_nonprod\_override](#input\_notify\_nonprod\_override) | List of notifications for non-prod alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_prod_override"></a> [notify\_prod\_override](#input\_notify\_prod\_override) | List of notifications for 12x5 prod alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_recovery_override"></a> [notify\_recovery\_override](#input\_notify\_recovery\_override) | List of notifications for alert recovery (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_warn_override"></a> [notify\_warn\_override](#input\_notify\_warn\_override) | List of notifications for alerts in warning threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_renotify_interval"></a> [renotify\_interval](#input\_renotify\_interval) | Interval in minutes to re-send notifications about an alert | `number` | `0` | no |
diff --git a/aws/apigateway/main.tf b/aws/apigateway/main.tf
index 02033c6..f624851 100644
--- a/aws/apigateway/main.tf
+++ b/aws/apigateway/main.tf
@@ -4,16 +4,16 @@ locals {
   monitor_warn_default_priority   = null
   monitor_nodata_default_priority = null
 
-  title_prefix = "${var.title_prefix == null ? "" : "[${var.title_prefix}]"}"
+  title_prefix = var.title_prefix == null ? "" : "[${var.title_prefix}]"
   title_suffix = var.title_suffix == null ? "" : " (${var.title_suffix})"
 }
 
 resource "datadog_monitor" "http_5xx_responses" {
   count = var.http_5xx_responses_enabled ? 1 : 0
 
-  name         = join("", [local.title_prefix, "API Gateway 5xx Responses - {{host.name}}", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  name         = join("", [local.title_prefix, "API Gateway 5xx Responses - {{apiname.name}}", local.title_suffix])
+  include_tags = false
+  message      = var.http_5xx_responses_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -27,8 +27,8 @@ resource "datadog_monitor" "http_5xx_responses" {
 
   query = <<END
     min(${var.http_5xx_responses_evaluation_window}):
-      default(avg:aws.apigateway.5xxerror{${local.query_filter}} by {stage,apiname,region,aws_account}.as_rate(), 0) / (
-      default(avg:aws.apigateway.count{${local.query_filter}} by {stage,apiname,region,aws_account}.as_rate(), 1)
+      default(avg:aws.apigateway.5xxerror{${local.query_filter}} by {stage,apiname,region,aws_account,env,datadog_managed}.as_rate(), 0) / (
+      default(avg:aws.apigateway.count{${local.query_filter}} by {stage,apiname,region,aws_account,env,datadog_managed}.as_rate(), 1)
     ) * 100 > ${var.http_5xx_responses_threshold_critical}
 END
 
@@ -41,9 +41,9 @@ END
 resource "datadog_monitor" "latency" {
   count = var.latency_enabled ? 1 : 0
 
-  name         = join("", [local.title_prefix, "API Gateway latency - {{host.name}}", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  name         = join("", [local.title_prefix, "API Gateway latency - {{apiname.name}}", local.title_suffix])
+  include_tags = false
+  message      = var.latency_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -57,7 +57,7 @@ resource "datadog_monitor" "latency" {
 
   query = <<END
     avg(${var.latency_evaluation_window}):
-      default(avg:aws.apigateway.latency{${local.query_filter}} by {stage,apiname,region,aws_account}, 0)
+      default(avg:aws.apigateway.latency{${local.query_filter}} by {stage,apiname,region,aws_account,env,datadog_managed}, 0)
     ) > ${var.latency_threshold_critical}
 END
 
diff --git a/aws/apigateway/variables.tf b/aws/apigateway/variables.tf
index 14d282a..d5eb215 100644
--- a/aws/apigateway/variables.tf
+++ b/aws/apigateway/variables.tf
@@ -46,6 +46,12 @@ variable "http_5xx_responses_threshold_warning" {
   type        = number
 }
 
+variable "http_5xx_responses_use_message" {
+  description = "Whether to use the query alert base message for HTTP 5xx responses monitor"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # Latency Instances
 ########################################
@@ -78,3 +84,9 @@ variable "latency_threshold_warning" {
   description = "Warning threshold (seconds)"
   type        = number
 }
+
+variable "latency_use_message" {
+  description = "Whether to use the query alert base message for the latency monitor"
+  type        = bool
+  default     = false
+}
diff --git a/aws/beanstalk/README.md b/aws/beanstalk/README.md
index 007fd00..84f314b 100644
--- a/aws/beanstalk/README.md
+++ b/aws/beanstalk/README.md
@@ -20,7 +20,7 @@ Configures the following for Beanstalk environments based on tags matches:
 
 | Name | Version |
 |------|---------|
-| <a name="provider_datadog"></a> [datadog](#provider\_datadog) | >= 3.37 |
+| <a name="provider_datadog"></a> [datadog](#provider\_datadog) | 3.37.0 |
 
 ## Modules
 
@@ -46,31 +46,37 @@ No modules.
 | <a name="input_base_tags"></a> [base\_tags](#input\_base\_tags) | Base tags (key:value format) to add to this type of check (combined with `local.tags` and `var.additional_tags`, generally you should not change this) | `list(string)` | <pre>[<br>  "resource:beanstalk"<br>]</pre> | no |
 | <a name="input_cost_center"></a> [cost\_center](#input\_cost\_center) | Cost Center of the monitored resource (leave blank to omit tag) | `string` | `null` | no |
 | <a name="input_dashboard_link"></a> [dashboard\_link](#input\_dashboard\_link) | Dashboard link to include in message | `string` | `null` | no |
-| <a name="input_env"></a> [env](#input\_env) | Environment the monitored resource is in (leave blank to omit tag) | `string` | n/a | yes |
+| <a name="input_env"></a> [env](#input\_env) | Environment the monitored resource is in (leave blank to omit tag) | `string` | `null` | no |
 | <a name="input_evaluation_delay"></a> [evaluation\_delay](#input\_evaluation\_delay) | Monitor evaluation delay (see [https://docs.datadoghq.com/monitors/configuration/?tab=thresholdalert#set-alert-conditions](Datadog Docs)) | `number` | `900` | no |
 | <a name="input_health_enabled"></a> [health\_enabled](#input\_health\_enabled) | Enable Beanstalk health monitor (requires enhanced metrics) | `bool` | `false` | no |
 | <a name="input_health_evaluation_window"></a> [health\_evaluation\_window](#input\_health\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`) | `string` | `"last_5m"` | no |
 | <a name="input_health_no_data_window"></a> [health\_no\_data\_window](#input\_health\_no\_data\_window) | No date threshold (minutes) | `number` | `20` | no |
 | <a name="input_health_threshold_critical"></a> [health\_threshold\_critical](#input\_health\_threshold\_critical) | Critical threshold (<br>    0 = OK<br>    1 = Info<br>    5 = Unknown<br>    10 =  No data<br>    15 =  Warning<br>    20 = Degraded<br>    25 = Severe<br>) | `number` | `25` | no |
 | <a name="input_health_threshold_warning"></a> [health\_threshold\_warning](#input\_health\_threshold\_warning) | Warning threshold (<br>    0 = OK<br>    1 = Info<br>    5 = Unknown<br>    10 =  No data<br>    15 =  Warning<br>    20 = Degraded<br>    25 = Severe<br>) | `number` | `20` | no |
+| <a name="input_health_use_message"></a> [health\_use\_message](#input\_health\_use\_message) | Whether to use the query alert base message for health monitor | `bool` | `false` | no |
 | <a name="input_http_5xx_responses_enabled"></a> [http\_5xx\_responses\_enabled](#input\_http\_5xx\_responses\_enabled) | Enable HTTP 5xx response monitor | `bool` | `false` | no |
 | <a name="input_http_5xx_responses_evaluation_window"></a> [http\_5xx\_responses\_evaluation\_window](#input\_http\_5xx\_responses\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
 | <a name="input_http_5xx_responses_no_data_window"></a> [http\_5xx\_responses\_no\_data\_window](#input\_http\_5xx\_responses\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
 | <a name="input_http_5xx_responses_threshold_critical"></a> [http\_5xx\_responses\_threshold\_critical](#input\_http\_5xx\_responses\_threshold\_critical) | Critical threshold (percentage) | `number` | `75` | no |
 | <a name="input_http_5xx_responses_threshold_warning"></a> [http\_5xx\_responses\_threshold\_warning](#input\_http\_5xx\_responses\_threshold\_warning) | Warning threshold (percentage) | `number` | `25` | no |
+| <a name="input_http_5xx_responses_use_message"></a> [http\_5xx\_responses\_use\_message](#input\_http\_5xx\_responses\_use\_message) | Whether to use the query alert base message for HTTP 5xx responses monitor | `bool` | `false` | no |
 | <a name="input_latency_enabled"></a> [latency\_enabled](#input\_latency\_enabled) | Enable latency monitor | `bool` | `false` | no |
 | <a name="input_latency_evaluation_window"></a> [latency\_evaluation\_window](#input\_latency\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
 | <a name="input_latency_measurement"></a> [latency\_measurement](#input\_latency\_measurement) | Latency Measurement<br><br>Valid options:<br>* p10<br>* p50<br>* p75<br>* p85<br>* p90<br>* p95<br>* p99<br>* p99\_9 | `string` | `"p50"` | no |
 | <a name="input_latency_no_data_window"></a> [latency\_no\_data\_window](#input\_latency\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
 | <a name="input_latency_threshold_critical"></a> [latency\_threshold\_critical](#input\_latency\_threshold\_critical) | Critical threshold (seconds) | `number` | `null` | no |
 | <a name="input_latency_threshold_warning"></a> [latency\_threshold\_warning](#input\_latency\_threshold\_warning) | Warning threshold (seconds) | `number` | `null` | no |
+| <a name="input_latency_use_message"></a> [latency\_use\_message](#input\_latency\_use\_message) | Whether to use the query alert base message for latency monitor | `bool` | `false` | no |
 | <a name="input_monitor_exclude_tags"></a> [monitor\_exclude\_tags](#input\_monitor\_exclude\_tags) | Tags to be excluded in the monitoring query. Specify in key:value format | `list(string)` | `[]` | no |
 | <a name="input_monitor_include_tags"></a> [monitor\_include\_tags](#input\_monitor\_include\_tags) | Tags to be included in the monitoring query. Specify in key:value format | `list(string)` | `[]` | no |
 | <a name="input_new_group_delay"></a> [new\_group\_delay](#input\_new\_group\_delay) | Delay in seconds before generating alerts for a new resource | `number` | `300` | no |
 | <a name="input_notify_alert_override"></a> [notify\_alert\_override](#input\_notify\_alert\_override) | List of notifications for alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_crit_override"></a> [notify\_crit\_override](#input\_notify\_crit\_override) | List of notifications for 24x7 alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_default"></a> [notify\_default](#input\_notify\_default) | List of alert notifications (can be overridden based on alert type) | `list(string)` | n/a | yes |
 | <a name="input_notify_no_data"></a> [notify\_no\_data](#input\_notify\_no\_data) | Alert if no matching data is found | `bool` | `false` | no |
 | <a name="input_notify_nodata_override"></a> [notify\_nodata\_override](#input\_notify\_nodata\_override) | List of notifications for no data (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_nonprod_override"></a> [notify\_nonprod\_override](#input\_notify\_nonprod\_override) | List of notifications for non-prod alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_prod_override"></a> [notify\_prod\_override](#input\_notify\_prod\_override) | List of notifications for 12x5 prod alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_recovery_override"></a> [notify\_recovery\_override](#input\_notify\_recovery\_override) | List of notifications for alert recovery (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_warn_override"></a> [notify\_warn\_override](#input\_notify\_warn\_override) | List of notifications for alerts in warning threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_renotify_interval"></a> [renotify\_interval](#input\_renotify\_interval) | Interval in minutes to re-send notifications about an alert | `number` | `0` | no |
@@ -79,6 +85,7 @@ No modules.
 | <a name="input_root_disk_usage_no_data_window"></a> [root\_disk\_usage\_no\_data\_window](#input\_root\_disk\_usage\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
 | <a name="input_root_disk_usage_threshold_critical"></a> [root\_disk\_usage\_threshold\_critical](#input\_root\_disk\_usage\_threshold\_critical) | Critical threshold (percent) | `number` | `90` | no |
 | <a name="input_root_disk_usage_threshold_warning"></a> [root\_disk\_usage\_threshold\_warning](#input\_root\_disk\_usage\_threshold\_warning) | Warning threshold (percent) | `number` | `80` | no |
+| <a name="input_root_disk_usage_use_message"></a> [root\_disk\_usage\_use\_message](#input\_root\_disk\_usage\_use\_message) | Whether to use the query alert base message for root disk usage monitor | `bool` | `false` | no |
 | <a name="input_runbook_link"></a> [runbook\_link](#input\_runbook\_link) | Runbook link to include in message | `string` | `null` | no |
 | <a name="input_service"></a> [service](#input\_service) | Service associated with the monitored resource (leave blank to omit tag) | `string` | `null` | no |
 | <a name="input_team"></a> [team](#input\_team) | Team supporting the monitored resource (leave blank to omit tag) | `string` | `null` | no |
diff --git a/aws/beanstalk/main.tf b/aws/beanstalk/main.tf
index f55018b..7fe3814 100644
--- a/aws/beanstalk/main.tf
+++ b/aws/beanstalk/main.tf
@@ -17,16 +17,16 @@ locals {
 
   latency_metric = local.latency_metric_map[var.latency_measurement]
 
-  title_prefix = "${var.title_prefix == null ? "" : "[${var.title_prefix}]"}"
+  title_prefix = var.title_prefix == null ? "" : "[${var.title_prefix}]"
   title_suffix = var.title_suffix == null ? "" : " (${var.title_suffix})"
 }
 
 resource "datadog_monitor" "health" {
   count = var.health_enabled ? 1 : 0
 
-  name         = join("", [local.title_prefix, "Beanstalk Health Events - {{host.name}}", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  name         = join("", [local.title_prefix, "Beanstalk Health Events - {{environmentname.name}}", local.title_suffix])
+  include_tags = false
+  message      = var.health_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "metric alert"
 
@@ -40,7 +40,7 @@ resource "datadog_monitor" "health" {
 
   query = <<END
     min(${var.health_evaluation_window}):
-      min:aws.elasticbeanstalk.environment_health${local.query_filter} by {environmentname,region,aws_account}
+      min:aws.elasticbeanstalk.environment_health${local.query_filter} by {environmentname,region,aws_account,env,datadog_managed}
     >= ${var.health_threshold_critical}
 END
 
@@ -53,9 +53,9 @@ END
 resource "datadog_monitor" "http_5xx_responses" {
   count = var.http_5xx_responses_enabled ? 1 : 0
 
-  name         = join("", [local.title_prefix, "ALB 5xx Responses - {{host.name}}", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  name         = join("", [local.title_prefix, "ALB 5xx Responses - {{environmentname.name}}", local.title_suffix])
+  include_tags = false
+  message      = var.http_5xx_responses_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -69,8 +69,8 @@ resource "datadog_monitor" "http_5xx_responses" {
 
   query = <<END
     min(${var.http_5xx_responses_evaluation_window}):(
-      default(sum:aws.elasticbeanstalk.application_requests_5xx${local.query_filter} by {environmentname,region,aws_account}.as_rate(), 0) /
-      default(sum:aws.elasticbeanstalk.application_requests_total${local.query_filter} by {environmentname,region,aws_account}.as_rate(), 1)
+      default(sum:aws.elasticbeanstalk.application_requests_5xx${local.query_filter} by {environmentname,region,aws_account,env,datadog_managed}.as_rate(), 0) /
+      default(sum:aws.elasticbeanstalk.application_requests_total${local.query_filter} by {environmentname,region,aws_account,env,datadog_managed}.as_rate(), 1)
     ) * 100 > ${var.http_5xx_responses_threshold_critical}
 END
 
@@ -83,9 +83,9 @@ END
 resource "datadog_monitor" "latency" {
   count = var.latency_enabled ? 1 : 0
 
-  name         = join("", [local.title_prefix, "Beanstalk Latency - {{host.name}}", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  name         = join("", [local.title_prefix, "Beanstalk Latency - {{environmentname.name}}", local.title_suffix])
+  include_tags = false
+  message      = var.latency_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -98,7 +98,7 @@ resource "datadog_monitor" "latency" {
   timeout_h           = var.timeout_h
 
   query = <<END
-    min:${var.latency_evaluation_window}):min:aws.elasticbeanstalk.${local.latency_metric}${local.query_filter} by {environmentname,region,aws_account}
+    min:${var.latency_evaluation_window}):min:aws.elasticbeanstalk.${local.latency_metric}${local.query_filter} by {environmentname,region,aws_account,env,datadog_managed}
      >= ${var.latency_threshold_critical}
 END
 
@@ -111,9 +111,9 @@ END
 resource "datadog_monitor" "root_disk_usage" {
   count = var.root_disk_usage_enabled ? 1 : 0
 
-  name         = join("", [local.title_prefix, "Beanstalk Instance Root Disk Usage - {{host.name}}", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  name         = join("", [local.title_prefix, "Beanstalk Instance Root Disk Usage - {{environmentname.name}}", local.title_suffix])
+  include_tags = false
+  message      = var.root_disk_usage_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -127,7 +127,7 @@ resource "datadog_monitor" "root_disk_usage" {
 
   query = <<END
     max:${var.latency_evaluation_window}):
-      min:aws.elasticbeanstalk.root_filesystem_util${local.query_filter} by {host,environmentname,region,aws_account}
+      min:aws.elasticbeanstalk.root_filesystem_util${local.query_filter} by {host,environmentname,region,aws_account,env,datadog_managed}
     >= ${var.root_disk_usage_threshold_critical}
 END
 
diff --git a/aws/beanstalk/variables.tf b/aws/beanstalk/variables.tf
index 451d74d..c537346 100644
--- a/aws/beanstalk/variables.tf
+++ b/aws/beanstalk/variables.tf
@@ -68,6 +68,12 @@ Warning threshold (
 END
 }
 
+variable "health_use_message" {
+  description = "Whether to use the query alert base message for health monitor"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # HTTP 5xx Responses
 ########################################
@@ -101,6 +107,12 @@ variable "http_5xx_responses_threshold_warning" {
   type        = number
 }
 
+variable "http_5xx_responses_use_message" {
+  description = "Whether to use the query alert base message for HTTP 5xx responses monitor"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # Latency Instances
 ########################################
@@ -153,6 +165,12 @@ variable "latency_threshold_warning" {
   type        = number
 }
 
+variable "latency_use_message" {
+  description = "Whether to use the query alert base message for latency monitor"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # Root FS Disk Usage
 ########################################
@@ -185,3 +203,9 @@ variable "root_disk_usage_threshold_warning" {
   description = "Warning threshold (percent)"
   type        = number
 }
+
+variable "root_disk_usage_use_message" {
+  description = "Whether to use the query alert base message for root disk usage monitor"
+  type        = bool
+  default     = false
+}
diff --git a/aws/ec2/README.md b/aws/ec2/README.md
index 9feda50..7679e19 100644
--- a/aws/ec2/README.md
+++ b/aws/ec2/README.md
@@ -17,7 +17,7 @@ All checks are enabled by default.
 
 | Name | Version |
 |------|---------|
-| <a name="provider_datadog"></a> [datadog](#provider\_datadog) | >= 3.37 |
+| <a name="provider_datadog"></a> [datadog](#provider\_datadog) | 3.37.0 |
 
 ## Modules
 
@@ -43,40 +43,39 @@ No modules.
 | <a name="input_base_tags"></a> [base\_tags](#input\_base\_tags) | Base tags (key:value format) to add to this type of check (combined with `local.tags` and `var.additional_tags`, generally you should not change this) | `list(string)` | <pre>[<br>  "resource:ec2"<br>]</pre> | no |
 | <a name="input_cost_center"></a> [cost\_center](#input\_cost\_center) | Cost Center of the monitored resource (leave blank to omit tag) | `string` | `null` | no |
 | <a name="input_dashboard_link"></a> [dashboard\_link](#input\_dashboard\_link) | Dashboard link to include in message | `string` | `null` | no |
-| <a name="input_env"></a> [env](#input\_env) | Environment the monitored resource is in (leave blank to omit tag) | `string` | n/a | yes |
+| <a name="input_env"></a> [env](#input\_env) | Environment the monitored resource is in (leave blank to omit tag) | `string` | `null` | no |
 | <a name="input_evaluation_delay"></a> [evaluation\_delay](#input\_evaluation\_delay) | Monitor evaluation delay (see [https://docs.datadoghq.com/monitors/configuration/?tab=thresholdalert#set-alert-conditions](Datadog Docs)) | `number` | `900` | no |
 | <a name="input_monitor_exclude_tags"></a> [monitor\_exclude\_tags](#input\_monitor\_exclude\_tags) | Tags to be excluded in the monitoring query. Specify in key:value format | `list(string)` | `[]` | no |
 | <a name="input_monitor_include_tags"></a> [monitor\_include\_tags](#input\_monitor\_include\_tags) | Tags to be included in the monitoring query. Specify in key:value format | `list(string)` | `[]` | no |
 | <a name="input_new_group_delay"></a> [new\_group\_delay](#input\_new\_group\_delay) | Delay in seconds before generating alerts for a new resource | `number` | `300` | no |
 | <a name="input_notify_alert_override"></a> [notify\_alert\_override](#input\_notify\_alert\_override) | List of notifications for alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_crit_override"></a> [notify\_crit\_override](#input\_notify\_crit\_override) | List of notifications for 24x7 alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_default"></a> [notify\_default](#input\_notify\_default) | List of alert notifications (can be overridden based on alert type) | `list(string)` | n/a | yes |
 | <a name="input_notify_no_data"></a> [notify\_no\_data](#input\_notify\_no\_data) | Alert if no matching data is found | `bool` | `false` | no |
 | <a name="input_notify_nodata_override"></a> [notify\_nodata\_override](#input\_notify\_nodata\_override) | List of notifications for no data (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_nonprod_override"></a> [notify\_nonprod\_override](#input\_notify\_nonprod\_override) | List of notifications for non-prod alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_prod_override"></a> [notify\_prod\_override](#input\_notify\_prod\_override) | List of notifications for 12x5 prod alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_recovery_override"></a> [notify\_recovery\_override](#input\_notify\_recovery\_override) | List of notifications for alert recovery (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_warn_override"></a> [notify\_warn\_override](#input\_notify\_warn\_override) | List of notifications for alerts in warning threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_renotify_interval"></a> [renotify\_interval](#input\_renotify\_interval) | Interval in minutes to re-send notifications about an alert | `number` | `0` | no |
 | <a name="input_runbook_link"></a> [runbook\_link](#input\_runbook\_link) | Runbook link to include in message | `string` | `null` | no |
 | <a name="input_service"></a> [service](#input\_service) | Service associated with the monitored resource (leave blank to omit tag) | `string` | `null` | no |
-| <a name="input_status_failed_check_enabled"></a> [status\_failed\_check\_enabled](#input\_status\_failed\_check\_enabled) | Enable ec2 instance status check monitor | `bool` | `false` | no |
+| <a name="input_status_failed_check_enabled"></a> [status\_failed\_check\_enabled](#input\_status\_failed\_check\_enabled) | Enable ec2 instance status check monitor | `bool` | `true` | no |
 | <a name="input_status_failed_check_evaluation_window"></a> [status\_failed\_check\_evaluation\_window](#input\_status\_failed\_check\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
 | <a name="input_status_failed_check_no_data_window"></a> [status\_failed\_check\_no\_data\_window](#input\_status\_failed\_check\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
-| <a name="input_status_failed_check_threshold_critical"></a> [status\_failed\_check\_threshold\_critical](#input\_status\_failed\_check\_threshold\_critical) | Critical threshold (percentage, 0-100) | `number` | `75` | no |
-| <a name="input_status_failed_check_threshold_warning"></a> [status\_failed\_check\_threshold\_warning](#input\_status\_failed\_check\_threshold\_warning) | Warning threshold (percentage, 0-100) | `number` | `25` | no |
-| <a name="input_status_failed_instance_enabled"></a> [status\_failed\_instance\_enabled](#input\_status\_failed\_instance\_enabled) | Enable instance status check monitor | `bool` | `false` | no |
+| <a name="input_status_failed_check_use_message"></a> [status\_failed\_check\_use\_message](#input\_status\_failed\_check\_use\_message) | Whether to use the query alert base message for ec2 instance status check monitor | `bool` | `false` | no |
+| <a name="input_status_failed_instance_enabled"></a> [status\_failed\_instance\_enabled](#input\_status\_failed\_instance\_enabled) | Enable instance status check monitor | `bool` | `true` | no |
 | <a name="input_status_failed_instance_evaluation_window"></a> [status\_failed\_instance\_evaluation\_window](#input\_status\_failed\_instance\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
 | <a name="input_status_failed_instance_no_data_window"></a> [status\_failed\_instance\_no\_data\_window](#input\_status\_failed\_instance\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
-| <a name="input_status_failed_instance_threshold_critical"></a> [status\_failed\_instance\_threshold\_critical](#input\_status\_failed\_instance\_threshold\_critical) | Critical threshold (percentage, 0-100) | `number` | `75` | no |
-| <a name="input_status_failed_instance_threshold_warning"></a> [status\_failed\_instance\_threshold\_warning](#input\_status\_failed\_instance\_threshold\_warning) | Warning threshold (percentage, 0-100) | `number` | `25` | no |
-| <a name="input_status_failed_system_enabled"></a> [status\_failed\_system\_enabled](#input\_status\_failed\_system\_enabled) | Enable instance system failure monitor | `bool` | `false` | no |
+| <a name="input_status_failed_instance_use_message"></a> [status\_failed\_instance\_use\_message](#input\_status\_failed\_instance\_use\_message) | Whether to use the query alert base message for instance status check monitor | `bool` | `false` | no |
+| <a name="input_status_failed_system_enabled"></a> [status\_failed\_system\_enabled](#input\_status\_failed\_system\_enabled) | Enable instance system failure monitor | `bool` | `true` | no |
 | <a name="input_status_failed_system_evaluation_window"></a> [status\_failed\_system\_evaluation\_window](#input\_status\_failed\_system\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
 | <a name="input_status_failed_system_no_data_window"></a> [status\_failed\_system\_no\_data\_window](#input\_status\_failed\_system\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
-| <a name="input_status_failed_system_threshold_critical"></a> [status\_failed\_system\_threshold\_critical](#input\_status\_failed\_system\_threshold\_critical) | Critical threshold (percentage, 0-100) | `number` | `75` | no |
-| <a name="input_status_failed_system_threshold_warning"></a> [status\_failed\_system\_threshold\_warning](#input\_status\_failed\_system\_threshold\_warning) | Warning threshold (percentage, 0-100) | `number` | `25` | no |
-| <a name="input_status_failed_volume_enabled"></a> [status\_failed\_volume\_enabled](#input\_status\_failed\_volume\_enabled) | Enable attached volume status monitor | `bool` | `false` | no |
+| <a name="input_status_failed_system_use_message"></a> [status\_failed\_system\_use\_message](#input\_status\_failed\_system\_use\_message) | Whether to use the query alert base message for instance system failure monitor | `bool` | `false` | no |
+| <a name="input_status_failed_volume_enabled"></a> [status\_failed\_volume\_enabled](#input\_status\_failed\_volume\_enabled) | Enable attached volume status monitor | `bool` | `true` | no |
 | <a name="input_status_failed_volume_evaluation_window"></a> [status\_failed\_volume\_evaluation\_window](#input\_status\_failed\_volume\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
 | <a name="input_status_failed_volume_no_data_window"></a> [status\_failed\_volume\_no\_data\_window](#input\_status\_failed\_volume\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
-| <a name="input_status_failed_volume_threshold_critical"></a> [status\_failed\_volume\_threshold\_critical](#input\_status\_failed\_volume\_threshold\_critical) | Critical threshold (percentage, 0-100) | `number` | `75` | no |
-| <a name="input_status_failed_volume_threshold_warning"></a> [status\_failed\_volume\_threshold\_warning](#input\_status\_failed\_volume\_threshold\_warning) | Warning threshold (percentage, 0-100) | `number` | `25` | no |
+| <a name="input_status_failed_volume_use_message"></a> [status\_failed\_volume\_use\_message](#input\_status\_failed\_volume\_use\_message) | Whether to use the query alert base message for attached volume status monitor | `bool` | `false` | no |
 | <a name="input_team"></a> [team](#input\_team) | Team supporting the monitored resource (leave blank to omit tag) | `string` | `null` | no |
 | <a name="input_timeout_h"></a> [timeout\_h](#input\_timeout\_h) | Auto-resolve alert in specified hours if condition no longer matches | `number` | `0` | no |
 | <a name="input_title_prefix"></a> [title\_prefix](#input\_title\_prefix) | Prefix all alerts with specified value in brackets | `string` | `null` | no |
diff --git a/aws/ec2/main.tf b/aws/ec2/main.tf
index 3a75582..337c979 100644
--- a/aws/ec2/main.tf
+++ b/aws/ec2/main.tf
@@ -4,7 +4,7 @@ locals {
   monitor_warn_default_priority   = null
   monitor_nodata_default_priority = null
 
-  title_prefix = "${var.title_prefix == null ? "" : "[${var.title_prefix}]"}"
+  title_prefix = var.title_prefix == null ? "" : "[${var.title_prefix}]"
   title_suffix = var.title_suffix == null ? "" : " (${var.title_suffix})"
 }
 
@@ -12,8 +12,8 @@ resource "datadog_monitor" "status_failed_check" {
   count = var.status_failed_check_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "EC2 instance status - status check failure - {{name.name}}({{instance_id.name}})", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.status_failed_check_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -26,7 +26,7 @@ resource "datadog_monitor" "status_failed_check" {
 
   query = <<END
     max(${var.status_failed_check_evaluation_window}):
-      max:aws.ec2.status_check_failed${local.query_filter} by {aws_account,env,instance_id,name,region}
+      max:aws.ec2.status_check_failed${local.query_filter} by {aws_account,env,instance_id,name,region,env,datadog_managed}
     >= 1
 END
 
@@ -39,8 +39,8 @@ resource "datadog_monitor" "status_failed_instance" {
   count = var.status_failed_instance_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "EC2 instance status - instance failure - {{name.name}}({{instance_id.name}})", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.status_failed_instance_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -53,7 +53,7 @@ resource "datadog_monitor" "status_failed_instance" {
 
   query = <<END
     max(${var.status_failed_instance_evaluation_window}):
-      max:aws.ec2.status_check_failed_instance${local.query_filter} by {aws_account,env,instance_id,name,region}
+      max:aws.ec2.status_check_failed_instance${local.query_filter} by {aws_account,env,instance_id,name,region,env,datadog_managed}
     >= 1
 END
 
@@ -66,8 +66,8 @@ resource "datadog_monitor" "status_failed_system" {
   count = var.status_failed_system_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "EC2 instance status - host failure - {{name.name}}({{instance_id.name}})", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.status_failed_system_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -80,7 +80,7 @@ resource "datadog_monitor" "status_failed_system" {
 
   query = <<END
     max(${var.status_failed_system_evaluation_window}):
-      max:aws.ec2.status_check_failed_system${local.query_filter} by {aws_account,env,instance_id,name,region}
+      max:aws.ec2.status_check_failed_system${local.query_filter} by {aws_account,env,instance_id,name,region,env,datadog_managed}
     >= 1
 END
 
@@ -93,8 +93,8 @@ resource "datadog_monitor" "status_failed_volume" {
   count = var.status_failed_volume_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "EC2 instance status - volume failure - {{name.name}}({{instance_id.name}})", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.status_failed_volume_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -107,7 +107,7 @@ resource "datadog_monitor" "status_failed_volume" {
 
   query = <<END
     max(${var.status_failed_volume_evaluation_window}):
-      max:aws.ec2.status_check_failed_attached_ebs${local.query_filter} by {aws_account,env,instance_id,name,region}
+      max:aws.ec2.status_check_failed_attached_ebs${local.query_filter} by {aws_account,env,instance_id,name,region,env,datadog_managed}
     >= 1
 END
 
diff --git a/aws/ec2/variables.tf b/aws/ec2/variables.tf
index b27bf0d..6aaed78 100644
--- a/aws/ec2/variables.tf
+++ b/aws/ec2/variables.tf
@@ -34,6 +34,12 @@ variable "status_failed_check_no_data_window" {
   type        = number
 }
 
+variable "status_failed_check_use_message" {
+  description = "Whether to use the query alert base message for ec2 instance status check monitor"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # Instance status check
 ########################################
@@ -55,6 +61,12 @@ variable "status_failed_instance_no_data_window" {
   type        = number
 }
 
+variable "status_failed_instance_use_message" {
+  description = "Whether to use the query alert base message for instance status check monitor"
+  type        = bool
+  default     = false
+}
+
 #####################################
 # system host status check
 ########################################
@@ -76,6 +88,12 @@ variable "status_failed_system_no_data_window" {
   type        = number
 }
 
+variable "status_failed_system_use_message" {
+  description = "Whether to use the query alert base message for instance system failure monitor"
+  type        = bool
+  default     = false
+}
+
 #####################################
 # Attached volume status check
 ########################################
@@ -96,3 +114,9 @@ variable "status_failed_volume_no_data_window" {
   description = "No data threshold (in minutes, 0 to disable)"
   type        = number
 }
+
+variable "status_failed_volume_use_message" {
+  description = "Whether to use the query alert base message for attached volume status monitor"
+  type        = bool
+  default     = false
+}
diff --git a/aws/ecs-cluster/README.md b/aws/ecs-cluster/README.md
index 479ac5c..cdbab68 100644
--- a/aws/ecs-cluster/README.md
+++ b/aws/ecs-cluster/README.md
@@ -19,7 +19,7 @@ Configures the following for ECS clusters based on tags matches:
 
 | Name | Version |
 |------|---------|
-| <a name="provider_datadog"></a> [datadog](#provider\_datadog) | >= 3.37 |
+| <a name="provider_datadog"></a> [datadog](#provider\_datadog) | 3.37.0 |
 
 ## Modules
 
@@ -44,6 +44,7 @@ No modules.
 | <a name="input_agent_status_no_data_window"></a> [agent\_status\_no\_data\_window](#input\_agent\_status\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
 | <a name="input_agent_status_threshold_critical"></a> [agent\_status\_threshold\_critical](#input\_agent\_status\_threshold\_critical) | Critical threshold | `number` | `5` | no |
 | <a name="input_agent_status_threshold_warning"></a> [agent\_status\_threshold\_warning](#input\_agent\_status\_threshold\_warning) | Warning threshold | `number` | `3` | no |
+| <a name="input_agent_status_use_message"></a> [agent\_status\_use\_message](#input\_agent\_status\_use\_message) | Whether to use the query alert base message for agent status monitor | `bool` | `false` | no |
 | <a name="input_alert_critical_priority"></a> [alert\_critical\_priority](#input\_alert\_critical\_priority) | Priority for alerts within critical threshold (P1-P5, uses monitor defaults if not specified) | `string` | `null` | no |
 | <a name="input_alert_message"></a> [alert\_message](#input\_alert\_message) | Message to prepend to alert notifications | `string` | `"Alert"` | no |
 | <a name="input_alert_nodata_priority"></a> [alert\_nodata\_priority](#input\_alert\_nodata\_priority) | Priority for alerts within warning threshold (P1-P5, uses monitor defaults if not specified) | `string` | `null` | no |
@@ -59,26 +60,32 @@ No modules.
 | <a name="input_cpu_utilization_anomaly_threshold_critical"></a> [cpu\_utilization\_anomaly\_threshold\_critical](#input\_cpu\_utilization\_anomaly\_threshold\_critical) | Critical threshold (percent) | `number` | `null` | no |
 | <a name="input_cpu_utilization_anomaly_threshold_warning"></a> [cpu\_utilization\_anomaly\_threshold\_warning](#input\_cpu\_utilization\_anomaly\_threshold\_warning) | Warning threshold (percent) | `number` | `null` | no |
 | <a name="input_cpu_utilization_anomaly_trigger_window"></a> [cpu\_utilization\_anomaly\_trigger\_window](#input\_cpu\_utilization\_anomaly\_trigger\_window) | Trigger window for anomaly monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_1h"` | no |
+| <a name="input_cpu_utilization_anomaly_use_message"></a> [cpu\_utilization\_anomaly\_use\_message](#input\_cpu\_utilization\_anomaly\_use\_message) | Whether to use the query alert base message for CPU utilization anomaly monitor | `bool` | `false` | no |
 | <a name="input_cpu_utilization_enabled"></a> [cpu\_utilization\_enabled](#input\_cpu\_utilization\_enabled) | Enable cluster CPU utilization monitor | `bool` | `false` | no |
 | <a name="input_cpu_utilization_evaluation_window"></a> [cpu\_utilization\_evaluation\_window](#input\_cpu\_utilization\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
 | <a name="input_cpu_utilization_no_data_window"></a> [cpu\_utilization\_no\_data\_window](#input\_cpu\_utilization\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
 | <a name="input_cpu_utilization_threshold_critical"></a> [cpu\_utilization\_threshold\_critical](#input\_cpu\_utilization\_threshold\_critical) | Critical threshold (percent) | `number` | `90` | no |
 | <a name="input_cpu_utilization_threshold_warning"></a> [cpu\_utilization\_threshold\_warning](#input\_cpu\_utilization\_threshold\_warning) | Warning threshold (percent) | `number` | `80` | no |
+| <a name="input_cpu_utilization_use_message"></a> [cpu\_utilization\_use\_message](#input\_cpu\_utilization\_use\_message) | Whether to use the query alert base message for CPU utilization monitor | `bool` | `false` | no |
 | <a name="input_dashboard_link"></a> [dashboard\_link](#input\_dashboard\_link) | Dashboard link to include in message | `string` | `null` | no |
-| <a name="input_env"></a> [env](#input\_env) | Environment the monitored resource is in (leave blank to omit tag) | `string` | n/a | yes |
+| <a name="input_env"></a> [env](#input\_env) | Environment the monitored resource is in (leave blank to omit tag) | `string` | `null` | no |
 | <a name="input_evaluation_delay"></a> [evaluation\_delay](#input\_evaluation\_delay) | Monitor evaluation delay (see [https://docs.datadoghq.com/monitors/configuration/?tab=thresholdalert#set-alert-conditions](Datadog Docs)) | `number` | `900` | no |
 | <a name="input_memory_reservation_enabled"></a> [memory\_reservation\_enabled](#input\_memory\_reservation\_enabled) | Enable cluster memory reservation monitor | `bool` | `false` | no |
 | <a name="input_memory_reservation_evaluation_window"></a> [memory\_reservation\_evaluation\_window](#input\_memory\_reservation\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_15m"` | no |
 | <a name="input_memory_reservation_no_data_window"></a> [memory\_reservation\_no\_data\_window](#input\_memory\_reservation\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
 | <a name="input_memory_reservation_threshold_critical"></a> [memory\_reservation\_threshold\_critical](#input\_memory\_reservation\_threshold\_critical) | Critical threshold (percent) | `number` | `90` | no |
 | <a name="input_memory_reservation_threshold_warning"></a> [memory\_reservation\_threshold\_warning](#input\_memory\_reservation\_threshold\_warning) | Warning threshold (percent) | `number` | `80` | no |
+| <a name="input_memory_reservation_use_message"></a> [memory\_reservation\_use\_message](#input\_memory\_reservation\_use\_message) | Whether to use the query alert base message for memory reservation monitor | `bool` | `false` | no |
 | <a name="input_monitor_exclude_tags"></a> [monitor\_exclude\_tags](#input\_monitor\_exclude\_tags) | Tags to be excluded in the monitoring query. Specify in key:value format | `list(string)` | `[]` | no |
 | <a name="input_monitor_include_tags"></a> [monitor\_include\_tags](#input\_monitor\_include\_tags) | Tags to be included in the monitoring query. Specify in key:value format | `list(string)` | `[]` | no |
 | <a name="input_new_group_delay"></a> [new\_group\_delay](#input\_new\_group\_delay) | Delay in seconds before generating alerts for a new resource | `number` | `300` | no |
 | <a name="input_notify_alert_override"></a> [notify\_alert\_override](#input\_notify\_alert\_override) | List of notifications for alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_crit_override"></a> [notify\_crit\_override](#input\_notify\_crit\_override) | List of notifications for 24x7 alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_default"></a> [notify\_default](#input\_notify\_default) | List of alert notifications (can be overridden based on alert type) | `list(string)` | n/a | yes |
 | <a name="input_notify_no_data"></a> [notify\_no\_data](#input\_notify\_no\_data) | Alert if no matching data is found | `bool` | `false` | no |
 | <a name="input_notify_nodata_override"></a> [notify\_nodata\_override](#input\_notify\_nodata\_override) | List of notifications for no data (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_nonprod_override"></a> [notify\_nonprod\_override](#input\_notify\_nonprod\_override) | List of notifications for non-prod alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_prod_override"></a> [notify\_prod\_override](#input\_notify\_prod\_override) | List of notifications for 12x5 prod alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_recovery_override"></a> [notify\_recovery\_override](#input\_notify\_recovery\_override) | List of notifications for alert recovery (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_warn_override"></a> [notify\_warn\_override](#input\_notify\_warn\_override) | List of notifications for alerts in warning threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_renotify_interval"></a> [renotify\_interval](#input\_renotify\_interval) | Interval in minutes to re-send notifications about an alert | `number` | `0` | no |
diff --git a/aws/ecs-cluster/main.tf b/aws/ecs-cluster/main.tf
index 82da113..60e5208 100644
--- a/aws/ecs-cluster/main.tf
+++ b/aws/ecs-cluster/main.tf
@@ -5,7 +5,7 @@ locals {
   monitor_warn_default_priority   = null
   monitor_nodata_default_priority = null
 
-  title_prefix = "${var.title_prefix == null ? "" : "[${var.title_prefix}]"}"
+  title_prefix = var.title_prefix == null ? "" : "[${var.title_prefix}]"
   title_suffix = var.title_suffix == null ? "" : " (${var.title_suffix})"
 }
 
@@ -13,10 +13,10 @@ resource "datadog_monitor" "agent_status" {
   count = var.agent_status_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "ECS Agent disconnected - {{clustername.name}}", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.agent_status_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
-  type    = "service check"
+  type         = "service check"
 
   evaluation_delay    = var.evaluation_delay
   new_group_delay     = var.new_group_delay
@@ -27,7 +27,7 @@ resource "datadog_monitor" "agent_status" {
   timeout_h           = var.timeout_h
 
   query = <<EOQ
-    "aws.ecs.agent_connected"${local.service_filter}.by("clustername","instance_id").last(6).count_by_status()
+    "aws.ecs.agent_connected"${local.service_filter}.by("clustername","instance_id",env,datadog_managed).last(6).count_by_status()
 EOQ
 
   monitor_thresholds {
@@ -40,8 +40,8 @@ resource "datadog_monitor" "cpu_utilization" {
   count = var.cpu_utilization_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "ECS Cluster CPU Utilization - {{clustername.name}} - {{value}}%", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.cpu_utilization_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -55,7 +55,7 @@ resource "datadog_monitor" "cpu_utilization" {
 
   query = <<END
     min(${var.cpu_utilization_evaluation_window}):
-      avg:aws.ecs.cluster.cpuutilization${local.query_filter} by {clustername,region,aws_account,env}
+      avg:aws.ecs.cluster.cpuutilization${local.query_filter} by {clustername,region,aws_account,env,datadog_managed}
     > ${var.cpu_utilization_threshold_critical}
 END
 
@@ -69,8 +69,8 @@ resource "datadog_monitor" "cpu_utilization_anomaly" {
   count = var.cpu_utilization_anomaly_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "ECS cluster CPU utilization anomalous activity - {{clustername.name}}", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.cpu_utilization_anomaly_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -84,7 +84,7 @@ resource "datadog_monitor" "cpu_utilization_anomaly" {
 
   query = <<END
     avg(${var.cpu_utilization_anomaly_evaluation_window}):anomalies(
-      avg:aws.ecs.cluster.cpuutilization${local.query_filter} by {clustername,region,aws_account,env}, 'agile', ${var.cpu_utilization_anomaly_deviations},
+      avg:aws.ecs.cluster.cpuutilization${local.query_filter} by {clustername,region,aws_account,env,datadog_managed}, 'agile', ${var.cpu_utilization_anomaly_deviations},
       direction='above', count_default_zero='true', interval=${var.cpu_utilization_anomaly_rollup},
       seasonality='${var.cpu_utilization_anomaly_seasonality}'
     ) >= ${var.cpu_utilization_anomaly_threshold_critical}
@@ -105,8 +105,8 @@ resource "datadog_monitor" "memory_reservation" {
   count = var.memory_reservation_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "ECS Cluster Memory Reservation High - {{clustername.name}} - {{value}}%", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.memory_reservation_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -120,7 +120,7 @@ resource "datadog_monitor" "memory_reservation" {
 
   query = <<END
     min(${var.memory_reservation_evaluation_window}):
-      avg:aws.ecs.cluster.memory_reservation${local.query_filter} by {clustername,region,aws_account,env}
+      avg:aws.ecs.cluster.memory_reservation${local.query_filter} by {clustername,region,aws_account,env,datadog_managed}
     > ${var.memory_reservation_threshold_critical}
 END
 
diff --git a/aws/ecs-cluster/variables.tf b/aws/ecs-cluster/variables.tf
index e6cd277..6671c12 100644
--- a/aws/ecs-cluster/variables.tf
+++ b/aws/ecs-cluster/variables.tf
@@ -46,6 +46,12 @@ variable "agent_status_threshold_warning" {
   type        = number
 }
 
+variable "agent_status_use_message" {
+  description = "Whether to use the query alert base message for agent status monitor"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # Cluster CPU Utilization
 ########################################
@@ -79,6 +85,12 @@ variable "cpu_utilization_threshold_warning" {
   type        = number
 }
 
+variable "cpu_utilization_use_message" {
+  description = "Whether to use the query alert base message for CPU utilization monitor"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # CPU Utilization (anomaly detection)
 ########################################
@@ -142,6 +154,12 @@ variable "cpu_utilization_anomaly_threshold_warning" {
   type        = number
 }
 
+variable "cpu_utilization_anomaly_use_message" {
+  description = "Whether to use the query alert base message for CPU utilization anomaly monitor"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # Cluster Memory Reservation
 ########################################
@@ -173,3 +191,9 @@ variable "memory_reservation_threshold_warning" {
   description = "Warning threshold (percent)"
   type        = number
 }
+
+variable "memory_reservation_use_message" {
+  description = "Whether to use the query alert base message for memory reservation monitor"
+  type        = bool
+  default     = false
+}
diff --git a/aws/ecs-fargate/README.md b/aws/ecs-fargate/README.md
index fc4875e..9977961 100644
--- a/aws/ecs-fargate/README.md
+++ b/aws/ecs-fargate/README.md
@@ -19,7 +19,7 @@ Configures the following for ECS Fargate tasks based on tag matches:
 
 | Name | Version |
 |------|---------|
-| <a name="provider_datadog"></a> [datadog](#provider\_datadog) | >= 3.37 |
+| <a name="provider_datadog"></a> [datadog](#provider\_datadog) | 3.37.0 |
 
 ## Modules
 
@@ -54,32 +54,39 @@ No modules.
 | <a name="input_cpu_utilization_anomaly_threshold_critical"></a> [cpu\_utilization\_anomaly\_threshold\_critical](#input\_cpu\_utilization\_anomaly\_threshold\_critical) | Critical threshold (percent) | `number` | `null` | no |
 | <a name="input_cpu_utilization_anomaly_threshold_warning"></a> [cpu\_utilization\_anomaly\_threshold\_warning](#input\_cpu\_utilization\_anomaly\_threshold\_warning) | Warning threshold (percent) | `number` | `null` | no |
 | <a name="input_cpu_utilization_anomaly_trigger_window"></a> [cpu\_utilization\_anomaly\_trigger\_window](#input\_cpu\_utilization\_anomaly\_trigger\_window) | Trigger window for anomaly monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_1h"` | no |
+| <a name="input_cpu_utilization_anomaly_use_message"></a> [cpu\_utilization\_anomaly\_use\_message](#input\_cpu\_utilization\_anomaly\_use\_message) | Whether to use the query alert base message for CPU utilization anomaly monitor | `bool` | `false` | no |
 | <a name="input_cpu_utilization_enabled"></a> [cpu\_utilization\_enabled](#input\_cpu\_utilization\_enabled) | Enable Fargate task CPU utilization monitor | `bool` | `false` | no |
 | <a name="input_cpu_utilization_evaluation_window"></a> [cpu\_utilization\_evaluation\_window](#input\_cpu\_utilization\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
 | <a name="input_cpu_utilization_no_data_window"></a> [cpu\_utilization\_no\_data\_window](#input\_cpu\_utilization\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
 | <a name="input_cpu_utilization_threshold_critical"></a> [cpu\_utilization\_threshold\_critical](#input\_cpu\_utilization\_threshold\_critical) | Critical threshold (percent) | `number` | `90` | no |
 | <a name="input_cpu_utilization_threshold_warning"></a> [cpu\_utilization\_threshold\_warning](#input\_cpu\_utilization\_threshold\_warning) | Warning threshold (percent) | `number` | `80` | no |
+| <a name="input_cpu_utilization_use_message"></a> [cpu\_utilization\_use\_message](#input\_cpu\_utilization\_use\_message) | Whether to use the query alert base message for CPU utilization monitor | `bool` | `false` | no |
 | <a name="input_dashboard_link"></a> [dashboard\_link](#input\_dashboard\_link) | Dashboard link to include in message | `string` | `null` | no |
-| <a name="input_env"></a> [env](#input\_env) | Environment the monitored resource is in (leave blank to omit tag) | `string` | n/a | yes |
+| <a name="input_env"></a> [env](#input\_env) | Environment the monitored resource is in (leave blank to omit tag) | `string` | `null` | no |
 | <a name="input_evaluation_delay"></a> [evaluation\_delay](#input\_evaluation\_delay) | Monitor evaluation delay (see [https://docs.datadoghq.com/monitors/configuration/?tab=thresholdalert#set-alert-conditions](Datadog Docs)) | `number` | `900` | no |
-| <a name="input_fargate_check_enabled"></a> [fargate\_check\_enabled](#input\_fargate\_check\_enabled) | Enable Fargate check monitor | `bool` | `false` | no |
+| <a name="input_fargate_check_enabled"></a> [fargate\_check\_enabled](#input\_fargate\_check\_enabled) | Enable Fargate check monitor | `bool` | `true` | no |
 | <a name="input_fargate_check_evaluation_window"></a> [fargate\_check\_evaluation\_window](#input\_fargate\_check\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
 | <a name="input_fargate_check_group_by"></a> [fargate\_check\_group\_by](#input\_fargate\_check\_group\_by) | Tag to group alerts by (will result in multiple alerts being generated based on tag cardinality) | `string` | `"*"` | no |
 | <a name="input_fargate_check_no_data_window"></a> [fargate\_check\_no\_data\_window](#input\_fargate\_check\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
 | <a name="input_fargate_check_threshold_critical"></a> [fargate\_check\_threshold\_critical](#input\_fargate\_check\_threshold\_critical) | Critical threshold | `number` | `5` | no |
 | <a name="input_fargate_check_threshold_warning"></a> [fargate\_check\_threshold\_warning](#input\_fargate\_check\_threshold\_warning) | Warning threshold | `number` | `3` | no |
+| <a name="input_fargate_check_use_message"></a> [fargate\_check\_use\_message](#input\_fargate\_check\_use\_message) | Whether to use the query alert base message for Fargate check monitor | `bool` | `false` | no |
 | <a name="input_memory_utilization_enabled"></a> [memory\_utilization\_enabled](#input\_memory\_utilization\_enabled) | Enable Fargate task memory utilization monitor | `bool` | `false` | no |
 | <a name="input_memory_utilization_evaluation_window"></a> [memory\_utilization\_evaluation\_window](#input\_memory\_utilization\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_15m"` | no |
 | <a name="input_memory_utilization_no_data_window"></a> [memory\_utilization\_no\_data\_window](#input\_memory\_utilization\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
 | <a name="input_memory_utilization_threshold_critical"></a> [memory\_utilization\_threshold\_critical](#input\_memory\_utilization\_threshold\_critical) | Critical threshold (percent) | `number` | `90` | no |
 | <a name="input_memory_utilization_threshold_warning"></a> [memory\_utilization\_threshold\_warning](#input\_memory\_utilization\_threshold\_warning) | Warning threshold (percent) | `number` | `80` | no |
+| <a name="input_memory_utilization_use_message"></a> [memory\_utilization\_use\_message](#input\_memory\_utilization\_use\_message) | Whether to use the query alert base message for memory utilization monitor | `bool` | `false` | no |
 | <a name="input_monitor_exclude_tags"></a> [monitor\_exclude\_tags](#input\_monitor\_exclude\_tags) | Tags to be excluded in the monitoring query. Specify in key:value format | `list(string)` | `[]` | no |
 | <a name="input_monitor_include_tags"></a> [monitor\_include\_tags](#input\_monitor\_include\_tags) | Tags to be included in the monitoring query. Specify in key:value format | `list(string)` | `[]` | no |
 | <a name="input_new_group_delay"></a> [new\_group\_delay](#input\_new\_group\_delay) | Delay in seconds before generating alerts for a new resource | `number` | `300` | no |
 | <a name="input_notify_alert_override"></a> [notify\_alert\_override](#input\_notify\_alert\_override) | List of notifications for alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_crit_override"></a> [notify\_crit\_override](#input\_notify\_crit\_override) | List of notifications for 24x7 alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_default"></a> [notify\_default](#input\_notify\_default) | List of alert notifications (can be overridden based on alert type) | `list(string)` | n/a | yes |
 | <a name="input_notify_no_data"></a> [notify\_no\_data](#input\_notify\_no\_data) | Alert if no matching data is found | `bool` | `false` | no |
 | <a name="input_notify_nodata_override"></a> [notify\_nodata\_override](#input\_notify\_nodata\_override) | List of notifications for no data (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_nonprod_override"></a> [notify\_nonprod\_override](#input\_notify\_nonprod\_override) | List of notifications for non-prod alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_prod_override"></a> [notify\_prod\_override](#input\_notify\_prod\_override) | List of notifications for 12x5 prod alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_recovery_override"></a> [notify\_recovery\_override](#input\_notify\_recovery\_override) | List of notifications for alert recovery (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_warn_override"></a> [notify\_warn\_override](#input\_notify\_warn\_override) | List of notifications for alerts in warning threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_renotify_interval"></a> [renotify\_interval](#input\_renotify\_interval) | Interval in minutes to re-send notifications about an alert | `number` | `0` | no |
diff --git a/aws/ecs-fargate/main.tf b/aws/ecs-fargate/main.tf
index 7bd1431..5b192a1 100644
--- a/aws/ecs-fargate/main.tf
+++ b/aws/ecs-fargate/main.tf
@@ -5,7 +5,7 @@ locals {
   monitor_warn_default_priority   = null
   monitor_nodata_default_priority = null
 
-  title_prefix = "${var.title_prefix == null ? "" : "[${var.title_prefix}]"}"
+  title_prefix = var.title_prefix == null ? "" : "[${var.title_prefix}]"
   title_suffix = var.title_suffix == null ? "" : " (${var.title_suffix})"
 }
 
@@ -13,8 +13,8 @@ resource "datadog_monitor" "fargate_check" {
   count = var.fargate_check_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "Fargate service not responding", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.fargate_check_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "service check"
 
@@ -40,9 +40,9 @@ END
 resource "datadog_monitor" "cpu_utilization" {
   count = var.cpu_utilization_enabled ? 1 : 0
 
-  name         = join("", [local.title_prefix, "ECS Fargate task CPU utilization", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  name         = join("", [local.title_prefix, "ECS Fargate task CPU utilization - {{ecs_cluster}} ({{task_family}})", local.title_suffix])
+  include_tags = false
+  message      = var.cpu_utilization_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -56,7 +56,7 @@ resource "datadog_monitor" "cpu_utilization" {
 
   query = <<END
     avg(${var.cpu_utilization_evaluation_window}):
-      avg:ecs.fargate.cpu.percent${local.query_filter} by {ecs_container_name,task_family,region,aws_account,env}
+      avg:ecs.fargate.cpu.percent${local.query_filter} by {ecs_cluster,ecs_container_name,task_family,region,aws_account,env,datadog_managed}
     > ${var.cpu_utilization_threshold_critical}
 END
 
@@ -69,9 +69,9 @@ END
 resource "datadog_monitor" "cpu_utilization_anomaly" {
   count = var.cpu_utilization_anomaly_enabled ? 1 : 0
 
-  name         = join("", [local.title_prefix, "ECS service CPU utilization anomalous activity", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  name         = join("", [local.title_prefix, "ECS service CPU utilization anomalous activity - {{ecs_cluster}} ({{task_family}})", local.title_suffix])
+  include_tags = false
+  message      = var.cpu_utilization_anomaly_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -85,7 +85,7 @@ resource "datadog_monitor" "cpu_utilization_anomaly" {
 
   query = <<END
     avg(${var.cpu_utilization_anomaly_evaluation_window}):anomalies(
-      avg:ecs.fargate.cpu.percent${local.query_filter} by {servicename,region,aws_account,env}, 'agile', ${var.cpu_utilization_anomaly_deviations},
+      avg:ecs.fargate.cpu.percent${local.query_filter} by {ecs_cluster,ecs_container_name,region,aws_account,env,datadog_managed,task_family}, 'agile', ${var.cpu_utilization_anomaly_deviations},
       direction='above', count_default_zero='true', interval=${var.cpu_utilization_anomaly_rollup},
       seasonality='${var.cpu_utilization_anomaly_seasonality}'
     ) >= ${var.cpu_utilization_anomaly_threshold_critical}
@@ -105,9 +105,9 @@ END
 resource "datadog_monitor" "memory_utilization" {
   count = var.memory_utilization_enabled ? 1 : 0
 
-  name         = join("", [local.title_prefix, "ECS Fargate task memory utilization", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  name         = join("", [local.title_prefix, "ECS Fargate task memory utilization - {{ecs_cluster}} ({{task_family}})", local.title_suffix])
+  include_tags = false
+  message      = var.memory_utilization_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -121,8 +121,8 @@ resource "datadog_monitor" "memory_utilization" {
 
   query = <<END
     avg(${var.memory_utilization_evaluation_window}):(
-      avg:ecs.fargate.mem.usage${local.query_filter} by {ecs_container_name,task_family,region,aws_account,env} /
-      avg:ecs.fargate.mem.limit${local.query_filter} by {ecs_container_name,task_family,region,aws_account,env}
+      avg:ecs.fargate.mem.usage${local.query_filter} by {ecs_cluster,ecs_container_name,task_family,region,aws_account,env,datadog_managed} /
+      avg:ecs.fargate.mem.limit${local.query_filter} by {ecs_cluster,ecs_container_name,task_family,region,aws_account,env,datadog_managed}
     )  >= ${var.memory_utilization_threshold_critical}
 END
 
diff --git a/aws/ecs-fargate/variables.tf b/aws/ecs-fargate/variables.tf
index 844ddb0..272f46e 100644
--- a/aws/ecs-fargate/variables.tf
+++ b/aws/ecs-fargate/variables.tf
@@ -17,7 +17,7 @@ variable "base_tags" {
 # Fargate Agent Status
 ########################################
 variable "fargate_check_enabled" {
-  default     = false
+  default     = true
   description = "Enable Fargate check monitor"
   type        = bool
 }
@@ -52,6 +52,12 @@ variable "fargate_check_threshold_warning" {
   type        = number
 }
 
+variable "fargate_check_use_message" {
+  description = "Whether to use the query alert base message for Fargate check monitor"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # Fargate Task CPU Utilization
 ########################################
@@ -85,6 +91,12 @@ variable "cpu_utilization_threshold_warning" {
   type        = number
 }
 
+variable "cpu_utilization_use_message" {
+  description = "Whether to use the query alert base message for CPU utilization monitor"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # CPU Utilization (anomaly detection)
 ########################################
@@ -148,6 +160,12 @@ variable "cpu_utilization_anomaly_threshold_warning" {
   type        = number
 }
 
+variable "cpu_utilization_anomaly_use_message" {
+  description = "Whether to use the query alert base message for CPU utilization anomaly monitor"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # Fargate Task Memory Reservation
 ########################################
@@ -179,3 +197,9 @@ variable "memory_utilization_threshold_warning" {
   description = "Warning threshold (percent)"
   type        = number
 }
+
+variable "memory_utilization_use_message" {
+  description = "Whether to use the query alert base message for memory utilization monitor"
+  type        = bool
+  default     = false
+}
diff --git a/aws/ecs-service/README.md b/aws/ecs-service/README.md
index f11e074..c7db7ba 100644
--- a/aws/ecs-service/README.md
+++ b/aws/ecs-service/README.md
@@ -19,7 +19,7 @@ Configures the following for ECS services based on tag matches:
 
 | Name | Version |
 |------|---------|
-| <a name="provider_datadog"></a> [datadog](#provider\_datadog) | >= 3.37 |
+| <a name="provider_datadog"></a> [datadog](#provider\_datadog) | 3.37.0 |
 
 ## Modules
 
@@ -51,38 +51,45 @@ No modules.
 | <a name="input_cpu_utilization_anomaly_recovery_window"></a> [cpu\_utilization\_anomaly\_recovery\_window](#input\_cpu\_utilization\_anomaly\_recovery\_window) | Recovery window for anomaly monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_15m"` | no |
 | <a name="input_cpu_utilization_anomaly_rollup"></a> [cpu\_utilization\_anomaly\_rollup](#input\_cpu\_utilization\_anomaly\_rollup) | Rollup interval (must be sized based on evaluation window/span and seasonaility) | `number` | `60` | no |
 | <a name="input_cpu_utilization_anomaly_seasonality"></a> [cpu\_utilization\_anomaly\_seasonality](#input\_cpu\_utilization\_anomaly\_seasonality) | Seasonaility (hourly, daily, weekly) | `string` | `"weekly"` | no |
-| <a name="input_cpu_utilization_anomaly_threshold_critical"></a> [cpu\_utilization\_anomaly\_threshold\_critical](#input\_cpu\_utilization\_anomaly\_threshold\_critical) | Critical threshold (percent) | `number` | `null` | no |
+| <a name="input_cpu_utilization_anomaly_threshold_critical"></a> [cpu\_utilization\_anomaly\_threshold\_critical](#input\_cpu\_utilization\_anomaly\_threshold\_critical) | Critical threshold (percent) | `number` | `0.75` | no |
 | <a name="input_cpu_utilization_anomaly_threshold_warning"></a> [cpu\_utilization\_anomaly\_threshold\_warning](#input\_cpu\_utilization\_anomaly\_threshold\_warning) | Warning threshold (percent) | `number` | `null` | no |
 | <a name="input_cpu_utilization_anomaly_trigger_window"></a> [cpu\_utilization\_anomaly\_trigger\_window](#input\_cpu\_utilization\_anomaly\_trigger\_window) | Trigger window for anomaly monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_1h"` | no |
-| <a name="input_cpu_utilization_enabled"></a> [cpu\_utilization\_enabled](#input\_cpu\_utilization\_enabled) | Enable Fargate task CPU utilization monitor | `bool` | `false` | no |
+| <a name="input_cpu_utilization_anomaly_use_message"></a> [cpu\_utilization\_anomaly\_use\_message](#input\_cpu\_utilization\_anomaly\_use\_message) | Whether to use the query alert base message for CPU utilization anomaly monitor | `bool` | `false` | no |
+| <a name="input_cpu_utilization_enabled"></a> [cpu\_utilization\_enabled](#input\_cpu\_utilization\_enabled) | Enable Fargate task CPU utilization monitor | `bool` | `true` | no |
 | <a name="input_cpu_utilization_evaluation_window"></a> [cpu\_utilization\_evaluation\_window](#input\_cpu\_utilization\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
 | <a name="input_cpu_utilization_no_data_window"></a> [cpu\_utilization\_no\_data\_window](#input\_cpu\_utilization\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
 | <a name="input_cpu_utilization_threshold_critical"></a> [cpu\_utilization\_threshold\_critical](#input\_cpu\_utilization\_threshold\_critical) | Critical threshold (percent) | `string` | `90` | no |
 | <a name="input_cpu_utilization_threshold_warning"></a> [cpu\_utilization\_threshold\_warning](#input\_cpu\_utilization\_threshold\_warning) | Warning threshold (percent) | `number` | `80` | no |
+| <a name="input_cpu_utilization_use_message"></a> [cpu\_utilization\_use\_message](#input\_cpu\_utilization\_use\_message) | Whether to use the query alert base message for CPU utilization monitor | `bool` | `false` | no |
 | <a name="input_dashboard_link"></a> [dashboard\_link](#input\_dashboard\_link) | Dashboard link to include in message | `string` | `null` | no |
-| <a name="input_env"></a> [env](#input\_env) | Environment the monitored resource is in (leave blank to omit tag) | `string` | n/a | yes |
+| <a name="input_env"></a> [env](#input\_env) | Environment the monitored resource is in (leave blank to omit tag) | `string` | `null` | no |
 | <a name="input_evaluation_delay"></a> [evaluation\_delay](#input\_evaluation\_delay) | Monitor evaluation delay (see [https://docs.datadoghq.com/monitors/configuration/?tab=thresholdalert#set-alert-conditions](Datadog Docs)) | `number` | `900` | no |
 | <a name="input_memory_utilization_enabled"></a> [memory\_utilization\_enabled](#input\_memory\_utilization\_enabled) | Enable Fargate task memory utilization monitor | `bool` | `false` | no |
 | <a name="input_memory_utilization_evaluation_window"></a> [memory\_utilization\_evaluation\_window](#input\_memory\_utilization\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_15m"` | no |
 | <a name="input_memory_utilization_no_data_window"></a> [memory\_utilization\_no\_data\_window](#input\_memory\_utilization\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
 | <a name="input_memory_utilization_threshold_critical"></a> [memory\_utilization\_threshold\_critical](#input\_memory\_utilization\_threshold\_critical) | Critical threshold (percent) | `string` | `0.9` | no |
 | <a name="input_memory_utilization_threshold_warning"></a> [memory\_utilization\_threshold\_warning](#input\_memory\_utilization\_threshold\_warning) | Warning threshold (percent) | `number` | `0.8` | no |
+| <a name="input_memory_utilization_use_message"></a> [memory\_utilization\_use\_message](#input\_memory\_utilization\_use\_message) | Whether to use the query alert base message for memory utilization monitor | `bool` | `false` | no |
 | <a name="input_monitor_exclude_tags"></a> [monitor\_exclude\_tags](#input\_monitor\_exclude\_tags) | Tags to be excluded in the monitoring query. Specify in key:value format | `list(string)` | `[]` | no |
 | <a name="input_monitor_include_tags"></a> [monitor\_include\_tags](#input\_monitor\_include\_tags) | Tags to be included in the monitoring query. Specify in key:value format | `list(string)` | `[]` | no |
 | <a name="input_new_group_delay"></a> [new\_group\_delay](#input\_new\_group\_delay) | Delay in seconds before generating alerts for a new resource | `number` | `300` | no |
 | <a name="input_notify_alert_override"></a> [notify\_alert\_override](#input\_notify\_alert\_override) | List of notifications for alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_crit_override"></a> [notify\_crit\_override](#input\_notify\_crit\_override) | List of notifications for 24x7 alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_default"></a> [notify\_default](#input\_notify\_default) | List of alert notifications (can be overridden based on alert type) | `list(string)` | n/a | yes |
 | <a name="input_notify_no_data"></a> [notify\_no\_data](#input\_notify\_no\_data) | Alert if no matching data is found | `bool` | `false` | no |
 | <a name="input_notify_nodata_override"></a> [notify\_nodata\_override](#input\_notify\_nodata\_override) | List of notifications for no data (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_nonprod_override"></a> [notify\_nonprod\_override](#input\_notify\_nonprod\_override) | List of notifications for non-prod alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_prod_override"></a> [notify\_prod\_override](#input\_notify\_prod\_override) | List of notifications for 12x5 prod alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_recovery_override"></a> [notify\_recovery\_override](#input\_notify\_recovery\_override) | List of notifications for alert recovery (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_warn_override"></a> [notify\_warn\_override](#input\_notify\_warn\_override) | List of notifications for alerts in warning threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_renotify_interval"></a> [renotify\_interval](#input\_renotify\_interval) | Interval in minutes to re-send notifications about an alert | `number` | `0` | no |
 | <a name="input_runbook_link"></a> [runbook\_link](#input\_runbook\_link) | Runbook link to include in message | `string` | `null` | no |
-| <a name="input_running_tasks_enabled"></a> [running\_tasks\_enabled](#input\_running\_tasks\_enabled) | Enable running tasks monitor | `bool` | `false` | no |
+| <a name="input_running_tasks_enabled"></a> [running\_tasks\_enabled](#input\_running\_tasks\_enabled) | Enable running tasks monitor | `bool` | `true` | no |
 | <a name="input_running_tasks_evaluation_window"></a> [running\_tasks\_evaluation\_window](#input\_running\_tasks\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
 | <a name="input_running_tasks_no_data_window"></a> [running\_tasks\_no\_data\_window](#input\_running\_tasks\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
-| <a name="input_running_tasks_threshold_critical"></a> [running\_tasks\_threshold\_critical](#input\_running\_tasks\_threshold\_critical) | Critical threshold (percentage) | `number` | `0.25` | no |
+| <a name="input_running_tasks_threshold_critical"></a> [running\_tasks\_threshold\_critical](#input\_running\_tasks\_threshold\_critical) | Critical threshold (percentage) | `number` | `0.5` | no |
 | <a name="input_running_tasks_threshold_warning"></a> [running\_tasks\_threshold\_warning](#input\_running\_tasks\_threshold\_warning) | Warning threshold (percentage) | `number` | `null` | no |
+| <a name="input_running_tasks_use_message"></a> [running\_tasks\_use\_message](#input\_running\_tasks\_use\_message) | Whether to use the query alert base message for running tasks monitor | `bool` | `true` | no |
 | <a name="input_service"></a> [service](#input\_service) | Service associated with the monitored resource (leave blank to omit tag) | `string` | `null` | no |
 | <a name="input_team"></a> [team](#input\_team) | Team supporting the monitored resource (leave blank to omit tag) | `string` | `null` | no |
 | <a name="input_timeout_h"></a> [timeout\_h](#input\_timeout\_h) | Auto-resolve alert in specified hours if condition no longer matches | `number` | `0` | no |
diff --git a/aws/ecs-service/main.tf b/aws/ecs-service/main.tf
index 0365e9b..677893b 100644
--- a/aws/ecs-service/main.tf
+++ b/aws/ecs-service/main.tf
@@ -5,7 +5,7 @@ locals {
   monitor_warn_default_priority   = null
   monitor_nodata_default_priority = null
 
-  title_prefix = "${var.title_prefix == null ? "" : "[${var.title_prefix}]"}"
+  title_prefix = var.title_prefix == null ? "" : "[${var.title_prefix}]"
   title_suffix = var.title_suffix == null ? "" : " (${var.title_suffix})"
 }
 
@@ -13,8 +13,8 @@ resource "datadog_monitor" "running_tasks" {
   count = var.running_tasks_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "ECS service failed tasks - {{servicename.name}}", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.running_tasks_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -28,8 +28,8 @@ resource "datadog_monitor" "running_tasks" {
 
   query = <<END
     min(${var.running_tasks_evaluation_window}):(
-      avg:aws.ecs.service.running${local.query_filter} by {servicename,region,aws_account,env} /
-      avg:aws.ecs.service.desired${local.query_filter} by {servicename,region,aws_account,env}
+      avg:aws.ecs.service.running${local.query_filter} by {servicename,region,aws_account,env,datadog_managed} /
+      avg:aws.ecs.service.desired${local.query_filter} by {servicename,region,aws_account,env,datadog_managed}
     ) <= ${var.running_tasks_threshold_critical}
 END
 
@@ -43,8 +43,8 @@ resource "datadog_monitor" "cpu_utilization" {
   count = var.cpu_utilization_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "ECS Service CPU Utilization - {{servicename.name}} - {{value}}%", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.cpu_utilization_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -58,7 +58,7 @@ resource "datadog_monitor" "cpu_utilization" {
 
   query = <<END
     avg(${var.cpu_utilization_evaluation_window}):
-      avg:aws.ecs.cpuutilization${local.query_filter} by {servicename,region,aws_account,env}
+      avg:aws.ecs.cpuutilization${local.query_filter} by {servicename,region,aws_account,env,datadog_managed}
     >= ${var.cpu_utilization_threshold_critical}
 END
 
@@ -72,8 +72,8 @@ resource "datadog_monitor" "cpu_utilization_anomaly" {
   count = var.cpu_utilization_anomaly_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "ECS service CPU utilization anomalous activity - {{servicename.name}}", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.cpu_utilization_anomaly_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -87,7 +87,7 @@ resource "datadog_monitor" "cpu_utilization_anomaly" {
 
   query = <<END
     avg(${var.cpu_utilization_anomaly_evaluation_window}):anomalies(
-      avg:aws.ecs.cpuutilization${local.query_filter} by {servicename,region,aws_account,env}, 'agile', ${var.cpu_utilization_anomaly_deviations},
+      avg:aws.ecs.cpuutilization${local.query_filter} by {servicename,region,aws_account,env,datadog_managed}, 'agile', ${var.cpu_utilization_anomaly_deviations},
       direction='above', count_default_zero='true', interval=${var.cpu_utilization_anomaly_rollup},
       seasonality='${var.cpu_utilization_anomaly_seasonality}'
     ) >= ${var.cpu_utilization_anomaly_threshold_critical}
@@ -108,8 +108,8 @@ resource "datadog_monitor" "memory_utilization" {
   count = var.memory_utilization_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "ECS Service memory utilization - {{servicename.name}} - {{value}}%", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.memory_utilization_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -123,7 +123,7 @@ resource "datadog_monitor" "memory_utilization" {
 
   query = <<END
     min(${var.memory_utilization_evaluation_window}):
-      avg:aws.ecs.memory_utilization${local.query_filter} by {servicename,region,aws_account,env}
+      avg:aws.ecs.memory_utilization${local.query_filter} by {servicename,region,aws_account,env,datadog_managed}
     >= ${var.memory_utilization_threshold_critical}
 END
 
diff --git a/aws/ecs-service/variables.tf b/aws/ecs-service/variables.tf
index ba8fd6e..0c7baef 100644
--- a/aws/ecs-service/variables.tf
+++ b/aws/ecs-service/variables.tf
@@ -17,7 +17,7 @@ variable "base_tags" {
 # ECS service running tasks
 ########################################
 variable "running_tasks_enabled" {
-  default     = false
+  default     = true
   description = "Enable running tasks monitor"
   type        = bool
 }
@@ -35,7 +35,7 @@ variable "running_tasks_no_data_window" {
 }
 
 variable "running_tasks_threshold_critical" {
-  default     = 0.25
+  default     = 0.50
   description = "Critical threshold (percentage)"
   type        = number
 }
@@ -46,11 +46,17 @@ variable "running_tasks_threshold_warning" {
   type        = number
 }
 
+variable "running_tasks_use_message" {
+  description = "Whether to use the query alert base message for running tasks monitor"
+  type        = bool
+  default     = true
+}
+
 ########################################
 # Service CPU Utilization
 ########################################
 variable "cpu_utilization_enabled" {
-  default     = false
+  default     = true
   description = "Enable Fargate task CPU utilization monitor"
   type        = bool
 }
@@ -79,6 +85,12 @@ variable "cpu_utilization_threshold_warning" {
   type        = number
 }
 
+variable "cpu_utilization_use_message" {
+  description = "Whether to use the query alert base message for CPU utilization monitor"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # CPU Utilization (anomaly detection)
 ########################################
@@ -131,7 +143,7 @@ variable "cpu_utilization_anomaly_trigger_window" {
 }
 
 variable "cpu_utilization_anomaly_threshold_critical" {
-  default     = null
+  default     = 0.75
   description = "Critical threshold (percent)"
   type        = number
 }
@@ -142,6 +154,13 @@ variable "cpu_utilization_anomaly_threshold_warning" {
   type        = number
 }
 
+
+variable "cpu_utilization_anomaly_use_message" {
+  description = "Whether to use the query alert base message for CPU utilization anomaly monitor"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # Service Memory Reservation
 ########################################
@@ -173,3 +192,9 @@ variable "memory_utilization_threshold_warning" {
   description = "Warning threshold (percent)"
   type        = number
 }
+
+variable "memory_utilization_use_message" {
+  description = "Whether to use the query alert base message for memory utilization monitor"
+  type        = bool
+  default     = false
+}
diff --git a/aws/elasticache/README.md b/aws/elasticache/README.md
index 55933f8..67890f6 100644
--- a/aws/elasticache/README.md
+++ b/aws/elasticache/README.md
@@ -24,7 +24,7 @@ Configures the following for ElastiCache clusters based on tag matches:
 
 | Name | Version |
 |------|---------|
-| <a name="provider_datadog"></a> [datadog](#provider\_datadog) | >= 3.37 |
+| <a name="provider_datadog"></a> [datadog](#provider\_datadog) | 3.37.0 |
 
 ## Modules
 
@@ -62,42 +62,51 @@ No modules.
 | <a name="input_cpu_utilization_anomaly_threshold_critical"></a> [cpu\_utilization\_anomaly\_threshold\_critical](#input\_cpu\_utilization\_anomaly\_threshold\_critical) | Critical threshold (percent) | `number` | `null` | no |
 | <a name="input_cpu_utilization_anomaly_threshold_warning"></a> [cpu\_utilization\_anomaly\_threshold\_warning](#input\_cpu\_utilization\_anomaly\_threshold\_warning) | Warning threshold (percent) | `number` | `null` | no |
 | <a name="input_cpu_utilization_anomaly_trigger_window"></a> [cpu\_utilization\_anomaly\_trigger\_window](#input\_cpu\_utilization\_anomaly\_trigger\_window) | Trigger window for anomaly monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_1h"` | no |
+| <a name="input_cpu_utilization_anomaly_use_message"></a> [cpu\_utilization\_anomaly\_use\_message](#input\_cpu\_utilization\_anomaly\_use\_message) | Whether to use the query alert base message for CPU utilization anomaly monitor | `bool` | `false` | no |
 | <a name="input_cpu_utilization_enabled"></a> [cpu\_utilization\_enabled](#input\_cpu\_utilization\_enabled) | Enable CPU utilization monitor | `bool` | `false` | no |
 | <a name="input_cpu_utilization_evaluation_window"></a> [cpu\_utilization\_evaluation\_window](#input\_cpu\_utilization\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
 | <a name="input_cpu_utilization_no_data_window"></a> [cpu\_utilization\_no\_data\_window](#input\_cpu\_utilization\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
 | <a name="input_cpu_utilization_threshold_critical"></a> [cpu\_utilization\_threshold\_critical](#input\_cpu\_utilization\_threshold\_critical) | Critical threshold (percent) | `number` | `90` | no |
 | <a name="input_cpu_utilization_threshold_warning"></a> [cpu\_utilization\_threshold\_warning](#input\_cpu\_utilization\_threshold\_warning) | Warning threshold (percent) | `number` | `80` | no |
+| <a name="input_cpu_utilization_use_message"></a> [cpu\_utilization\_use\_message](#input\_cpu\_utilization\_use\_message) | Whether to use the query alert base message for CPU utilization monitor | `bool` | `false` | no |
 | <a name="input_dashboard_link"></a> [dashboard\_link](#input\_dashboard\_link) | Dashboard link to include in message | `string` | `null` | no |
-| <a name="input_env"></a> [env](#input\_env) | Environment the monitored resource is in (leave blank to omit tag) | `string` | n/a | yes |
+| <a name="input_env"></a> [env](#input\_env) | Environment the monitored resource is in (leave blank to omit tag) | `string` | `null` | no |
 | <a name="input_evaluation_delay"></a> [evaluation\_delay](#input\_evaluation\_delay) | Monitor evaluation delay (see [https://docs.datadoghq.com/monitors/configuration/?tab=thresholdalert#set-alert-conditions](Datadog Docs)) | `number` | `900` | no |
 | <a name="input_evictions_enabled"></a> [evictions\_enabled](#input\_evictions\_enabled) | Enable eviction rate monitor | `bool` | `false` | no |
 | <a name="input_evictions_evaluation_window"></a> [evictions\_evaluation\_window](#input\_evictions\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
 | <a name="input_evictions_no_data_window"></a> [evictions\_no\_data\_window](#input\_evictions\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
 | <a name="input_evictions_threshold_critical"></a> [evictions\_threshold\_critical](#input\_evictions\_threshold\_critical) | Critical threshold (count) | `number` | `null` | no |
 | <a name="input_evictions_threshold_warning"></a> [evictions\_threshold\_warning](#input\_evictions\_threshold\_warning) | Warning threshold (count) | `number` | `null` | no |
+| <a name="input_evictions_use_message"></a> [evictions\_use\_message](#input\_evictions\_use\_message) | Whether to use the query alert base message for evictions monitor | `bool` | `false` | no |
 | <a name="input_hit_rate_anomaly_deviations"></a> [hit\_rate\_anomaly\_deviations](#input\_hit\_rate\_anomaly\_deviations) | Standard deviations | `number` | `2` | no |
 | <a name="input_hit_rate_anomaly_enabled"></a> [hit\_rate\_anomaly\_enabled](#input\_hit\_rate\_anomaly\_enabled) | Enable cache hit rate anomaly monitor | `bool` | `false` | no |
 | <a name="input_hit_rate_anomaly_evaluation_window"></a> [hit\_rate\_anomaly\_evaluation\_window](#input\_hit\_rate\_anomaly\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_1h"` | no |
 | <a name="input_hit_rate_anomaly_no_data_window"></a> [hit\_rate\_anomaly\_no\_data\_window](#input\_hit\_rate\_anomaly\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
 | <a name="input_hit_rate_anomaly_seasonality"></a> [hit\_rate\_anomaly\_seasonality](#input\_hit\_rate\_anomaly\_seasonality) | Seasonaility (hourly, daily, weekly) | `string` | `"daily"` | no |
 | <a name="input_hit_rate_anomaly_threshold_critical"></a> [hit\_rate\_anomaly\_threshold\_critical](#input\_hit\_rate\_anomaly\_threshold\_critical) | Critical threshold (percentage) | `number` | `null` | no |
+| <a name="input_hit_rate_anomaly_use_message"></a> [hit\_rate\_anomaly\_use\_message](#input\_hit\_rate\_anomaly\_use\_message) | Whether to use the query alert base message for hit rate anomaly monitor | `bool` | `false` | no |
 | <a name="input_hit_rate_enabled"></a> [hit\_rate\_enabled](#input\_hit\_rate\_enabled) | Enable cache hit rate monitor | `bool` | `false` | no |
 | <a name="input_hit_rate_evaluation_window"></a> [hit\_rate\_evaluation\_window](#input\_hit\_rate\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
 | <a name="input_hit_rate_no_data_window"></a> [hit\_rate\_no\_data\_window](#input\_hit\_rate\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
 | <a name="input_hit_rate_threshold_critical"></a> [hit\_rate\_threshold\_critical](#input\_hit\_rate\_threshold\_critical) | Critical threshold (percentage) | `number` | `null` | no |
 | <a name="input_hit_rate_threshold_warning"></a> [hit\_rate\_threshold\_warning](#input\_hit\_rate\_threshold\_warning) | Warning threshold (percentage) | `number` | `null` | no |
+| <a name="input_hit_rate_use_message"></a> [hit\_rate\_use\_message](#input\_hit\_rate\_use\_message) | Whether to use the query alert base message for hit rate monitor | `bool` | `false` | no |
 | <a name="input_max_connections_enabled"></a> [max\_connections\_enabled](#input\_max\_connections\_enabled) | Enable max connections monitor | `bool` | `false` | no |
 | <a name="input_max_connections_evaluation_window"></a> [max\_connections\_evaluation\_window](#input\_max\_connections\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
 | <a name="input_max_connections_no_data_window"></a> [max\_connections\_no\_data\_window](#input\_max\_connections\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
 | <a name="input_max_connections_threshold_critical"></a> [max\_connections\_threshold\_critical](#input\_max\_connections\_threshold\_critical) | Critical threshold (connections) | `number` | `64000` | no |
 | <a name="input_max_connections_threshold_warning"></a> [max\_connections\_threshold\_warning](#input\_max\_connections\_threshold\_warning) | Warning threshold (connections) | `number` | `60000` | no |
+| <a name="input_max_connections_use_message"></a> [max\_connections\_use\_message](#input\_max\_connections\_use\_message) | Whether to use the query alert base message for max connections monitor | `bool` | `false` | no |
 | <a name="input_monitor_exclude_tags"></a> [monitor\_exclude\_tags](#input\_monitor\_exclude\_tags) | Tags to be excluded in the monitoring query. Specify in key:value format | `list(string)` | `[]` | no |
 | <a name="input_monitor_include_tags"></a> [monitor\_include\_tags](#input\_monitor\_include\_tags) | Tags to be included in the monitoring query. Specify in key:value format | `list(string)` | `[]` | no |
 | <a name="input_new_group_delay"></a> [new\_group\_delay](#input\_new\_group\_delay) | Delay in seconds before generating alerts for a new resource | `number` | `300` | no |
 | <a name="input_notify_alert_override"></a> [notify\_alert\_override](#input\_notify\_alert\_override) | List of notifications for alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_crit_override"></a> [notify\_crit\_override](#input\_notify\_crit\_override) | List of notifications for 24x7 alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_default"></a> [notify\_default](#input\_notify\_default) | List of alert notifications (can be overridden based on alert type) | `list(string)` | n/a | yes |
 | <a name="input_notify_no_data"></a> [notify\_no\_data](#input\_notify\_no\_data) | Alert if no matching data is found | `bool` | `false` | no |
 | <a name="input_notify_nodata_override"></a> [notify\_nodata\_override](#input\_notify\_nodata\_override) | List of notifications for no data (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_nonprod_override"></a> [notify\_nonprod\_override](#input\_notify\_nonprod\_override) | List of notifications for non-prod alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_prod_override"></a> [notify\_prod\_override](#input\_notify\_prod\_override) | List of notifications for 12x5 prod alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_recovery_override"></a> [notify\_recovery\_override](#input\_notify\_recovery\_override) | List of notifications for alert recovery (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_warn_override"></a> [notify\_warn\_override](#input\_notify\_warn\_override) | List of notifications for alerts in warning threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_renotify_interval"></a> [renotify\_interval](#input\_renotify\_interval) | Interval in minutes to re-send notifications about an alert | `number` | `0` | no |
@@ -108,6 +117,7 @@ No modules.
 | <a name="input_swap_usage_no_data_window"></a> [swap\_usage\_no\_data\_window](#input\_swap\_usage\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
 | <a name="input_swap_usage_threshold_critical"></a> [swap\_usage\_threshold\_critical](#input\_swap\_usage\_threshold\_critical) | Critical threshold (bytes) | `number` | `52428800` | no |
 | <a name="input_swap_usage_threshold_warning"></a> [swap\_usage\_threshold\_warning](#input\_swap\_usage\_threshold\_warning) | Warning threshold (bytes) | `number` | `null` | no |
+| <a name="input_swap_usage_use_message"></a> [swap\_usage\_use\_message](#input\_swap\_usage\_use\_message) | Whether to use the query alert base message for swap usage monitor | `bool` | `false` | no |
 | <a name="input_team"></a> [team](#input\_team) | Team supporting the monitored resource (leave blank to omit tag) | `string` | `null` | no |
 | <a name="input_timeout_h"></a> [timeout\_h](#input\_timeout\_h) | Auto-resolve alert in specified hours if condition no longer matches | `number` | `0` | no |
 | <a name="input_title_prefix"></a> [title\_prefix](#input\_title\_prefix) | Prefix all alerts with specified value in brackets | `string` | `null` | no |
diff --git a/aws/elasticache/main.tf b/aws/elasticache/main.tf
index 3f7c8a5..2ad69b1 100644
--- a/aws/elasticache/main.tf
+++ b/aws/elasticache/main.tf
@@ -4,7 +4,7 @@ locals {
   monitor_warn_default_priority   = null
   monitor_nodata_default_priority = null
 
-  title_prefix = "${var.title_prefix == null ? "" : "[${var.title_prefix}]"}"
+  title_prefix = var.title_prefix == null ? "" : "[${var.title_prefix}]"
   title_suffix = var.title_suffix == null ? "" : " (${var.title_suffix})"
 }
 
@@ -12,8 +12,8 @@ resource "datadog_monitor" "cpu_utilization" {
   count = var.cpu_utilization_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "Elasticache CPU Utilization - {{cacheclusterid.name}} - {{value}}%", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.cpu_utilization_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -27,7 +27,7 @@ resource "datadog_monitor" "cpu_utilization" {
 
   query = <<END
     avg(${var.cpu_utilization_evaluation_window}):
-      avg:aws.elasticache.cpuutilization${local.query_filter} by {cachenodeid,cacheclusterid,region,aws_account,env}
+      avg:aws.elasticache.cpuutilization${local.query_filter} by {cachenodeid,cacheclusterid,region,aws_account,env,datadog_managed}
     >= ${var.cpu_utilization_threshold_critical}
 END
 
@@ -41,8 +41,8 @@ resource "datadog_monitor" "cpu_utilization_anomaly" {
   count = var.cpu_utilization_anomaly_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "Elasticache CPU utilization anomalous activity - {{cacheclusterid.name}}", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.cpu_utilization_anomaly_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -56,7 +56,7 @@ resource "datadog_monitor" "cpu_utilization_anomaly" {
 
   query = <<END
     avg(${var.cpu_utilization_evaluation_window}):anomalies(
-      avg:aws.elasticache.cpuutilization${local.query_filter} by {cachenodeid,cacheclusterid,region,aws_account,env}, 'agile', ${var.cpu_utilization_anomaly_deviations},
+      avg:aws.elasticache.cpuutilization${local.query_filter} by {cachenodeid,cacheclusterid,region,aws_account,env,datadog_managed}, 'agile', ${var.cpu_utilization_anomaly_deviations},
       direction='above', count_default_zero='true', interval=${var.cpu_utilization_anomaly_rollup},
       seasonality='${var.cpu_utilization_anomaly_seasonality}'
     ) >= ${var.cpu_utilization_anomaly_threshold_critical}
@@ -71,8 +71,8 @@ resource "datadog_monitor" "evictions" {
   count = var.evictions_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "Elasticache evictions - {{cacheclusterid.name}}", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.evictions_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -86,7 +86,7 @@ resource "datadog_monitor" "evictions" {
 
   query = <<END
     sum(${var.evictions_evaluation_window}): (
-      avg:aws.elasticache.evictions${local.query_filter} by {cachenodeid,cacheclusterid,region,aws_account,env}
+      avg:aws.elasticache.evictions${local.query_filter} by {cachenodeid,cacheclusterid,region,aws_account,env,datadog_managed}
     ) >= ${var.evictions_threshold_critical}
 END
 
@@ -100,8 +100,8 @@ resource "datadog_monitor" "hit_rate" {
   count = var.hit_rate_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "Elasticache cache hit rate - {{cacheclusterid.name}} - {{value}}% ", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.hit_rate_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -115,7 +115,7 @@ resource "datadog_monitor" "hit_rate" {
 
   query = <<END
     max(${var.hit_rate_evaluation_window}):(
-      avg:aws.elasticache.cache_hit_rate${local.query_filter} by {cachenodeid,cacheclusterid,region,aws_account,env}
+      avg:aws.elasticache.cache_hit_rate${local.query_filter} by {cachenodeid,cacheclusterid,region,aws_account,env,datadog_managed}
     )  >= ${var.hit_rate_threshold_critical}
 END
 
@@ -129,8 +129,8 @@ resource "datadog_monitor" "hit_rate_anomaly" {
   count = var.hit_rate_anomaly_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "Elasticache cache hit rate anomalous activity - {{cacheclusterid.name}}", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.hit_rate_anomaly_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -144,7 +144,7 @@ resource "datadog_monitor" "hit_rate_anomaly" {
 
   query = <<END
     avg(${var.hit_rate_evaluation_window}):anomalies(
-      avg:aws.elasticache.cache_hit_rate${local.query_filter} by {cachenodeid,cacheclusterid,region,aws_account,env}, 'agile', ${var.hit_rate_anomaly_deviations},
+      avg:aws.elasticache.cache_hit_rate${local.query_filter} by {cachenodeid,cacheclusterid,region,aws_account,env,datadog_managed}, 'agile', ${var.hit_rate_anomaly_deviations},
       direction='below', count_default_zero='true',
       seasonality='${var.hit_rate_anomaly_seasonality}'
     ) >= ${var.hit_rate_anomaly_threshold_critical}
@@ -159,8 +159,8 @@ resource "datadog_monitor" "max_connections" {
   count = var.max_connections_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "Elasticache max connections reached - {{cacheclusterid.name}}", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.max_connections_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -174,7 +174,7 @@ resource "datadog_monitor" "max_connections" {
 
   query = <<END
     max(${var.max_connections_evaluation_window}):(
-      avg:aws.elasticache.curr_connections${local.query_filter} by {cachenodeid,cacheclusterid,region,aws_account,env}
+      avg:aws.elasticache.curr_connections${local.query_filter} by {cachenodeid,cacheclusterid,region,aws_account,env,datadog_managed}
     )  >= ${var.max_connections_threshold_critical}
 END
 
@@ -188,8 +188,8 @@ resource "datadog_monitor" "swap_usage" {
   count = var.swap_usage_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "Elasticache swap usage - {{cacheclusterid.name}} - {{value}}MB", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.swap_usage_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -203,7 +203,7 @@ resource "datadog_monitor" "swap_usage" {
 
   query = <<END
     max(${var.swap_usage_evaluation_window}):(
-      avg:aws.elasticache.swap_usage${local.query_filter} by {cachenodeid,cacheclusterid,region,aws_account,env}
+      avg:aws.elasticache.swap_usage${local.query_filter} by {cachenodeid,cacheclusterid,region,aws_account,env,datadog_managed}
     )  <= ${var.swap_usage_threshold_critical}
 END
 
diff --git a/aws/elasticache/variables.tf b/aws/elasticache/variables.tf
index 0ef1148..da5dd70 100644
--- a/aws/elasticache/variables.tf
+++ b/aws/elasticache/variables.tf
@@ -46,6 +46,12 @@ variable "cpu_utilization_threshold_warning" {
   type        = number
 }
 
+variable "cpu_utilization_use_message" {
+  description = "Whether to use the query alert base message for CPU utilization monitor"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # CPU Utilization (anomaly detection)
 ########################################
@@ -109,6 +115,12 @@ variable "cpu_utilization_anomaly_threshold_warning" {
   type        = number
 }
 
+variable "cpu_utilization_anomaly_use_message" {
+  description = "Whether to use the query alert base message for CPU utilization anomaly monitor"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # Elasticache Evictions
 ########################################
@@ -142,6 +154,12 @@ variable "evictions_threshold_warning" {
   type        = number
 }
 
+variable "evictions_use_message" {
+  description = "Whether to use the query alert base message for evictions monitor"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # Cache hit rate
 ########################################
@@ -175,6 +193,12 @@ variable "hit_rate_threshold_warning" {
   type        = number
 }
 
+variable "hit_rate_use_message" {
+  description = "Whether to use the query alert base message for hit rate monitor"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # Cache hit rate (anomaly detection)
 ########################################
@@ -214,6 +238,12 @@ variable "hit_rate_anomaly_threshold_critical" {
   type        = number
 }
 
+variable "hit_rate_anomaly_use_message" {
+  description = "Whether to use the query alert base message for hit rate anomaly monitor"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # Max Connections
 ########################################
@@ -247,6 +277,12 @@ variable "max_connections_threshold_warning" {
   type        = number
 }
 
+variable "max_connections_use_message" {
+  description = "Whether to use the query alert base message for max connections monitor"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # Swap usage (by node)
 ########################################
@@ -279,3 +315,9 @@ variable "swap_usage_threshold_warning" {
   description = "Warning threshold (bytes)"
   type        = number
 }
+
+variable "swap_usage_use_message" {
+  description = "Whether to use the query alert base message for swap usage monitor"
+  type        = bool
+  default     = false
+}
diff --git a/aws/elasticsearch/README.md b/aws/elasticsearch/README.md
index fc6d9c4..20ad716 100644
--- a/aws/elasticsearch/README.md
+++ b/aws/elasticsearch/README.md
@@ -20,7 +20,7 @@ Configures the following for ElasticSearch domains based on tag matches:
 
 | Name | Version |
 |------|---------|
-| <a name="provider_datadog"></a> [datadog](#provider\_datadog) | >= 3.37 |
+| <a name="provider_datadog"></a> [datadog](#provider\_datadog) | 3.37.0 |
 
 ## Modules
 
@@ -45,12 +45,14 @@ No modules.
 | <a name="input_alert_message"></a> [alert\_message](#input\_alert\_message) | Message to prepend to alert notifications | `string` | `"Alert"` | no |
 | <a name="input_alert_nodata_priority"></a> [alert\_nodata\_priority](#input\_alert\_nodata\_priority) | Priority for alerts within warning threshold (P1-P5, uses monitor defaults if not specified) | `string` | `null` | no |
 | <a name="input_base_tags"></a> [base\_tags](#input\_base\_tags) | Base tags (key:value format) to add to this type of check (combined with `local.tags` and `var.additional_tags`, generally you should not change this) | `list(string)` | <pre>[<br>  "resource:elasticsearch"<br>]</pre> | no |
-| <a name="input_cluster_health_red_enabled"></a> [cluster\_health\_red\_enabled](#input\_cluster\_health\_red\_enabled) | Enable cluster health\_red monitor | `bool` | `false` | no |
+| <a name="input_cluster_health_red_enabled"></a> [cluster\_health\_red\_enabled](#input\_cluster\_health\_red\_enabled) | Enable cluster health\_red monitor | `bool` | `true` | no |
 | <a name="input_cluster_health_red_evaluation_window"></a> [cluster\_health\_red\_evaluation\_window](#input\_cluster\_health\_red\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
 | <a name="input_cluster_health_red_no_data_window"></a> [cluster\_health\_red\_no\_data\_window](#input\_cluster\_health\_red\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
-| <a name="input_cluster_health_yellow_enabled"></a> [cluster\_health\_yellow\_enabled](#input\_cluster\_health\_yellow\_enabled) | Enable cluster health monitor | `bool` | `false` | no |
+| <a name="input_cluster_health_red_use_message"></a> [cluster\_health\_red\_use\_message](#input\_cluster\_health\_red\_use\_message) | Whether to use the query alert base message for cluster health red monitor | `bool` | `true` | no |
+| <a name="input_cluster_health_yellow_enabled"></a> [cluster\_health\_yellow\_enabled](#input\_cluster\_health\_yellow\_enabled) | Enable cluster health monitor | `bool` | `true` | no |
 | <a name="input_cluster_health_yellow_evaluation_window"></a> [cluster\_health\_yellow\_evaluation\_window](#input\_cluster\_health\_yellow\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
 | <a name="input_cluster_health_yellow_no_data_window"></a> [cluster\_health\_yellow\_no\_data\_window](#input\_cluster\_health\_yellow\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
+| <a name="input_cluster_health_yellow_use_message"></a> [cluster\_health\_yellow\_use\_message](#input\_cluster\_health\_yellow\_use\_message) | Whether to use the query alert base message for cluster health yellow monitor | `bool` | `false` | no |
 | <a name="input_cost_center"></a> [cost\_center](#input\_cost\_center) | Cost Center of the monitored resource (leave blank to omit tag) | `string` | `null` | no |
 | <a name="input_cpu_utilization_anomaly_deviations"></a> [cpu\_utilization\_anomaly\_deviations](#input\_cpu\_utilization\_anomaly\_deviations) | Standard deviations | `number` | `4` | no |
 | <a name="input_cpu_utilization_anomaly_enabled"></a> [cpu\_utilization\_anomaly\_enabled](#input\_cpu\_utilization\_anomaly\_enabled) | Enable CPU utilization anomaly monitor | `bool` | `false` | no |
@@ -62,26 +64,32 @@ No modules.
 | <a name="input_cpu_utilization_anomaly_threshold_critical"></a> [cpu\_utilization\_anomaly\_threshold\_critical](#input\_cpu\_utilization\_anomaly\_threshold\_critical) | Critical threshold (percent) | `number` | `null` | no |
 | <a name="input_cpu_utilization_anomaly_threshold_warning"></a> [cpu\_utilization\_anomaly\_threshold\_warning](#input\_cpu\_utilization\_anomaly\_threshold\_warning) | Warning threshold (percent) | `number` | `null` | no |
 | <a name="input_cpu_utilization_anomaly_trigger_window"></a> [cpu\_utilization\_anomaly\_trigger\_window](#input\_cpu\_utilization\_anomaly\_trigger\_window) | Trigger window for anomaly monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_1h"` | no |
+| <a name="input_cpu_utilization_anomaly_use_message"></a> [cpu\_utilization\_anomaly\_use\_message](#input\_cpu\_utilization\_anomaly\_use\_message) | Whether to use the query alert base message for CPU utilization anomaly monitor | `bool` | `false` | no |
 | <a name="input_cpu_utilization_enabled"></a> [cpu\_utilization\_enabled](#input\_cpu\_utilization\_enabled) | Enable CPU utilization monitor | `bool` | `false` | no |
 | <a name="input_cpu_utilization_evaluation_window"></a> [cpu\_utilization\_evaluation\_window](#input\_cpu\_utilization\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
 | <a name="input_cpu_utilization_no_data_window"></a> [cpu\_utilization\_no\_data\_window](#input\_cpu\_utilization\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
 | <a name="input_cpu_utilization_threshold_critical"></a> [cpu\_utilization\_threshold\_critical](#input\_cpu\_utilization\_threshold\_critical) | Critical threshold (percent) | `number` | `0.9` | no |
 | <a name="input_cpu_utilization_threshold_warning"></a> [cpu\_utilization\_threshold\_warning](#input\_cpu\_utilization\_threshold\_warning) | Warning threshold (percent) | `number` | `0.8` | no |
+| <a name="input_cpu_utilization_use_message"></a> [cpu\_utilization\_use\_message](#input\_cpu\_utilization\_use\_message) | Whether to use the query alert base message for CPU utilization monitor | `bool` | `false` | no |
 | <a name="input_dashboard_link"></a> [dashboard\_link](#input\_dashboard\_link) | Dashboard link to include in message | `string` | `null` | no |
-| <a name="input_env"></a> [env](#input\_env) | Environment the monitored resource is in (leave blank to omit tag) | `string` | n/a | yes |
+| <a name="input_env"></a> [env](#input\_env) | Environment the monitored resource is in (leave blank to omit tag) | `string` | `null` | no |
 | <a name="input_evaluation_delay"></a> [evaluation\_delay](#input\_evaluation\_delay) | Monitor evaluation delay (see [https://docs.datadoghq.com/monitors/configuration/?tab=thresholdalert#set-alert-conditions](Datadog Docs)) | `number` | `900` | no |
-| <a name="input_free_storage_enabled"></a> [free\_storage\_enabled](#input\_free\_storage\_enabled) | Enable free storage monitor | `bool` | `false` | no |
+| <a name="input_free_storage_enabled"></a> [free\_storage\_enabled](#input\_free\_storage\_enabled) | Enable free storage monitor | `bool` | `true` | no |
 | <a name="input_free_storage_evaluation_window"></a> [free\_storage\_evaluation\_window](#input\_free\_storage\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
 | <a name="input_free_storage_no_data_window"></a> [free\_storage\_no\_data\_window](#input\_free\_storage\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
-| <a name="input_free_storage_threshold_critical"></a> [free\_storage\_threshold\_critical](#input\_free\_storage\_threshold\_critical) | Critical threshold (GB) | `number` | `null` | no |
-| <a name="input_free_storage_threshold_warning"></a> [free\_storage\_threshold\_warning](#input\_free\_storage\_threshold\_warning) | Warning threshold (GB) | `number` | `null` | no |
+| <a name="input_free_storage_threshold_critical"></a> [free\_storage\_threshold\_critical](#input\_free\_storage\_threshold\_critical) | Critical threshold for used disk space (%) | `number` | `90` | no |
+| <a name="input_free_storage_threshold_warning"></a> [free\_storage\_threshold\_warning](#input\_free\_storage\_threshold\_warning) | Warning threshold for used disk space (%) | `number` | `80` | no |
+| <a name="input_free_storage_use_message"></a> [free\_storage\_use\_message](#input\_free\_storage\_use\_message) | Whether to use the query alert base message for free storage monitor | `bool` | `true` | no |
 | <a name="input_monitor_exclude_tags"></a> [monitor\_exclude\_tags](#input\_monitor\_exclude\_tags) | Tags to be excluded in the monitoring query. Specify in key:value format | `list(string)` | `[]` | no |
 | <a name="input_monitor_include_tags"></a> [monitor\_include\_tags](#input\_monitor\_include\_tags) | Tags to be included in the monitoring query. Specify in key:value format | `list(string)` | `[]` | no |
 | <a name="input_new_group_delay"></a> [new\_group\_delay](#input\_new\_group\_delay) | Delay in seconds before generating alerts for a new resource | `number` | `300` | no |
 | <a name="input_notify_alert_override"></a> [notify\_alert\_override](#input\_notify\_alert\_override) | List of notifications for alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_crit_override"></a> [notify\_crit\_override](#input\_notify\_crit\_override) | List of notifications for 24x7 alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_default"></a> [notify\_default](#input\_notify\_default) | List of alert notifications (can be overridden based on alert type) | `list(string)` | n/a | yes |
 | <a name="input_notify_no_data"></a> [notify\_no\_data](#input\_notify\_no\_data) | Alert if no matching data is found | `bool` | `false` | no |
 | <a name="input_notify_nodata_override"></a> [notify\_nodata\_override](#input\_notify\_nodata\_override) | List of notifications for no data (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_nonprod_override"></a> [notify\_nonprod\_override](#input\_notify\_nonprod\_override) | List of notifications for non-prod alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_prod_override"></a> [notify\_prod\_override](#input\_notify\_prod\_override) | List of notifications for 12x5 prod alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_recovery_override"></a> [notify\_recovery\_override](#input\_notify\_recovery\_override) | List of notifications for alert recovery (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_warn_override"></a> [notify\_warn\_override](#input\_notify\_warn\_override) | List of notifications for alerts in warning threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_renotify_interval"></a> [renotify\_interval](#input\_renotify\_interval) | Interval in minutes to re-send notifications about an alert | `number` | `0` | no |
diff --git a/aws/elasticsearch/main.tf b/aws/elasticsearch/main.tf
index 632e503..479754c 100644
--- a/aws/elasticsearch/main.tf
+++ b/aws/elasticsearch/main.tf
@@ -4,7 +4,7 @@ locals {
   monitor_warn_default_priority   = null
   monitor_nodata_default_priority = null
 
-  title_prefix = "${var.title_prefix == null ? "" : "[${var.title_prefix}]"}"
+  title_prefix = var.title_prefix == null ? "" : "[${var.title_prefix}]"
   title_suffix = var.title_suffix == null ? "" : " (${var.title_suffix})"
 }
 
@@ -12,8 +12,8 @@ resource "datadog_monitor" "cluster_health_red" {
   count = var.cluster_health_red_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "ElasticSearch cluster health red - {{name.name}}", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.cluster_health_red_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -27,7 +27,7 @@ resource "datadog_monitor" "cluster_health_red" {
 
   query = <<END
     max(${var.cluster_health_red_evaluation_window}):
-      max:aws.es.cluster_statusred${local.query_filter} by {name,region,aws_account,env}
+      max:aws.es.cluster_statusred${local.query_filter} by {name,region,aws_account,env,datadog_managed}
     >= 1
 END
 
@@ -40,8 +40,8 @@ resource "datadog_monitor" "cluster_health_yellow" {
   count = var.cluster_health_yellow_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "ElasticSearch cluster health yellow - {{name.name}}", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.cluster_health_yellow_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -55,7 +55,7 @@ resource "datadog_monitor" "cluster_health_yellow" {
 
   query = <<END
     max(${var.cluster_health_yellow_evaluation_window}):
-      max:aws.es.cluster_statusyellow${local.query_filter} by {name,region,aws_account,env}
+      max:aws.es.cluster_statusyellow${local.query_filter} by {name,region,aws_account,env,datadog_managed}
     >= 1
 END
 
@@ -68,8 +68,8 @@ resource "datadog_monitor" "cpu_utilization" {
   count = var.cpu_utilization_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "ElasticSearch CPU Utilization - {{name.name}} - {{value}}%", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.cpu_utilization_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -83,7 +83,7 @@ resource "datadog_monitor" "cpu_utilization" {
 
   query = <<END
     avg(${var.cpu_utilization_evaluation_window}):
-      avg:aws.es.cpuutilization${local.query_filter} by {name,region,aws_account,env}
+      avg:aws.es.cpuutilization${local.query_filter} by {name,region,aws_account,env,datadog_managed}
     >= ${var.cpu_utilization_threshold_critical}
 END
 
@@ -97,8 +97,8 @@ resource "datadog_monitor" "cpu_utilization_anomaly" {
   count = var.cpu_utilization_anomaly_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "ElasticSearch CPU utilization anomalous activity - {{name.name}}", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.cpu_utilization_anomaly_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -133,8 +133,8 @@ resource "datadog_monitor" "free_storage" {
   count = var.free_storage_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "ElasticSearch cluster storage - {{name.name}} - {{value}}% used", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.free_storage_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -148,9 +148,9 @@ resource "datadog_monitor" "free_storage" {
 
   query = <<EOQ
     max(${var.free_storage_evaluation_window}): (
-    avg:aws.es.cluster_used_space.average${local.query_filter} by {name,region,aws_account,env} / 
-    ( avg:aws.es.free_storage_space${local.query_filter} by {name,region,aws_account,env} + 
-    avg:aws.es.cluster_used_space.average${local.query_filter} by {name,region,aws_account,env})) * 100 
+    max:aws.es.cluster_used_space.average${local.query_filter} by {name,region,aws_account,env,datadog_managed} /
+    ( max:aws.es.free_storage_space${local.query_filter} by {name,region,aws_account,env,datadog_managed} +
+    max:aws.es.cluster_used_space.average${local.query_filter} by {name,region,aws_account,env,datadog_managed})) * 100
     > ${var.free_storage_threshold_critical}
 EOQ
 
diff --git a/aws/elasticsearch/variables.tf b/aws/elasticsearch/variables.tf
index 971cdd4..d251705 100644
--- a/aws/elasticsearch/variables.tf
+++ b/aws/elasticsearch/variables.tf
@@ -17,7 +17,7 @@ variable "base_tags" {
 # ElasticSearch cluster health (red)
 ########################################
 variable "cluster_health_red_enabled" {
-  default     = false
+  default     = true
   description = "Enable cluster health_red monitor"
   type        = bool
 }
@@ -34,11 +34,17 @@ variable "cluster_health_red_no_data_window" {
   type        = number
 }
 
+variable "cluster_health_red_use_message" {
+  description = "Whether to use the query alert base message for cluster health red monitor"
+  type        = bool
+  default     = true
+}
+
 #######################################
 # ElasticSearch cluster health (yellow)
 ########################################
 variable "cluster_health_yellow_enabled" {
-  default     = false
+  default     = true
   description = "Enable cluster health monitor"
   type        = bool
 }
@@ -55,11 +61,17 @@ variable "cluster_health_yellow_no_data_window" {
   type        = number
 }
 
+variable "cluster_health_yellow_use_message" {
+  description = "Whether to use the query alert base message for cluster health yellow monitor"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # Node CPU Utilization
 ########################################
 variable "cpu_utilization_enabled" {
-  default     = false
+  default     = true
   description = "Enable CPU utilization monitor"
   type        = bool
 }
@@ -88,6 +100,12 @@ variable "cpu_utilization_threshold_warning" {
   type        = number
 }
 
+variable "cpu_utilization_use_message" {
+  description = "Whether to use the query alert base message for CPU utilization monitor"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # CPU Utilization (anomaly detection)
 ########################################
@@ -151,6 +169,12 @@ variable "cpu_utilization_anomaly_threshold_warning" {
   type        = number
 }
 
+variable "cpu_utilization_anomaly_use_message" {
+  description = "Whether to use the query alert base message for CPU utilization anomaly monitor"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # ElasticSearch cluster free storage
 ########################################
@@ -173,13 +197,19 @@ variable "free_storage_evaluation_window" {
 }
 
 variable "free_storage_threshold_critical" {
-  default     = null
-  description = "Critical threshold (GB)"
+  default     = 90
+  description = "Critical threshold for used disk space (%)"
   type        = number
 }
 
 variable "free_storage_threshold_warning" {
-  default     = null
-  description = "Warning threshold (GB)"
+  default     = 80
+  description = "Warning threshold for used disk space (%)"
   type        = number
 }
+
+variable "free_storage_use_message" {
+  description = "Whether to use the query alert base message for free storage monitor"
+  type        = bool
+  default     = true
+}
diff --git a/aws/elb/README.md b/aws/elb/README.md
index 9063d12..a0edca2 100644
--- a/aws/elb/README.md
+++ b/aws/elb/README.md
@@ -20,7 +20,7 @@ Configures the following for Classic ELBs based on tag matches:
 
 | Name | Version |
 |------|---------|
-| <a name="provider_datadog"></a> [datadog](#provider\_datadog) | >= 3.37 |
+| <a name="provider_datadog"></a> [datadog](#provider\_datadog) | 3.37.0 |
 
 ## Modules
 
@@ -30,8 +30,8 @@ No modules.
 
 | Name | Type |
 |------|------|
+| [datadog_monitor.http_5xx_backend_responses](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
 | [datadog_monitor.http_5xx_responses](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
-| [datadog_monitor.http_5xx_tg_responses](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
 | [datadog_monitor.latency](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
 | [datadog_monitor.no_healthy_instances](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
 
@@ -43,37 +43,45 @@ No modules.
 | <a name="input_alert_critical_priority"></a> [alert\_critical\_priority](#input\_alert\_critical\_priority) | Priority for alerts within critical threshold (P1-P5, uses monitor defaults if not specified) | `string` | `null` | no |
 | <a name="input_alert_message"></a> [alert\_message](#input\_alert\_message) | Message to prepend to alert notifications | `string` | `"Alert"` | no |
 | <a name="input_alert_nodata_priority"></a> [alert\_nodata\_priority](#input\_alert\_nodata\_priority) | Priority for alerts within warning threshold (P1-P5, uses monitor defaults if not specified) | `string` | `null` | no |
-| <a name="input_base_tags"></a> [base\_tags](#input\_base\_tags) | Base tags (key:value format) to add to this type of check (combined with `local.tags` and `var.additional_tags`, generally you should not change this) | `list(string)` | <pre>[<br>  "resource:alb"<br>]</pre> | no |
+| <a name="input_base_tags"></a> [base\_tags](#input\_base\_tags) | Base tags (key:value format) to add to this type of check (combined with `local.tags` and `var.additional_tags`, generally you should not change this) | `list(string)` | <pre>[<br>  "resource:lb"<br>]</pre> | no |
 | <a name="input_cost_center"></a> [cost\_center](#input\_cost\_center) | Cost Center of the monitored resource (leave blank to omit tag) | `string` | `null` | no |
 | <a name="input_dashboard_link"></a> [dashboard\_link](#input\_dashboard\_link) | Dashboard link to include in message | `string` | `null` | no |
-| <a name="input_env"></a> [env](#input\_env) | Environment the monitored resource is in (leave blank to omit tag) | `string` | n/a | yes |
+| <a name="input_env"></a> [env](#input\_env) | Environment the monitored resource is in (leave blank to omit tag) | `string` | `null` | no |
 | <a name="input_evaluation_delay"></a> [evaluation\_delay](#input\_evaluation\_delay) | Monitor evaluation delay (see [https://docs.datadoghq.com/monitors/configuration/?tab=thresholdalert#set-alert-conditions](Datadog Docs)) | `number` | `900` | no |
+| <a name="input_http_5xx_backend_responses_enabled"></a> [http\_5xx\_backend\_responses\_enabled](#input\_http\_5xx\_backend\_responses\_enabled) | Enable HTTP 5xx response monitor (backend) | `bool` | `false` | no |
+| <a name="input_http_5xx_backend_responses_evaluation_window"></a> [http\_5xx\_backend\_responses\_evaluation\_window](#input\_http\_5xx\_backend\_responses\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
+| <a name="input_http_5xx_backend_responses_no_data_window"></a> [http\_5xx\_backend\_responses\_no\_data\_window](#input\_http\_5xx\_backend\_responses\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
+| <a name="input_http_5xx_backend_responses_threshold_critical"></a> [http\_5xx\_backend\_responses\_threshold\_critical](#input\_http\_5xx\_backend\_responses\_threshold\_critical) | Critical threshold (percentage, 0-100) | `number` | `75` | no |
+| <a name="input_http_5xx_backend_responses_threshold_warning"></a> [http\_5xx\_backend\_responses\_threshold\_warning](#input\_http\_5xx\_backend\_responses\_threshold\_warning) | Warning threshold (percentage, 0-100) | `number` | `25` | no |
+| <a name="input_http_5xx_backend_responses_use_message"></a> [http\_5xx\_backend\_responses\_use\_message](#input\_http\_5xx\_backend\_responses\_use\_message) | Whether to use the query alert base message for HTTP 5xx backend responses monitor | `bool` | `false` | no |
 | <a name="input_http_5xx_responses_enabled"></a> [http\_5xx\_responses\_enabled](#input\_http\_5xx\_responses\_enabled) | Enable HTTP 5xx response monitor | `bool` | `false` | no |
 | <a name="input_http_5xx_responses_evaluation_window"></a> [http\_5xx\_responses\_evaluation\_window](#input\_http\_5xx\_responses\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
 | <a name="input_http_5xx_responses_no_data_window"></a> [http\_5xx\_responses\_no\_data\_window](#input\_http\_5xx\_responses\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
 | <a name="input_http_5xx_responses_threshold_critical"></a> [http\_5xx\_responses\_threshold\_critical](#input\_http\_5xx\_responses\_threshold\_critical) | Critical threshold (percentage, 0-100) | `number` | `75` | no |
 | <a name="input_http_5xx_responses_threshold_warning"></a> [http\_5xx\_responses\_threshold\_warning](#input\_http\_5xx\_responses\_threshold\_warning) | Warning threshold (percentage, 0-100) | `number` | `25` | no |
-| <a name="input_http_5xx_tg_responses_enabled"></a> [http\_5xx\_tg\_responses\_enabled](#input\_http\_5xx\_tg\_responses\_enabled) | Enable HTTP 5xx response monitor (target group) | `bool` | `false` | no |
-| <a name="input_http_5xx_tg_responses_evaluation_window"></a> [http\_5xx\_tg\_responses\_evaluation\_window](#input\_http\_5xx\_tg\_responses\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
-| <a name="input_http_5xx_tg_responses_no_data_window"></a> [http\_5xx\_tg\_responses\_no\_data\_window](#input\_http\_5xx\_tg\_responses\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
-| <a name="input_http_5xx_tg_responses_threshold_critical"></a> [http\_5xx\_tg\_responses\_threshold\_critical](#input\_http\_5xx\_tg\_responses\_threshold\_critical) | Critical threshold (percentage, 0-100) | `number` | `75` | no |
-| <a name="input_http_5xx_tg_responses_threshold_warning"></a> [http\_5xx\_tg\_responses\_threshold\_warning](#input\_http\_5xx\_tg\_responses\_threshold\_warning) | Warning threshold (percentage, 0-100) | `number` | `25` | no |
+| <a name="input_http_5xx_responses_use_message"></a> [http\_5xx\_responses\_use\_message](#input\_http\_5xx\_responses\_use\_message) | Whether to use the query alert base message for HTTP 5xx responses monitor | `bool` | `false` | no |
 | <a name="input_latency_enabled"></a> [latency\_enabled](#input\_latency\_enabled) | Enable latency monitor | `bool` | `false` | no |
 | <a name="input_latency_evaluation_window"></a> [latency\_evaluation\_window](#input\_latency\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
 | <a name="input_latency_no_data_window"></a> [latency\_no\_data\_window](#input\_latency\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
 | <a name="input_latency_threshold_critical"></a> [latency\_threshold\_critical](#input\_latency\_threshold\_critical) | Critical threshold (seconds) | `number` | `null` | no |
 | <a name="input_latency_threshold_warning"></a> [latency\_threshold\_warning](#input\_latency\_threshold\_warning) | Warning threshold (seconds) | `number` | `null` | no |
+| <a name="input_latency_use_message"></a> [latency\_use\_message](#input\_latency\_use\_message) | Whether to use the query alert base message for latency monitor | `bool` | `false` | no |
 | <a name="input_monitor_exclude_tags"></a> [monitor\_exclude\_tags](#input\_monitor\_exclude\_tags) | Tags to be excluded in the monitoring query. Specify in key:value format | `list(string)` | `[]` | no |
 | <a name="input_monitor_include_tags"></a> [monitor\_include\_tags](#input\_monitor\_include\_tags) | Tags to be included in the monitoring query. Specify in key:value format | `list(string)` | `[]` | no |
 | <a name="input_new_group_delay"></a> [new\_group\_delay](#input\_new\_group\_delay) | Delay in seconds before generating alerts for a new resource | `number` | `300` | no |
 | <a name="input_no_healthy_instances_enabled"></a> [no\_healthy\_instances\_enabled](#input\_no\_healthy\_instances\_enabled) | Enable no healthy instances monitor | `bool` | `true` | no |
 | <a name="input_no_healthy_instances_evaluation_window"></a> [no\_healthy\_instances\_evaluation\_window](#input\_no\_healthy\_instances\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
 | <a name="input_no_healthy_instances_no_data_window"></a> [no\_healthy\_instances\_no\_data\_window](#input\_no\_healthy\_instances\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
-| <a name="input_no_healthy_instances_threshold_warning"></a> [no\_healthy\_instances\_threshold\_warning](#input\_no\_healthy\_instances\_threshold\_warning) | Warning threshold (percentage, 0 to disable) | `number` | `0` | no |
+| <a name="input_no_healthy_instances_threshold_critical"></a> [no\_healthy\_instances\_threshold\_critical](#input\_no\_healthy\_instances\_threshold\_critical) | Warning threshold (percentage) | `number` | `0` | no |
+| <a name="input_no_healthy_instances_threshold_warning"></a> [no\_healthy\_instances\_threshold\_warning](#input\_no\_healthy\_instances\_threshold\_warning) | Warning threshold (percentage) | `number` | `null` | no |
+| <a name="input_no_healthy_instances_use_message"></a> [no\_healthy\_instances\_use\_message](#input\_no\_healthy\_instances\_use\_message) | Whether to use the query alert base message for no healthy instances monitor | `bool` | `true` | no |
 | <a name="input_notify_alert_override"></a> [notify\_alert\_override](#input\_notify\_alert\_override) | List of notifications for alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_crit_override"></a> [notify\_crit\_override](#input\_notify\_crit\_override) | List of notifications for 24x7 alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_default"></a> [notify\_default](#input\_notify\_default) | List of alert notifications (can be overridden based on alert type) | `list(string)` | n/a | yes |
 | <a name="input_notify_no_data"></a> [notify\_no\_data](#input\_notify\_no\_data) | Alert if no matching data is found | `bool` | `false` | no |
 | <a name="input_notify_nodata_override"></a> [notify\_nodata\_override](#input\_notify\_nodata\_override) | List of notifications for no data (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_nonprod_override"></a> [notify\_nonprod\_override](#input\_notify\_nonprod\_override) | List of notifications for non-prod alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_prod_override"></a> [notify\_prod\_override](#input\_notify\_prod\_override) | List of notifications for 12x5 prod alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_recovery_override"></a> [notify\_recovery\_override](#input\_notify\_recovery\_override) | List of notifications for alert recovery (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_warn_override"></a> [notify\_warn\_override](#input\_notify\_warn\_override) | List of notifications for alerts in warning threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_renotify_interval"></a> [renotify\_interval](#input\_renotify\_interval) | Interval in minutes to re-send notifications about an alert | `number` | `0` | no |
diff --git a/aws/elb/main.tf b/aws/elb/main.tf
index 182c7e2..dfce887 100644
--- a/aws/elb/main.tf
+++ b/aws/elb/main.tf
@@ -4,16 +4,16 @@ locals {
   monitor_warn_default_priority   = null
   monitor_nodata_default_priority = null
 
-  title_prefix = "${var.title_prefix == null ? "" : "[${var.title_prefix}]"}"
+  title_prefix = var.title_prefix == null ? "" : "[${var.title_prefix}]"
   title_suffix = var.title_suffix == null ? "" : " (${var.title_suffix})"
 }
 
 resource "datadog_monitor" "http_5xx_responses" {
   count = var.http_5xx_responses_enabled ? 1 : 0
 
-  name         = join("", [local.title_prefix, "ELB 5xx Responses - {{host.name}}", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  name         = join("", [local.title_prefix, "ELB 5xx Responses - {{loadbalancername.name}}", local.title_suffix])
+  include_tags = false
+  message      = var.http_5xx_responses_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -27,8 +27,8 @@ resource "datadog_monitor" "http_5xx_responses" {
 
   query = <<END
     min(${var.http_5xx_responses_evaluation_window}):
-      default(avg:aws.elb.httpcode_elb_5xx${local.query_filter} by {loadbalancername,region,aws_account}.as_rate(), 0) / (
-      default(avg:aws.elb.request_count${local.query_filter} by {loadbalancername,region,aws_account}.as_rate(), 1)
+      default(avg:aws.elb.httpcode_elb_5xx${local.query_filter} by {loadbalancername,region,aws_account,env,datadog_managed}.as_rate(), 0) / (
+      default(avg:aws.elb.request_count${local.query_filter} by {loadbalancername,region,aws_account,env,datadog_managed}.as_rate(), 1)
     ) * 100 > ${var.http_5xx_responses_threshold_critical}
 END
 
@@ -41,9 +41,9 @@ END
 resource "datadog_monitor" "http_5xx_backend_responses" {
   count = var.http_5xx_backend_responses_enabled ? 1 : 0
 
-  name         = join("", [local.title_prefix, "ELB Backend 5xx Responses - {{host.name}}", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  name         = join("", [local.title_prefix, "ELB Backend 5xx Responses - {{loadbalancername.name}}", local.title_suffix])
+  include_tags = false
+  message      = var.http_5xx_backend_responses_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -57,8 +57,8 @@ resource "datadog_monitor" "http_5xx_backend_responses" {
 
   query = <<END
     min(${var.http_5xx_backend_responses_evaluation_window}):
-      default(avg:aws.elb.httpcode_backend_5xx${local.query_filter} by {loadbalancername,region,aws_account}.as_rate(), 0) / (
-      default(avg:aws.elb.request_count${local.query_filter} by {loadbalancername,region,aws_account}.as_rate(), 1)
+      default(avg:aws.elb.httpcode_backend_5xx${local.query_filter} by {loadbalancername,region,aws_account,env,datadog_managed}.as_rate(), 0) / (
+      default(avg:aws.elb.request_count${local.query_filter} by {loadbalancername,region,aws_account,env,datadog_managed}.as_rate(), 1)
     ) * 100 > ${var.http_5xx_backend_responses_threshold_critical}
 END
 
@@ -72,9 +72,9 @@ END
 resource "datadog_monitor" "latency" {
   count = var.latency_enabled ? 1 : 0
 
-  name         = join("", [local.title_prefix, "ELB backend latency - {{host.name}}", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  name         = join("", [local.title_prefix, "ELB backend latency - {{loadbalancername.name}}", local.title_suffix])
+  include_tags = false
+  message      = var.latency_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -88,7 +88,7 @@ resource "datadog_monitor" "latency" {
 
   query = <<END
     avg(${var.latency_evaluation_window}):
-      default(avg:aws.elb.latency${local.query_filter} by {loadbalancername,region,aws_account}, 0
+      default(avg:aws.elb.latency${local.query_filter} by {loadbalancername,region,aws_account,env,datadog_managed}, 0
     ) > ${var.latency_threshold_critical}
 END
 
@@ -101,9 +101,9 @@ END
 resource "datadog_monitor" "no_healthy_instances" {
   count = var.no_healthy_instances_enabled ? 1 : 0
 
-  name         = join("", [local.title_prefix, "ALB healthy instances - {{host.name}}", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  name         = join("", [local.title_prefix, "ALB healthy instances - {{loadbalancername.name}}", local.title_suffix])
+  include_tags = false
+  message      = var.no_healthy_instances_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -117,9 +117,9 @@ resource "datadog_monitor" "no_healthy_instances" {
 
   query = <<END
     min(${var.no_healthy_instances_evaluation_window}): (
-      sum:aws.elb.healthy_host_count.minimum${local.query_filter} by {loadbalancername,region,aws_account} / (
-      sum:aws.elb.healthy_host_count.minimum${local.query_filter} by {loadbalancername,region,aws_account} +
-      sum:aws.elb.un_healthy_host_count.maximum${local.query_filter} by {loadbalancername,region,aws_account} )
+      sum:aws.elb.healthy_host_count.minimum${local.query_filter} by {loadbalancername,region,aws_accoun,env,datadog_managedt} / (
+      sum:aws.elb.healthy_host_count.minimum${local.query_filter} by {loadbalancername,region,aws_account,env,datadog_managed} +
+      sum:aws.elb.un_healthy_host_count.maximum${local.query_filter} by {loadbalancername,region,aws_account,env,datadog_managed} )
     ) <= ${var.no_healthy_instances_threshold_critical}
 END
 
diff --git a/aws/elb/variables.tf b/aws/elb/variables.tf
index d2235be..13357e9 100644
--- a/aws/elb/variables.tf
+++ b/aws/elb/variables.tf
@@ -46,6 +46,12 @@ variable "http_5xx_responses_threshold_warning" {
   type        = number
 }
 
+variable "http_5xx_responses_use_message" {
+  description = "Whether to use the query alert base message for HTTP 5xx responses monitor"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # HTTP 5xx Response Codes (backend)
 ########################################
@@ -79,6 +85,12 @@ variable "http_5xx_backend_responses_threshold_warning" {
   type        = number
 }
 
+variable "http_5xx_backend_responses_use_message" {
+  description = "Whether to use the query alert base message for HTTP 5xx backend responses monitor"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # Latency (backend)
 ########################################
@@ -112,6 +124,12 @@ variable "latency_threshold_warning" {
   type        = number
 }
 
+variable "latency_use_message" {
+  description = "Whether to use the query alert base message for latency monitor"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # No Healthy Instances
 ########################################
@@ -144,3 +162,10 @@ variable "no_healthy_instances_threshold_warning" {
   description = "Warning threshold (percentage)"
   type        = number
 }
+
+
+variable "no_healthy_instances_use_message" {
+  description = "Whether to use the query alert base message for no healthy instances monitor"
+  type        = bool
+  default     = true
+}
diff --git a/aws/lambda/README.md b/aws/lambda/README.md
index 2393fd1..77489b5 100644
--- a/aws/lambda/README.md
+++ b/aws/lambda/README.md
@@ -23,7 +23,7 @@ Configures the following for Lambda functions based on tag matches:
 
 | Name | Version |
 |------|---------|
-| <a name="provider_datadog"></a> [datadog](#provider\_datadog) | >= 3.37 |
+| <a name="provider_datadog"></a> [datadog](#provider\_datadog) | 3.37.0 |
 
 ## Modules
 
@@ -33,10 +33,13 @@ No modules.
 
 | Name | Type |
 |------|------|
-| [datadog_monitor.http_5xx_responses](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
-| [datadog_monitor.http_5xx_tg_responses](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
-| [datadog_monitor.latency](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
-| [datadog_monitor.no_healthy_instances](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
+| [datadog_monitor.cold_starts](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
+| [datadog_monitor.error_rate](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
+| [datadog_monitor.iterator_age](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
+| [datadog_monitor.iterator_age_forecast](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
+| [datadog_monitor.out_of_memory](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
+| [datadog_monitor.throttle_rate](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
+| [datadog_monitor.timeouts](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
 
 ## Inputs
 
@@ -46,44 +49,68 @@ No modules.
 | <a name="input_alert_critical_priority"></a> [alert\_critical\_priority](#input\_alert\_critical\_priority) | Priority for alerts within critical threshold (P1-P5, uses monitor defaults if not specified) | `string` | `null` | no |
 | <a name="input_alert_message"></a> [alert\_message](#input\_alert\_message) | Message to prepend to alert notifications | `string` | `"Alert"` | no |
 | <a name="input_alert_nodata_priority"></a> [alert\_nodata\_priority](#input\_alert\_nodata\_priority) | Priority for alerts within warning threshold (P1-P5, uses monitor defaults if not specified) | `string` | `null` | no |
-| <a name="input_base_tags"></a> [base\_tags](#input\_base\_tags) | Base tags (key:value format) to add to this type of check (combined with `local.tags` and `var.additional_tags`, generally you should not change this) | `list(string)` | <pre>[<br>  "resource:alb"<br>]</pre> | no |
+| <a name="input_base_tags"></a> [base\_tags](#input\_base\_tags) | Base tags (key:value format) to add to this type of check (combined with `local.tags` and `var.additional_tags`, generally you should not change this) | `list(string)` | <pre>[<br>  "resource:lambda"<br>]</pre> | no |
+| <a name="input_cold_starts_enabled"></a> [cold\_starts\_enabled](#input\_cold\_starts\_enabled) | Enable cold starts monitor (requires enhanced metrics) | `bool` | `false` | no |
+| <a name="input_cold_starts_evaluation_window"></a> [cold\_starts\_evaluation\_window](#input\_cold\_starts\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_4h"` | no |
+| <a name="input_cold_starts_no_data_window"></a> [cold\_starts\_no\_data\_window](#input\_cold\_starts\_no\_data\_window) | No data threshold (in minutes, null to disable) | `number` | `null` | no |
+| <a name="input_cold_starts_threshold_critical"></a> [cold\_starts\_threshold\_critical](#input\_cold\_starts\_threshold\_critical) | Critical threshold (count) | `number` | `null` | no |
+| <a name="input_cold_starts_threshold_warning"></a> [cold\_starts\_threshold\_warning](#input\_cold\_starts\_threshold\_warning) | Warning threshold (count) | `number` | `null` | no |
+| <a name="input_cold_starts_use_message"></a> [cold\_starts\_use\_message](#input\_cold\_starts\_use\_message) | Whether to use the query alert base message for cold starts monitor | `bool` | `false` | no |
 | <a name="input_cost_center"></a> [cost\_center](#input\_cost\_center) | Cost Center of the monitored resource (leave blank to omit tag) | `string` | `null` | no |
 | <a name="input_dashboard_link"></a> [dashboard\_link](#input\_dashboard\_link) | Dashboard link to include in message | `string` | `null` | no |
-| <a name="input_env"></a> [env](#input\_env) | Environment the monitored resource is in (leave blank to omit tag) | `string` | n/a | yes |
+| <a name="input_env"></a> [env](#input\_env) | Environment the monitored resource is in (leave blank to omit tag) | `string` | `null` | no |
+| <a name="input_error_rate_enabled"></a> [error\_rate\_enabled](#input\_error\_rate\_enabled) | Enable Lambda error rate monitor | `bool` | `true` | no |
+| <a name="input_error_rate_evaluation_window"></a> [error\_rate\_evaluation\_window](#input\_error\_rate\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
+| <a name="input_error_rate_no_data_window"></a> [error\_rate\_no\_data\_window](#input\_error\_rate\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
+| <a name="input_error_rate_threshold_critical"></a> [error\_rate\_threshold\_critical](#input\_error\_rate\_threshold\_critical) | Critical threshold (percentage, 0-100) | `number` | `75` | no |
+| <a name="input_error_rate_threshold_warning"></a> [error\_rate\_threshold\_warning](#input\_error\_rate\_threshold\_warning) | Warning threshold (percentage, 0-100) | `number` | `25` | no |
+| <a name="input_error_rate_use_message"></a> [error\_rate\_use\_message](#input\_error\_rate\_use\_message) | Whether to use the query alert base message for error rate monitor | `bool` | `true` | no |
 | <a name="input_evaluation_delay"></a> [evaluation\_delay](#input\_evaluation\_delay) | Monitor evaluation delay (see [https://docs.datadoghq.com/monitors/configuration/?tab=thresholdalert#set-alert-conditions](Datadog Docs)) | `number` | `900` | no |
-| <a name="input_http_5xx_responses_enabled"></a> [http\_5xx\_responses\_enabled](#input\_http\_5xx\_responses\_enabled) | Enable HTTP 5xx response monitor | `bool` | `false` | no |
-| <a name="input_http_5xx_responses_evaluation_window"></a> [http\_5xx\_responses\_evaluation\_window](#input\_http\_5xx\_responses\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
-| <a name="input_http_5xx_responses_no_data_window"></a> [http\_5xx\_responses\_no\_data\_window](#input\_http\_5xx\_responses\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
-| <a name="input_http_5xx_responses_threshold_critical"></a> [http\_5xx\_responses\_threshold\_critical](#input\_http\_5xx\_responses\_threshold\_critical) | Critical threshold (percentage, 0-100) | `number` | `75` | no |
-| <a name="input_http_5xx_responses_threshold_warning"></a> [http\_5xx\_responses\_threshold\_warning](#input\_http\_5xx\_responses\_threshold\_warning) | Warning threshold (percentage, 0-100) | `number` | `25` | no |
-| <a name="input_http_5xx_tg_responses_enabled"></a> [http\_5xx\_tg\_responses\_enabled](#input\_http\_5xx\_tg\_responses\_enabled) | Enable HTTP 5xx response monitor (target group) | `bool` | `false` | no |
-| <a name="input_http_5xx_tg_responses_evaluation_window"></a> [http\_5xx\_tg\_responses\_evaluation\_window](#input\_http\_5xx\_tg\_responses\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
-| <a name="input_http_5xx_tg_responses_no_data_window"></a> [http\_5xx\_tg\_responses\_no\_data\_window](#input\_http\_5xx\_tg\_responses\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
-| <a name="input_http_5xx_tg_responses_threshold_critical"></a> [http\_5xx\_tg\_responses\_threshold\_critical](#input\_http\_5xx\_tg\_responses\_threshold\_critical) | Critical threshold (percentage, 0-100) | `number` | `75` | no |
-| <a name="input_http_5xx_tg_responses_threshold_warning"></a> [http\_5xx\_tg\_responses\_threshold\_warning](#input\_http\_5xx\_tg\_responses\_threshold\_warning) | Warning threshold (percentage, 0-100) | `number` | `25` | no |
-| <a name="input_latency_enabled"></a> [latency\_enabled](#input\_latency\_enabled) | Enable latency monitor | `bool` | `false` | no |
-| <a name="input_latency_evaluation_window"></a> [latency\_evaluation\_window](#input\_latency\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
-| <a name="input_latency_no_data_window"></a> [latency\_no\_data\_window](#input\_latency\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
-| <a name="input_latency_threshold_critical"></a> [latency\_threshold\_critical](#input\_latency\_threshold\_critical) | Critical threshold (seconds) | `number` | `null` | no |
-| <a name="input_latency_threshold_warning"></a> [latency\_threshold\_warning](#input\_latency\_threshold\_warning) | Warning threshold (seconds) | `number` | `null` | no |
+| <a name="input_iterator_age_enabled"></a> [iterator\_age\_enabled](#input\_iterator\_age\_enabled) | Enable iterator age monitor | `bool` | `false` | no |
+| <a name="input_iterator_age_evaluation_window"></a> [iterator\_age\_evaluation\_window](#input\_iterator\_age\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_1h"` | no |
+| <a name="input_iterator_age_forecast_enabled"></a> [iterator\_age\_forecast\_enabled](#input\_iterator\_age\_forecast\_enabled) | Enable iterator age monitor | `bool` | `false` | no |
+| <a name="input_iterator_age_forecast_evaluation_window"></a> [iterator\_age\_forecast\_evaluation\_window](#input\_iterator\_age\_forecast\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_1d"` | no |
+| <a name="input_iterator_age_forecast_no_data_window"></a> [iterator\_age\_forecast\_no\_data\_window](#input\_iterator\_age\_forecast\_no\_data\_window) | No data threshold (in minutes, null to disable) | `number` | `null` | no |
+| <a name="input_iterator_age_forecast_use_message"></a> [iterator\_age\_forecast\_use\_message](#input\_iterator\_age\_forecast\_use\_message) | Whether to use the query alert base message for iterator age forecast monitor | `bool` | `false` | no |
+| <a name="input_iterator_age_no_data_window"></a> [iterator\_age\_no\_data\_window](#input\_iterator\_age\_no\_data\_window) | No data threshold (in minutes, null to disable) | `number` | `null` | no |
+| <a name="input_iterator_age_threshold_critical"></a> [iterator\_age\_threshold\_critical](#input\_iterator\_age\_threshold\_critical) | Critical threshold (milliseconds) | `number` | `86400000` | no |
+| <a name="input_iterator_age_threshold_warning"></a> [iterator\_age\_threshold\_warning](#input\_iterator\_age\_threshold\_warning) | Warning threshold (milliseconds) | `number` | `null` | no |
+| <a name="input_iterator_age_use_message"></a> [iterator\_age\_use\_message](#input\_iterator\_age\_use\_message) | Whether to use the query alert base message for iterator age monitor | `bool` | `false` | no |
 | <a name="input_monitor_exclude_tags"></a> [monitor\_exclude\_tags](#input\_monitor\_exclude\_tags) | Tags to be excluded in the monitoring query. Specify in key:value format | `list(string)` | `[]` | no |
 | <a name="input_monitor_include_tags"></a> [monitor\_include\_tags](#input\_monitor\_include\_tags) | Tags to be included in the monitoring query. Specify in key:value format | `list(string)` | `[]` | no |
 | <a name="input_new_group_delay"></a> [new\_group\_delay](#input\_new\_group\_delay) | Delay in seconds before generating alerts for a new resource | `number` | `300` | no |
-| <a name="input_no_healthy_instances_enabled"></a> [no\_healthy\_instances\_enabled](#input\_no\_healthy\_instances\_enabled) | Enable no healthy instances monitor | `bool` | `true` | no |
-| <a name="input_no_healthy_instances_evaluation_window"></a> [no\_healthy\_instances\_evaluation\_window](#input\_no\_healthy\_instances\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
-| <a name="input_no_healthy_instances_no_data_window"></a> [no\_healthy\_instances\_no\_data\_window](#input\_no\_healthy\_instances\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
-| <a name="input_no_healthy_instances_threshold_warning"></a> [no\_healthy\_instances\_threshold\_warning](#input\_no\_healthy\_instances\_threshold\_warning) | Warning threshold (percentage, 0 to disable) | `number` | `0` | no |
 | <a name="input_notify_alert_override"></a> [notify\_alert\_override](#input\_notify\_alert\_override) | List of notifications for alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_crit_override"></a> [notify\_crit\_override](#input\_notify\_crit\_override) | List of notifications for 24x7 alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_default"></a> [notify\_default](#input\_notify\_default) | List of alert notifications (can be overridden based on alert type) | `list(string)` | n/a | yes |
 | <a name="input_notify_no_data"></a> [notify\_no\_data](#input\_notify\_no\_data) | Alert if no matching data is found | `bool` | `false` | no |
 | <a name="input_notify_nodata_override"></a> [notify\_nodata\_override](#input\_notify\_nodata\_override) | List of notifications for no data (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_nonprod_override"></a> [notify\_nonprod\_override](#input\_notify\_nonprod\_override) | List of notifications for non-prod alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_prod_override"></a> [notify\_prod\_override](#input\_notify\_prod\_override) | List of notifications for 12x5 prod alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_recovery_override"></a> [notify\_recovery\_override](#input\_notify\_recovery\_override) | List of notifications for alert recovery (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_warn_override"></a> [notify\_warn\_override](#input\_notify\_warn\_override) | List of notifications for alerts in warning threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_out_of_memory_enabled"></a> [out\_of\_memory\_enabled](#input\_out\_of\_memory\_enabled) | Enable out of memory monitor (requires enhanced metrics) | `bool` | `true` | no |
+| <a name="input_out_of_memory_evaluation_window"></a> [out\_of\_memory\_evaluation\_window](#input\_out\_of\_memory\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_4h"` | no |
+| <a name="input_out_of_memory_no_data_window"></a> [out\_of\_memory\_no\_data\_window](#input\_out\_of\_memory\_no\_data\_window) | No data threshold (in minutes, null to disable) | `number` | `null` | no |
+| <a name="input_out_of_memory_threshold_critical"></a> [out\_of\_memory\_threshold\_critical](#input\_out\_of\_memory\_threshold\_critical) | Critical threshold (count) | `number` | `5` | no |
+| <a name="input_out_of_memory_threshold_warning"></a> [out\_of\_memory\_threshold\_warning](#input\_out\_of\_memory\_threshold\_warning) | Warning threshold (count) | `number` | `null` | no |
+| <a name="input_out_of_memory_use_message"></a> [out\_of\_memory\_use\_message](#input\_out\_of\_memory\_use\_message) | Whether to use the query alert base message for out of memory monitor | `bool` | `false` | no |
 | <a name="input_renotify_interval"></a> [renotify\_interval](#input\_renotify\_interval) | Interval in minutes to re-send notifications about an alert | `number` | `0` | no |
 | <a name="input_runbook_link"></a> [runbook\_link](#input\_runbook\_link) | Runbook link to include in message | `string` | `null` | no |
 | <a name="input_service"></a> [service](#input\_service) | Service associated with the monitored resource (leave blank to omit tag) | `string` | `null` | no |
 | <a name="input_team"></a> [team](#input\_team) | Team supporting the monitored resource (leave blank to omit tag) | `string` | `null` | no |
+| <a name="input_throttle_rate_enabled"></a> [throttle\_rate\_enabled](#input\_throttle\_rate\_enabled) | Enable Lambda throttle rate monitor | `bool` | `true` | no |
+| <a name="input_throttle_rate_evaluation_window"></a> [throttle\_rate\_evaluation\_window](#input\_throttle\_rate\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
+| <a name="input_throttle_rate_no_data_window"></a> [throttle\_rate\_no\_data\_window](#input\_throttle\_rate\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
+| <a name="input_throttle_rate_threshold_critical"></a> [throttle\_rate\_threshold\_critical](#input\_throttle\_rate\_threshold\_critical) | Critical threshold (percentage, 0-100) | `number` | `75` | no |
+| <a name="input_throttle_rate_threshold_warning"></a> [throttle\_rate\_threshold\_warning](#input\_throttle\_rate\_threshold\_warning) | Warning threshold (percentage, 0-100) | `number` | `25` | no |
+| <a name="input_throttle_rate_use_message"></a> [throttle\_rate\_use\_message](#input\_throttle\_rate\_use\_message) | Whether to use the query alert base message for throttle rate monitor | `bool` | `false` | no |
 | <a name="input_timeout_h"></a> [timeout\_h](#input\_timeout\_h) | Auto-resolve alert in specified hours if condition no longer matches | `number` | `0` | no |
+| <a name="input_timeouts_enabled"></a> [timeouts\_enabled](#input\_timeouts\_enabled) | Enable timeout count monitor | `bool` | `true` | no |
+| <a name="input_timeouts_evaluation_window"></a> [timeouts\_evaluation\_window](#input\_timeouts\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
+| <a name="input_timeouts_no_data_window"></a> [timeouts\_no\_data\_window](#input\_timeouts\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
+| <a name="input_timeouts_threshold_critical"></a> [timeouts\_threshold\_critical](#input\_timeouts\_threshold\_critical) | Critical threshold (count) | `number` | `75` | no |
+| <a name="input_timeouts_threshold_warning"></a> [timeouts\_threshold\_warning](#input\_timeouts\_threshold\_warning) | Warning threshold (count) | `number` | `25` | no |
+| <a name="input_timeouts_use_message"></a> [timeouts\_use\_message](#input\_timeouts\_use\_message) | Whether to use the query alert base message for timeouts monitor | `bool` | `false` | no |
 | <a name="input_title_prefix"></a> [title\_prefix](#input\_title\_prefix) | Prefix all alerts with specified value in brackets | `string` | `null` | no |
 | <a name="input_title_suffix"></a> [title\_suffix](#input\_title\_suffix) | Suffix all alerts with specified value in parenthesis | `string` | `null` | no |
 | <a name="input_warn_priority"></a> [warn\_priority](#input\_warn\_priority) | Priority for alerts with no data (P1-P5, uses monitor defaults if not specified) | `string` | `null` | no |
diff --git a/aws/lambda/main.tf b/aws/lambda/main.tf
index 1eb0d13..e37a8f4 100644
--- a/aws/lambda/main.tf
+++ b/aws/lambda/main.tf
@@ -4,7 +4,7 @@ locals {
   monitor_warn_default_priority   = null
   monitor_nodata_default_priority = null
 
-  title_prefix = "${var.title_prefix == null ? "" : "[${var.title_prefix}]"}"
+  title_prefix = var.title_prefix == null ? "" : "[${var.title_prefix}]"
   title_suffix = var.title_suffix == null ? "" : " (${var.title_suffix})"
 
   cold_start_query_filter = local.query_filter == "{*}" ? "{cold_start:true}" : replace(local.query_filter, "{", "{cold_star:true,")
@@ -14,8 +14,8 @@ resource "datadog_monitor" "error_rate" {
   count = var.error_rate_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "Lambda error rate - {{functionname.name}} - {{value}}%", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.error_rate_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -29,8 +29,8 @@ resource "datadog_monitor" "error_rate" {
 
   query = <<END
     min(${var.error_rate_evaluation_window}):
-      default(avg:aws.lambda.errors${local.query_filter} by {functionname,region,aws_account,env}.as_rate(), 0) / (
-      default(avg:aws.lambda.invocations${local.query_filter} by {functionname,region,aws_account,env}.as_rate(), 1)
+      default(avg:aws.lambda.errors${local.query_filter} by {functionname,region,aws_account,env,datadog_managed}.as_rate(), 0) / (
+      default(avg:aws.lambda.invocations${local.query_filter} by {functionname,region,aws_account,env,datadog_managed}.as_rate(), 1)
     ) * 100 > ${var.error_rate_threshold_critical}
 END
 
@@ -44,8 +44,8 @@ resource "datadog_monitor" "timeouts" {
   count = var.timeouts_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "Lambda timeouts - {{functionname.name}}", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.timeouts_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -59,8 +59,8 @@ resource "datadog_monitor" "timeouts" {
 
   query = <<END
     min(${var.timeouts_evaluation_window}):
-      default(avg:aws.lambda.duration.maximum${local.query_filter} by {functionname,region,aws_account,env}.as_rate(), 0) / (
-      (default(avg:aws.lambda.timeout${local.query_filter} by {functionname,region,aws_account,env}.as_rate(), 1) * 1000)
+      default(avg:aws.lambda.duration.maximum${local.query_filter} by {functionname,region,aws_account,env,datadog_managed}.as_rate(), 0) / (
+      (default(avg:aws.lambda.timeout${local.query_filter} by {functionname,region,aws_account,env,datadog_managed}.as_rate(), 1) * 1000)
     )  > ${var.timeouts_threshold_critical}
 END
 
@@ -74,8 +74,8 @@ resource "datadog_monitor" "cold_starts" {
   count = var.cold_starts_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "Lambda cold starts - {{functionname.name}}", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.cold_starts_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -89,8 +89,8 @@ resource "datadog_monitor" "cold_starts" {
 
   query = <<END
     min(${var.cold_starts_evaluation_window}):
-      default(avg:aws.lambda.enhanced.invocations${local.cold_start_query_filter} by {functionname,region,aws_account,env}.as_rate(), 0) / (
-      default(avg:aws.lambda.enhanced.invocations${local.query_filter} by {functionname,region,aws_account,env}.as_rate(), 1)
+      default(avg:aws.lambda.enhanced.invocations${local.cold_start_query_filter} by {functionname,region,aws_account,env,datadog_managed}.as_rate(), 0) / (
+      default(avg:aws.lambda.enhanced.invocations${local.query_filter} by {functionname,region,aws_account,env,datadog_managed}.as_rate(), 1)
     ) > ${var.cold_starts_threshold_critical}
 END
 
@@ -104,8 +104,8 @@ resource "datadog_monitor" "out_of_memory" {
   count = var.out_of_memory_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "Lambda out of memory - {{functionname.name}}", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.out_of_memory_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -134,8 +134,8 @@ resource "datadog_monitor" "iterator_age" {
   count = var.iterator_age_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "Lambda iterator age - {{functionname.name}}", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.iterator_age_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -149,7 +149,7 @@ resource "datadog_monitor" "iterator_age" {
 
   query = <<END
     max(${var.iterator_age_evaluation_window}):
-      default(avg:aws.lambda.iterator_age.maximum${local.query_filter} by {functionname,region,aws_account,env}
+      default(avg:aws.lambda.iterator_age.maximum${local.query_filter} by {functionname,region,aws_account,env,datadog_managed}
     > ${var.iterator_age_threshold_critical}
 END
 
@@ -163,8 +163,8 @@ resource "datadog_monitor" "iterator_age_forecast" {
   count = var.iterator_age_forecast_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "Lambda stream data loss forecasted - {{functionname.name}}", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.iterator_age_forecast_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -191,8 +191,8 @@ resource "datadog_monitor" "throttle_rate" {
   count = var.throttle_rate_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "Lambda throttle rate - {{functionname.name}}", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.throttle_rate_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
diff --git a/aws/lambda/variables.tf b/aws/lambda/variables.tf
index 8aa64cc..4332d90 100644
--- a/aws/lambda/variables.tf
+++ b/aws/lambda/variables.tf
@@ -17,7 +17,7 @@ variable "base_tags" {
 # Lambda error rate
 ########################################
 variable "error_rate_enabled" {
-  default     = false
+  default     = true
   description = "Enable Lambda error rate monitor"
   type        = bool
 }
@@ -46,11 +46,17 @@ variable "error_rate_threshold_warning" {
   type        = number
 }
 
+variable "error_rate_use_message" {
+  description = "Whether to use the query alert base message for error rate monitor"
+  type        = bool
+  default     = true
+}
+
 ########################################
 # Lambda timeouts
 ########################################
 variable "timeouts_enabled" {
-  default     = false
+  default     = true
   description = "Enable timeout count monitor"
   type        = bool
 }
@@ -79,6 +85,12 @@ variable "timeouts_threshold_warning" {
   type        = number
 }
 
+variable "timeouts_use_message" {
+  description = "Whether to use the query alert base message for timeouts monitor"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # Cold start monitor
 ########################################
@@ -112,11 +124,17 @@ variable "cold_starts_threshold_warning" {
   type        = number
 }
 
+variable "cold_starts_use_message" {
+  description = "Whether to use the query alert base message for cold starts monitor"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # OOM monitor
 ########################################
 variable "out_of_memory_enabled" {
-  default     = false
+  default     = true
   description = "Enable out of memory monitor (requires enhanced metrics)"
   type        = bool
 }
@@ -134,7 +152,7 @@ variable "out_of_memory_no_data_window" {
 }
 
 variable "out_of_memory_threshold_critical" {
-  default     = null
+  default     = 5
   description = "Critical threshold (count)"
   type        = number
 }
@@ -145,6 +163,12 @@ variable "out_of_memory_threshold_warning" {
   type        = number
 }
 
+variable "out_of_memory_use_message" {
+  description = "Whether to use the query alert base message for out of memory monitor"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # Iterator Age monitor
 ########################################
@@ -178,6 +202,12 @@ variable "iterator_age_threshold_warning" {
   type        = number
 }
 
+variable "iterator_age_use_message" {
+  description = "Whether to use the query alert base message for iterator age monitor"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # Iterator Age forecast data loss
 ########################################
@@ -199,11 +229,17 @@ variable "iterator_age_forecast_no_data_window" {
   type        = number
 }
 
+variable "iterator_age_forecast_use_message" {
+  description = "Whether to use the query alert base message for iterator age forecast monitor"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # Lambda throttle rate
 ########################################
 variable "throttle_rate_enabled" {
-  default     = false
+  default     = true
   description = "Enable Lambda throttle rate monitor"
   type        = bool
 }
@@ -231,3 +267,9 @@ variable "throttle_rate_threshold_warning" {
   description = "Warning threshold (percentage, 0-100)"
   type        = number
 }
+
+variable "throttle_rate_use_message" {
+  description = "Whether to use the query alert base message for throttle rate monitor"
+  type        = bool
+  default     = false
+}
diff --git a/aws/rds/README.md b/aws/rds/README.md
index cc05203..130995c 100644
--- a/aws/rds/README.md
+++ b/aws/rds/README.md
@@ -21,7 +21,7 @@ Configures the following for RDS databases based on tag matches:
 
 | Name | Version |
 |------|---------|
-| <a name="provider_datadog"></a> [datadog](#provider\_datadog) | >= 3.37 |
+| <a name="provider_datadog"></a> [datadog](#provider\_datadog) | 3.37.0 |
 
 ## Modules
 
@@ -31,10 +31,10 @@ No modules.
 
 | Name | Type |
 |------|------|
-| [datadog_monitor.http_5xx_responses](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
-| [datadog_monitor.http_5xx_tg_responses](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
-| [datadog_monitor.latency](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
-| [datadog_monitor.no_healthy_instances](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
+| [datadog_monitor.connection_count_anomaly](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
+| [datadog_monitor.cpu_utilization](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
+| [datadog_monitor.cpu_utilization_anomaly](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
+| [datadog_monitor.used_storage](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
 
 ## Inputs
 
@@ -44,37 +44,49 @@ No modules.
 | <a name="input_alert_critical_priority"></a> [alert\_critical\_priority](#input\_alert\_critical\_priority) | Priority for alerts within critical threshold (P1-P5, uses monitor defaults if not specified) | `string` | `null` | no |
 | <a name="input_alert_message"></a> [alert\_message](#input\_alert\_message) | Message to prepend to alert notifications | `string` | `"Alert"` | no |
 | <a name="input_alert_nodata_priority"></a> [alert\_nodata\_priority](#input\_alert\_nodata\_priority) | Priority for alerts within warning threshold (P1-P5, uses monitor defaults if not specified) | `string` | `null` | no |
-| <a name="input_base_tags"></a> [base\_tags](#input\_base\_tags) | Base tags (key:value format) to add to this type of check (combined with `local.tags` and `var.additional_tags`, generally you should not change this) | `list(string)` | <pre>[<br>  "resource:alb"<br>]</pre> | no |
+| <a name="input_base_tags"></a> [base\_tags](#input\_base\_tags) | Base tags (key:value format) to add to this type of check (combined with `local.tags` and `var.additional_tags`, generally you should not change this) | `list(string)` | <pre>[<br>  "resource:rds"<br>]</pre> | no |
+| <a name="input_connection_count_anomaly_deviations"></a> [connection\_count\_anomaly\_deviations](#input\_connection\_count\_anomaly\_deviations) | Standard deviations | `number` | `3` | no |
+| <a name="input_connection_count_anomaly_enabled"></a> [connection\_count\_anomaly\_enabled](#input\_connection\_count\_anomaly\_enabled) | Enable CPU utilization anomaly monitor | `bool` | `true` | no |
+| <a name="input_connection_count_anomaly_evaluation_window"></a> [connection\_count\_anomaly\_evaluation\_window](#input\_connection\_count\_anomaly\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_1h"` | no |
+| <a name="input_connection_count_anomaly_no_data_window"></a> [connection\_count\_anomaly\_no\_data\_window](#input\_connection\_count\_anomaly\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
+| <a name="input_connection_count_anomaly_recovery_window"></a> [connection\_count\_anomaly\_recovery\_window](#input\_connection\_count\_anomaly\_recovery\_window) | Recovery window for anomaly monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_15m"` | no |
+| <a name="input_connection_count_anomaly_rollup"></a> [connection\_count\_anomaly\_rollup](#input\_connection\_count\_anomaly\_rollup) | Rollup interval (must be sized based on evaluation window/span and seasonaility) | `number` | `60` | no |
+| <a name="input_connection_count_anomaly_seasonality"></a> [connection\_count\_anomaly\_seasonality](#input\_connection\_count\_anomaly\_seasonality) | Seasonaility (hourly, daily, weekly) | `string` | `"weekly"` | no |
+| <a name="input_connection_count_anomaly_threshold_critical"></a> [connection\_count\_anomaly\_threshold\_critical](#input\_connection\_count\_anomaly\_threshold\_critical) | Critical threshold (percent) | `number` | `0.75` | no |
+| <a name="input_connection_count_anomaly_threshold_warning"></a> [connection\_count\_anomaly\_threshold\_warning](#input\_connection\_count\_anomaly\_threshold\_warning) | Warning threshold (percent) | `number` | `null` | no |
+| <a name="input_connection_count_anomaly_trigger_window"></a> [connection\_count\_anomaly\_trigger\_window](#input\_connection\_count\_anomaly\_trigger\_window) | Trigger window for anomaly monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_1h"` | no |
+| <a name="input_connection_count_anomaly_use_message"></a> [connection\_count\_anomaly\_use\_message](#input\_connection\_count\_anomaly\_use\_message) | Whether to use the query alert base message for connection count anomaly monitor | `bool` | `true` | no |
 | <a name="input_cost_center"></a> [cost\_center](#input\_cost\_center) | Cost Center of the monitored resource (leave blank to omit tag) | `string` | `null` | no |
+| <a name="input_cpu_utilization_anomaly_deviations"></a> [cpu\_utilization\_anomaly\_deviations](#input\_cpu\_utilization\_anomaly\_deviations) | Standard deviations | `number` | `4` | no |
+| <a name="input_cpu_utilization_anomaly_enabled"></a> [cpu\_utilization\_anomaly\_enabled](#input\_cpu\_utilization\_anomaly\_enabled) | Enable CPU utilization anomaly monitor | `bool` | `false` | no |
+| <a name="input_cpu_utilization_anomaly_evaluation_window"></a> [cpu\_utilization\_anomaly\_evaluation\_window](#input\_cpu\_utilization\_anomaly\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_1h"` | no |
+| <a name="input_cpu_utilization_anomaly_no_data_window"></a> [cpu\_utilization\_anomaly\_no\_data\_window](#input\_cpu\_utilization\_anomaly\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
+| <a name="input_cpu_utilization_anomaly_recovery_window"></a> [cpu\_utilization\_anomaly\_recovery\_window](#input\_cpu\_utilization\_anomaly\_recovery\_window) | Recovery window for anomaly monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_15m"` | no |
+| <a name="input_cpu_utilization_anomaly_rollup"></a> [cpu\_utilization\_anomaly\_rollup](#input\_cpu\_utilization\_anomaly\_rollup) | Rollup interval (must be sized based on evaluation window/span and seasonaility) | `number` | `60` | no |
+| <a name="input_cpu_utilization_anomaly_seasonality"></a> [cpu\_utilization\_anomaly\_seasonality](#input\_cpu\_utilization\_anomaly\_seasonality) | Seasonaility (hourly, daily, weekly) | `string` | `"weekly"` | no |
+| <a name="input_cpu_utilization_anomaly_threshold_critical"></a> [cpu\_utilization\_anomaly\_threshold\_critical](#input\_cpu\_utilization\_anomaly\_threshold\_critical) | Critical threshold (percent) | `number` | `null` | no |
+| <a name="input_cpu_utilization_anomaly_threshold_warning"></a> [cpu\_utilization\_anomaly\_threshold\_warning](#input\_cpu\_utilization\_anomaly\_threshold\_warning) | Warning threshold (percent) | `number` | `null` | no |
+| <a name="input_cpu_utilization_anomaly_trigger_window"></a> [cpu\_utilization\_anomaly\_trigger\_window](#input\_cpu\_utilization\_anomaly\_trigger\_window) | Trigger window for anomaly monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_1h"` | no |
+| <a name="input_cpu_utilization_anomaly_use_message"></a> [cpu\_utilization\_anomaly\_use\_message](#input\_cpu\_utilization\_anomaly\_use\_message) | Whether to use the query alert base message for CPU utilization anomaly monitor | `bool` | `false` | no |
+| <a name="input_cpu_utilization_enabled"></a> [cpu\_utilization\_enabled](#input\_cpu\_utilization\_enabled) | Enable CPU utilization monitor | `bool` | `true` | no |
+| <a name="input_cpu_utilization_evaluation_window"></a> [cpu\_utilization\_evaluation\_window](#input\_cpu\_utilization\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
+| <a name="input_cpu_utilization_no_data_window"></a> [cpu\_utilization\_no\_data\_window](#input\_cpu\_utilization\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
+| <a name="input_cpu_utilization_threshold_critical"></a> [cpu\_utilization\_threshold\_critical](#input\_cpu\_utilization\_threshold\_critical) | Critical threshold (percent) | `number` | `90` | no |
+| <a name="input_cpu_utilization_threshold_warning"></a> [cpu\_utilization\_threshold\_warning](#input\_cpu\_utilization\_threshold\_warning) | Warning threshold (percent) | `number` | `80` | no |
+| <a name="input_cpu_utilization_use_message"></a> [cpu\_utilization\_use\_message](#input\_cpu\_utilization\_use\_message) | Whether to use the query alert base message for CPU utilization monitor | `bool` | `false` | no |
 | <a name="input_dashboard_link"></a> [dashboard\_link](#input\_dashboard\_link) | Dashboard link to include in message | `string` | `null` | no |
-| <a name="input_env"></a> [env](#input\_env) | Environment the monitored resource is in (leave blank to omit tag) | `string` | n/a | yes |
+| <a name="input_env"></a> [env](#input\_env) | Environment the monitored resource is in (leave blank to omit tag) | `string` | `null` | no |
 | <a name="input_evaluation_delay"></a> [evaluation\_delay](#input\_evaluation\_delay) | Monitor evaluation delay (see [https://docs.datadoghq.com/monitors/configuration/?tab=thresholdalert#set-alert-conditions](Datadog Docs)) | `number` | `900` | no |
-| <a name="input_http_5xx_responses_enabled"></a> [http\_5xx\_responses\_enabled](#input\_http\_5xx\_responses\_enabled) | Enable HTTP 5xx response monitor | `bool` | `false` | no |
-| <a name="input_http_5xx_responses_evaluation_window"></a> [http\_5xx\_responses\_evaluation\_window](#input\_http\_5xx\_responses\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
-| <a name="input_http_5xx_responses_no_data_window"></a> [http\_5xx\_responses\_no\_data\_window](#input\_http\_5xx\_responses\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
-| <a name="input_http_5xx_responses_threshold_critical"></a> [http\_5xx\_responses\_threshold\_critical](#input\_http\_5xx\_responses\_threshold\_critical) | Critical threshold (percentage, 0-100) | `number` | `75` | no |
-| <a name="input_http_5xx_responses_threshold_warning"></a> [http\_5xx\_responses\_threshold\_warning](#input\_http\_5xx\_responses\_threshold\_warning) | Warning threshold (percentage, 0-100) | `number` | `25` | no |
-| <a name="input_http_5xx_tg_responses_enabled"></a> [http\_5xx\_tg\_responses\_enabled](#input\_http\_5xx\_tg\_responses\_enabled) | Enable HTTP 5xx response monitor (target group) | `bool` | `false` | no |
-| <a name="input_http_5xx_tg_responses_evaluation_window"></a> [http\_5xx\_tg\_responses\_evaluation\_window](#input\_http\_5xx\_tg\_responses\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
-| <a name="input_http_5xx_tg_responses_no_data_window"></a> [http\_5xx\_tg\_responses\_no\_data\_window](#input\_http\_5xx\_tg\_responses\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
-| <a name="input_http_5xx_tg_responses_threshold_critical"></a> [http\_5xx\_tg\_responses\_threshold\_critical](#input\_http\_5xx\_tg\_responses\_threshold\_critical) | Critical threshold (percentage, 0-100) | `number` | `75` | no |
-| <a name="input_http_5xx_tg_responses_threshold_warning"></a> [http\_5xx\_tg\_responses\_threshold\_warning](#input\_http\_5xx\_tg\_responses\_threshold\_warning) | Warning threshold (percentage, 0-100) | `number` | `25` | no |
-| <a name="input_latency_enabled"></a> [latency\_enabled](#input\_latency\_enabled) | Enable latency monitor | `bool` | `false` | no |
-| <a name="input_latency_evaluation_window"></a> [latency\_evaluation\_window](#input\_latency\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
-| <a name="input_latency_no_data_window"></a> [latency\_no\_data\_window](#input\_latency\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
-| <a name="input_latency_threshold_critical"></a> [latency\_threshold\_critical](#input\_latency\_threshold\_critical) | Critical threshold (seconds) | `number` | `null` | no |
-| <a name="input_latency_threshold_warning"></a> [latency\_threshold\_warning](#input\_latency\_threshold\_warning) | Warning threshold (seconds) | `number` | `null` | no |
 | <a name="input_monitor_exclude_tags"></a> [monitor\_exclude\_tags](#input\_monitor\_exclude\_tags) | Tags to be excluded in the monitoring query. Specify in key:value format | `list(string)` | `[]` | no |
 | <a name="input_monitor_include_tags"></a> [monitor\_include\_tags](#input\_monitor\_include\_tags) | Tags to be included in the monitoring query. Specify in key:value format | `list(string)` | `[]` | no |
 | <a name="input_new_group_delay"></a> [new\_group\_delay](#input\_new\_group\_delay) | Delay in seconds before generating alerts for a new resource | `number` | `300` | no |
-| <a name="input_no_healthy_instances_enabled"></a> [no\_healthy\_instances\_enabled](#input\_no\_healthy\_instances\_enabled) | Enable no healthy instances monitor | `bool` | `true` | no |
-| <a name="input_no_healthy_instances_evaluation_window"></a> [no\_healthy\_instances\_evaluation\_window](#input\_no\_healthy\_instances\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
-| <a name="input_no_healthy_instances_no_data_window"></a> [no\_healthy\_instances\_no\_data\_window](#input\_no\_healthy\_instances\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
-| <a name="input_no_healthy_instances_threshold_warning"></a> [no\_healthy\_instances\_threshold\_warning](#input\_no\_healthy\_instances\_threshold\_warning) | Warning threshold (percentage, 0 to disable) | `number` | `0` | no |
 | <a name="input_notify_alert_override"></a> [notify\_alert\_override](#input\_notify\_alert\_override) | List of notifications for alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_crit_override"></a> [notify\_crit\_override](#input\_notify\_crit\_override) | List of notifications for 24x7 alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_default"></a> [notify\_default](#input\_notify\_default) | List of alert notifications (can be overridden based on alert type) | `list(string)` | n/a | yes |
 | <a name="input_notify_no_data"></a> [notify\_no\_data](#input\_notify\_no\_data) | Alert if no matching data is found | `bool` | `false` | no |
 | <a name="input_notify_nodata_override"></a> [notify\_nodata\_override](#input\_notify\_nodata\_override) | List of notifications for no data (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_nonprod_override"></a> [notify\_nonprod\_override](#input\_notify\_nonprod\_override) | List of notifications for non-prod alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_prod_override"></a> [notify\_prod\_override](#input\_notify\_prod\_override) | List of notifications for 12x5 prod alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_recovery_override"></a> [notify\_recovery\_override](#input\_notify\_recovery\_override) | List of notifications for alert recovery (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_warn_override"></a> [notify\_warn\_override](#input\_notify\_warn\_override) | List of notifications for alerts in warning threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_renotify_interval"></a> [renotify\_interval](#input\_renotify\_interval) | Interval in minutes to re-send notifications about an alert | `number` | `0` | no |
@@ -84,6 +96,12 @@ No modules.
 | <a name="input_timeout_h"></a> [timeout\_h](#input\_timeout\_h) | Auto-resolve alert in specified hours if condition no longer matches | `number` | `0` | no |
 | <a name="input_title_prefix"></a> [title\_prefix](#input\_title\_prefix) | Prefix all alerts with specified value in brackets | `string` | `null` | no |
 | <a name="input_title_suffix"></a> [title\_suffix](#input\_title\_suffix) | Suffix all alerts with specified value in parenthesis | `string` | `null` | no |
+| <a name="input_used_storage_enabled"></a> [used\_storage\_enabled](#input\_used\_storage\_enabled) | Enable used storage monitor | `bool` | `true` | no |
+| <a name="input_used_storage_evaluation_window"></a> [used\_storage\_evaluation\_window](#input\_used\_storage\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_15m"` | no |
+| <a name="input_used_storage_no_data_window"></a> [used\_storage\_no\_data\_window](#input\_used\_storage\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
+| <a name="input_used_storage_threshold_critical"></a> [used\_storage\_threshold\_critical](#input\_used\_storage\_threshold\_critical) | Critical threshold (percentage, 0-100) | `number` | `90` | no |
+| <a name="input_used_storage_threshold_warning"></a> [used\_storage\_threshold\_warning](#input\_used\_storage\_threshold\_warning) | Warning threshold (percentage, 0-100) | `number` | `80` | no |
+| <a name="input_used_storage_use_message"></a> [used\_storage\_use\_message](#input\_used\_storage\_use\_message) | Whether to use the query alert base message for used storage monitor | `bool` | `true` | no |
 | <a name="input_warn_priority"></a> [warn\_priority](#input\_warn\_priority) | Priority for alerts with no data (P1-P5, uses monitor defaults if not specified) | `string` | `null` | no |
 
 ## Outputs
diff --git a/aws/rds/main.tf b/aws/rds/main.tf
index bbb3292..c64956c 100644
--- a/aws/rds/main.tf
+++ b/aws/rds/main.tf
@@ -4,7 +4,7 @@ locals {
   monitor_warn_default_priority   = null
   monitor_nodata_default_priority = null
 
-  title_prefix = "${var.title_prefix == null ? "" : "[${var.title_prefix}]"}"
+  title_prefix = var.title_prefix == null ? "" : "[${var.title_prefix}]"
   title_suffix = var.title_suffix == null ? "" : " (${var.title_suffix})"
 }
 
@@ -12,8 +12,8 @@ resource "datadog_monitor" "connection_count_anomaly" {
   count = var.connection_count_anomaly_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "RDS connection count anomalous activity - {{dbinstanceidentifier.name}}", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.connection_count_anomaly_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -27,7 +27,7 @@ resource "datadog_monitor" "connection_count_anomaly" {
 
   query = <<END
     avg(${var.connection_count_anomaly_evaluation_window}):anomalies(
-      avg:aws.rds.database_connections${local.query_filter} by {dbinstanceidentifier,region,aws_account,env}, 'agile', ${var.connection_count_anomaly_deviations},
+      avg:aws.rds.database_connections${local.query_filter} by {dbinstanceidentifier,region,aws_account,env,datadog_managed}, 'agile', ${var.connection_count_anomaly_deviations},
       direction='both', count_default_zero='true', interval=${var.connection_count_anomaly_rollup},
       seasonality='${var.connection_count_anomaly_seasonality}'
     ) >= ${var.connection_count_anomaly_threshold_critical}
@@ -48,8 +48,8 @@ resource "datadog_monitor" "cpu_utilization" {
   count = var.cpu_utilization_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "RDS CPU Utilization - {{dbinstanceidentifier.name}} - {{value}}%", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.cpu_utilization_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -63,7 +63,7 @@ resource "datadog_monitor" "cpu_utilization" {
 
   query = <<END
     avg(${var.cpu_utilization_evaluation_window}):
-      avg:aws.rds.cpuutilization${local.query_filter} by {dbinstanceidentifier,region,aws_account,env}
+      avg:aws.rds.cpuutilization${local.query_filter} by {dbinstanceidentifier,region,aws_account,env,datadog_managed}
     >= ${var.cpu_utilization_threshold_critical}
 END
 
@@ -77,8 +77,8 @@ resource "datadog_monitor" "cpu_utilization_anomaly" {
   count = var.cpu_utilization_anomaly_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "RDS CPU utilization anomalous activity - {{dbinstanceidentifier.name}}", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.cpu_utilization_anomaly_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -92,7 +92,7 @@ resource "datadog_monitor" "cpu_utilization_anomaly" {
 
   query = <<END
     avg(${var.cpu_utilization_anomaly_evaluation_window}):anomalies(
-      avg:aws.rds.cpuutilization${local.query_filter} by {dbinstanceidentifier,region,aws_account,env}, 'agile', ${var.cpu_utilization_anomaly_deviations},
+      avg:aws.rds.cpuutilization${local.query_filter} by {dbinstanceidentifier,region,aws_account,env,datadog_managed}, 'agile', ${var.cpu_utilization_anomaly_deviations},
       direction='below', count_default_zero='true', interval=${var.cpu_utilization_anomaly_rollup},
       seasonality='${var.cpu_utilization_anomaly_seasonality}'
     ) >= ${var.cpu_utilization_anomaly_threshold_critical}
@@ -113,8 +113,8 @@ resource "datadog_monitor" "used_storage" {
   count = var.used_storage_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "RDS instance storage - {{dbinstanceidentifier.name}} - {{value}}% used", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.used_storage_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -129,8 +129,8 @@ resource "datadog_monitor" "used_storage" {
   query = <<END
     max(${var.used_storage_evaluation_window}):(
       100 - ((
-        default(avg:aws.rds.free_storage_space${local.query_filter} by {dbinstanceidentifier,region,aws_account,env}, 0) /
-        default(avg:aws.rds.total_storage_space${local.query_filter} by {dbinstanceidentifier,region,aws_account,env}, 1)
+        default(avg:aws.rds.free_storage_space${local.query_filter} by {dbinstanceidentifier,region,aws_account,env,datadog_managed}, 0) /
+        default(avg:aws.rds.total_storage_space${local.query_filter} by {dbinstanceidentifier,region,aws_account,env,datadog_managed}, 1)
       ) * 100)
     ) >= ${var.used_storage_threshold_critical}
 END
diff --git a/aws/rds/variables.tf b/aws/rds/variables.tf
index 6e74aa4..64f2191 100644
--- a/aws/rds/variables.tf
+++ b/aws/rds/variables.tf
@@ -17,7 +17,7 @@ variable "base_tags" {
 # Connection Rate (anomaly detection)
 ########################################
 variable "connection_count_anomaly_enabled" {
-  default     = false
+  default     = true
   description = "Enable CPU utilization anomaly monitor"
   type        = bool
 }
@@ -65,7 +65,7 @@ variable "connection_count_anomaly_trigger_window" {
 }
 
 variable "connection_count_anomaly_threshold_critical" {
-  default     = null
+  default     = 0.75
   description = "Critical threshold (percent)"
   type        = number
 }
@@ -76,11 +76,17 @@ variable "connection_count_anomaly_threshold_warning" {
   type        = number
 }
 
+variable "connection_count_anomaly_use_message" {
+  description = "Whether to use the query alert base message for connection count anomaly monitor"
+  type        = bool
+  default     = true
+}
+
 ########################################
 # Node CPU Utilization
 ########################################
 variable "cpu_utilization_enabled" {
-  default     = false
+  default     = true
   description = "Enable CPU utilization monitor"
   type        = bool
 }
@@ -109,6 +115,12 @@ variable "cpu_utilization_threshold_warning" {
   type        = number
 }
 
+variable "cpu_utilization_use_message" {
+  description = "Whether to use the query alert base message for CPU utilization monitor"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # CPU Utilization (anomaly detection)
 ########################################
@@ -172,6 +184,12 @@ variable "cpu_utilization_anomaly_threshold_warning" {
   type        = number
 }
 
+variable "cpu_utilization_anomaly_use_message" {
+  description = "Whether to use the query alert base message for CPU utilization anomaly monitor"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # ElasticSearch cluster used storage
 ########################################
@@ -204,3 +222,9 @@ variable "used_storage_threshold_warning" {
   description = "Warning threshold (percentage, 0-100)"
   type        = number
 }
+
+variable "used_storage_use_message" {
+  description = "Whether to use the query alert base message for used storage monitor"
+  type        = bool
+  default     = true
+}
diff --git a/aws/sqs/.terraform.lock.hcl b/aws/sqs/.terraform.lock.hcl
index 5fa8913..f4429ee 100644
--- a/aws/sqs/.terraform.lock.hcl
+++ b/aws/sqs/.terraform.lock.hcl
@@ -5,6 +5,7 @@ provider "registry.terraform.io/datadog/datadog" {
   version     = "3.44.0"
   constraints = ">= 3.37.0"
   hashes = [
+    "h1:gapxzCRcnTGm4HLO1zuoelGC15+0LEYceGNWGh69JLE=",
     "h1:neJ/si/8CotiW8ulfjU6dFmb1bpzbTjhfHLTlCvdynw=",
     "zh:12119fe0cafbe7e05c32d4101a804d479ae756e19512c789c67cb3c51420ac98",
     "zh:35267ecc27de00e449893df9a37481f38b8fe24d14fe94198cd68966f1aa586f",
@@ -27,6 +28,7 @@ provider "registry.terraform.io/hashicorp/null" {
   version     = "3.2.2"
   constraints = ">= 3.1.0"
   hashes = [
+    "h1:IMVAUHKoydFrlPrl9OzasDnw/8ntZFerCC9iXw1rXQY=",
     "h1:vWAsYRd7MjYr3adj8BVKRohVfHpWQdvkIwUQ2Jf5FVM=",
     "zh:3248aae6a2198f3ec8394218d05bd5e42be59f43a3a7c0b71c66ec0df08b69e7",
     "zh:32b1aaa1c3013d33c245493f4a65465eab9436b454d250102729321a44c8ab9a",
diff --git a/aws/sqs/README.md b/aws/sqs/README.md
index 78b8d6e..2d27fa4 100644
--- a/aws/sqs/README.md
+++ b/aws/sqs/README.md
@@ -18,7 +18,7 @@ Configures the following for Lambda functions based on tag matches:
 
 | Name | Version |
 |------|---------|
-| <a name="provider_datadog"></a> [datadog](#provider\_datadog) | >= 3.37 |
+| <a name="provider_datadog"></a> [datadog](#provider\_datadog) | 3.44.0 |
 
 ## Modules
 
@@ -28,10 +28,8 @@ No modules.
 
 | Name | Type |
 |------|------|
-| [datadog_monitor.http_5xx_responses](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
-| [datadog_monitor.http_5xx_tg_responses](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
-| [datadog_monitor.latency](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
-| [datadog_monitor.no_healthy_instances](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
+| [datadog_monitor.oldest_message](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
+| [datadog_monitor.queue_depth](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
 
 ## Inputs
 
@@ -41,39 +39,35 @@ No modules.
 | <a name="input_alert_critical_priority"></a> [alert\_critical\_priority](#input\_alert\_critical\_priority) | Priority for alerts within critical threshold (P1-P5, uses monitor defaults if not specified) | `string` | `null` | no |
 | <a name="input_alert_message"></a> [alert\_message](#input\_alert\_message) | Message to prepend to alert notifications | `string` | `"Alert"` | no |
 | <a name="input_alert_nodata_priority"></a> [alert\_nodata\_priority](#input\_alert\_nodata\_priority) | Priority for alerts within warning threshold (P1-P5, uses monitor defaults if not specified) | `string` | `null` | no |
-| <a name="input_base_tags"></a> [base\_tags](#input\_base\_tags) | Base tags (key:value format) to add to this type of check (combined with `local.tags` and `var.additional_tags`, generally you should not change this) | `list(string)` | <pre>[<br>  "resource:alb"<br>]</pre> | no |
+| <a name="input_base_tags"></a> [base\_tags](#input\_base\_tags) | Base tags (key:value format) to add to this type of check (combined with `local.tags` and `var.additional_tags`, generally you should not change this) | `list(string)` | <pre>[<br>  "resource:queue"<br>]</pre> | no |
 | <a name="input_cost_center"></a> [cost\_center](#input\_cost\_center) | Cost Center of the monitored resource (leave blank to omit tag) | `string` | `null` | no |
 | <a name="input_dashboard_link"></a> [dashboard\_link](#input\_dashboard\_link) | Dashboard link to include in message | `string` | `null` | no |
-| <a name="input_env"></a> [env](#input\_env) | Environment the monitored resource is in (leave blank to omit tag) | `string` | n/a | yes |
+| <a name="input_env"></a> [env](#input\_env) | Environment the monitored resource is in (leave blank to omit tag) | `string` | `null` | no |
 | <a name="input_evaluation_delay"></a> [evaluation\_delay](#input\_evaluation\_delay) | Monitor evaluation delay (see [https://docs.datadoghq.com/monitors/configuration/?tab=thresholdalert#set-alert-conditions](Datadog Docs)) | `number` | `900` | no |
-| <a name="input_http_5xx_responses_enabled"></a> [http\_5xx\_responses\_enabled](#input\_http\_5xx\_responses\_enabled) | Enable HTTP 5xx response monitor | `bool` | `false` | no |
-| <a name="input_http_5xx_responses_evaluation_window"></a> [http\_5xx\_responses\_evaluation\_window](#input\_http\_5xx\_responses\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
-| <a name="input_http_5xx_responses_no_data_window"></a> [http\_5xx\_responses\_no\_data\_window](#input\_http\_5xx\_responses\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
-| <a name="input_http_5xx_responses_threshold_critical"></a> [http\_5xx\_responses\_threshold\_critical](#input\_http\_5xx\_responses\_threshold\_critical) | Critical threshold (percentage, 0-100) | `number` | `75` | no |
-| <a name="input_http_5xx_responses_threshold_warning"></a> [http\_5xx\_responses\_threshold\_warning](#input\_http\_5xx\_responses\_threshold\_warning) | Warning threshold (percentage, 0-100) | `number` | `25` | no |
-| <a name="input_http_5xx_tg_responses_enabled"></a> [http\_5xx\_tg\_responses\_enabled](#input\_http\_5xx\_tg\_responses\_enabled) | Enable HTTP 5xx response monitor (target group) | `bool` | `false` | no |
-| <a name="input_http_5xx_tg_responses_evaluation_window"></a> [http\_5xx\_tg\_responses\_evaluation\_window](#input\_http\_5xx\_tg\_responses\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
-| <a name="input_http_5xx_tg_responses_no_data_window"></a> [http\_5xx\_tg\_responses\_no\_data\_window](#input\_http\_5xx\_tg\_responses\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
-| <a name="input_http_5xx_tg_responses_threshold_critical"></a> [http\_5xx\_tg\_responses\_threshold\_critical](#input\_http\_5xx\_tg\_responses\_threshold\_critical) | Critical threshold (percentage, 0-100) | `number` | `75` | no |
-| <a name="input_http_5xx_tg_responses_threshold_warning"></a> [http\_5xx\_tg\_responses\_threshold\_warning](#input\_http\_5xx\_tg\_responses\_threshold\_warning) | Warning threshold (percentage, 0-100) | `number` | `25` | no |
-| <a name="input_latency_enabled"></a> [latency\_enabled](#input\_latency\_enabled) | Enable latency monitor | `bool` | `false` | no |
-| <a name="input_latency_evaluation_window"></a> [latency\_evaluation\_window](#input\_latency\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
-| <a name="input_latency_no_data_window"></a> [latency\_no\_data\_window](#input\_latency\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
-| <a name="input_latency_threshold_critical"></a> [latency\_threshold\_critical](#input\_latency\_threshold\_critical) | Critical threshold (seconds) | `number` | `null` | no |
-| <a name="input_latency_threshold_warning"></a> [latency\_threshold\_warning](#input\_latency\_threshold\_warning) | Warning threshold (seconds) | `number` | `null` | no |
 | <a name="input_monitor_exclude_tags"></a> [monitor\_exclude\_tags](#input\_monitor\_exclude\_tags) | Tags to be excluded in the monitoring query. Specify in key:value format | `list(string)` | `[]` | no |
 | <a name="input_monitor_include_tags"></a> [monitor\_include\_tags](#input\_monitor\_include\_tags) | Tags to be included in the monitoring query. Specify in key:value format | `list(string)` | `[]` | no |
 | <a name="input_new_group_delay"></a> [new\_group\_delay](#input\_new\_group\_delay) | Delay in seconds before generating alerts for a new resource | `number` | `300` | no |
-| <a name="input_no_healthy_instances_enabled"></a> [no\_healthy\_instances\_enabled](#input\_no\_healthy\_instances\_enabled) | Enable no healthy instances monitor | `bool` | `true` | no |
-| <a name="input_no_healthy_instances_evaluation_window"></a> [no\_healthy\_instances\_evaluation\_window](#input\_no\_healthy\_instances\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
-| <a name="input_no_healthy_instances_no_data_window"></a> [no\_healthy\_instances\_no\_data\_window](#input\_no\_healthy\_instances\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
-| <a name="input_no_healthy_instances_threshold_warning"></a> [no\_healthy\_instances\_threshold\_warning](#input\_no\_healthy\_instances\_threshold\_warning) | Warning threshold (percentage, 0 to disable) | `number` | `0` | no |
 | <a name="input_notify_alert_override"></a> [notify\_alert\_override](#input\_notify\_alert\_override) | List of notifications for alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_crit_override"></a> [notify\_crit\_override](#input\_notify\_crit\_override) | List of notifications for 24x7 alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_default"></a> [notify\_default](#input\_notify\_default) | List of alert notifications (can be overridden based on alert type) | `list(string)` | n/a | yes |
 | <a name="input_notify_no_data"></a> [notify\_no\_data](#input\_notify\_no\_data) | Alert if no matching data is found | `bool` | `false` | no |
 | <a name="input_notify_nodata_override"></a> [notify\_nodata\_override](#input\_notify\_nodata\_override) | List of notifications for no data (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_nonprod_override"></a> [notify\_nonprod\_override](#input\_notify\_nonprod\_override) | List of notifications for non-prod alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_prod_override"></a> [notify\_prod\_override](#input\_notify\_prod\_override) | List of notifications for 12x5 prod alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_recovery_override"></a> [notify\_recovery\_override](#input\_notify\_recovery\_override) | List of notifications for alert recovery (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_warn_override"></a> [notify\_warn\_override](#input\_notify\_warn\_override) | List of notifications for alerts in warning threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_oldest_message_enabled"></a> [oldest\_message\_enabled](#input\_oldest\_message\_enabled) | Enable oldest queued message monitor | `bool` | `false` | no |
+| <a name="input_oldest_message_evaluation_window"></a> [oldest\_message\_evaluation\_window](#input\_oldest\_message\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
+| <a name="input_oldest_message_no_data_window"></a> [oldest\_message\_no\_data\_window](#input\_oldest\_message\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
+| <a name="input_oldest_message_threshold_critical"></a> [oldest\_message\_threshold\_critical](#input\_oldest\_message\_threshold\_critical) | Critical threshold (seconds) | `number` | `75` | no |
+| <a name="input_oldest_message_threshold_warning"></a> [oldest\_message\_threshold\_warning](#input\_oldest\_message\_threshold\_warning) | Warning threshold (seconds) | `number` | `null` | no |
+| <a name="input_oldest_message_use_message"></a> [oldest\_message\_use\_message](#input\_oldest\_message\_use\_message) | Whether to use the query alert base message for oldest message monitor | `bool` | `false` | no |
+| <a name="input_queue_depth_enabled"></a> [queue\_depth\_enabled](#input\_queue\_depth\_enabled) | Enable queue depth count monitor | `bool` | `false` | no |
+| <a name="input_queue_depth_evaluation_window"></a> [queue\_depth\_evaluation\_window](#input\_queue\_depth\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
+| <a name="input_queue_depth_no_data_window"></a> [queue\_depth\_no\_data\_window](#input\_queue\_depth\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
+| <a name="input_queue_depth_threshold_critical"></a> [queue\_depth\_threshold\_critical](#input\_queue\_depth\_threshold\_critical) | Critical threshold (count) | `number` | `null` | no |
+| <a name="input_queue_depth_threshold_warning"></a> [queue\_depth\_threshold\_warning](#input\_queue\_depth\_threshold\_warning) | Warning threshold (count) | `number` | `null` | no |
+| <a name="input_queue_depth_use_message"></a> [queue\_depth\_use\_message](#input\_queue\_depth\_use\_message) | Whether to use the query alert base message for queue depth monitor | `bool` | `false` | no |
 | <a name="input_renotify_interval"></a> [renotify\_interval](#input\_renotify\_interval) | Interval in minutes to re-send notifications about an alert | `number` | `0` | no |
 | <a name="input_runbook_link"></a> [runbook\_link](#input\_runbook\_link) | Runbook link to include in message | `string` | `null` | no |
 | <a name="input_service"></a> [service](#input\_service) | Service associated with the monitored resource (leave blank to omit tag) | `string` | `null` | no |
diff --git a/aws/sqs/main.tf b/aws/sqs/main.tf
index edbfc91..6c98447 100644
--- a/aws/sqs/main.tf
+++ b/aws/sqs/main.tf
@@ -4,7 +4,7 @@ locals {
   monitor_warn_default_priority   = null
   monitor_nodata_default_priority = null
 
-  title_prefix = "${var.title_prefix == null ? "" : "[${var.title_prefix}]"}"
+  title_prefix = var.title_prefix == null ? "" : "[${var.title_prefix}]"
   title_suffix = var.title_suffix == null ? "" : " (${var.title_suffix})"
 }
 
@@ -12,8 +12,8 @@ resource "datadog_monitor" "oldest_message" {
   count = var.oldest_message_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "Oldest queued message - {{queuename.name}}", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.oldest_message_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -27,7 +27,7 @@ resource "datadog_monitor" "oldest_message" {
 
   query = <<END
     min(${var.oldest_message_evaluation_window}):(
-      avg:aws.sqs.approximate_age_of_oldest_message${local.query_filter} by {queuename,region}
+      avg:aws.sqs.approximate_age_of_oldest_message${local.query_filter} by {queuename,region,env,datadog_managed}
     ) > ${var.oldest_message_threshold_critical}
 END
 
@@ -41,8 +41,8 @@ resource "datadog_monitor" "queue_depth" {
   count = var.queue_depth_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "Queue depth - {{queuename.name}}", local.title_suffix])
-  include_tags = true
-  message      = local.query_alert_base_message
+  include_tags = false
+  message      = var.queue_depth_use_message ? local.query_alert_base_message : ""
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
 
@@ -56,7 +56,7 @@ resource "datadog_monitor" "queue_depth" {
 
   query = <<END
     min(${var.queue_depth_evaluation_window}):(
-      avg:aws.sqs.approximate_number_of_messages_visible${local.query_filter} by {queuename,region}
+      avg:aws.sqs.approximate_number_of_messages_visible${local.query_filter} by {queuename,region,env,datadog_managed}
     ) > ${var.queue_depth_threshold_critical}
 END
 
diff --git a/aws/sqs/variables.tf b/aws/sqs/variables.tf
index 0a4b1c5..4bb5de0 100644
--- a/aws/sqs/variables.tf
+++ b/aws/sqs/variables.tf
@@ -46,6 +46,12 @@ variable "oldest_message_threshold_warning" {
   type        = number
 }
 
+variable "oldest_message_use_message" {
+  description = "Whether to use the query alert base message for oldest message monitor"
+  type        = bool
+  default     = false
+}
+
 ########################################
 # Lambda queue_depth
 ########################################
@@ -78,3 +84,9 @@ variable "queue_depth_threshold_warning" {
   description = "Warning threshold (count)"
   type        = number
 }
+
+variable "queue_depth_use_message" {
+  description = "Whether to use the query alert base message for queue depth monitor"
+  type        = bool
+  default     = false
+}
diff --git a/aws/vpn/.terraform.lock.hcl b/aws/vpn/.terraform.lock.hcl
index 5fa8913..f4429ee 100644
--- a/aws/vpn/.terraform.lock.hcl
+++ b/aws/vpn/.terraform.lock.hcl
@@ -5,6 +5,7 @@ provider "registry.terraform.io/datadog/datadog" {
   version     = "3.44.0"
   constraints = ">= 3.37.0"
   hashes = [
+    "h1:gapxzCRcnTGm4HLO1zuoelGC15+0LEYceGNWGh69JLE=",
     "h1:neJ/si/8CotiW8ulfjU6dFmb1bpzbTjhfHLTlCvdynw=",
     "zh:12119fe0cafbe7e05c32d4101a804d479ae756e19512c789c67cb3c51420ac98",
     "zh:35267ecc27de00e449893df9a37481f38b8fe24d14fe94198cd68966f1aa586f",
@@ -27,6 +28,7 @@ provider "registry.terraform.io/hashicorp/null" {
   version     = "3.2.2"
   constraints = ">= 3.1.0"
   hashes = [
+    "h1:IMVAUHKoydFrlPrl9OzasDnw/8ntZFerCC9iXw1rXQY=",
     "h1:vWAsYRd7MjYr3adj8BVKRohVfHpWQdvkIwUQ2Jf5FVM=",
     "zh:3248aae6a2198f3ec8394218d05bd5e42be59f43a3a7c0b71c66ec0df08b69e7",
     "zh:32b1aaa1c3013d33c245493f4a65465eab9436b454d250102729321a44c8ab9a",
diff --git a/aws/vpn/README.md b/aws/vpn/README.md
index 06a3bb5..662a44a 100644
--- a/aws/vpn/README.md
+++ b/aws/vpn/README.md
@@ -15,7 +15,7 @@ Configures up/down monitoring for VPN tunnels
 
 | Name | Version |
 |------|---------|
-| <a name="provider_datadog"></a> [datadog](#provider\_datadog) | >= 3.37 |
+| <a name="provider_datadog"></a> [datadog](#provider\_datadog) | 3.44.0 |
 
 ## Modules
 
@@ -25,10 +25,7 @@ No modules.
 
 | Name | Type |
 |------|------|
-| [datadog_monitor.http_5xx_responses](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
-| [datadog_monitor.http_5xx_tg_responses](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
-| [datadog_monitor.latency](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
-| [datadog_monitor.no_healthy_instances](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
+| [datadog_monitor.tunnel_state](https://registry.terraform.io/providers/datadog/datadog/latest/docs/resources/monitor) | resource |
 
 ## Inputs
 
@@ -38,37 +35,21 @@ No modules.
 | <a name="input_alert_critical_priority"></a> [alert\_critical\_priority](#input\_alert\_critical\_priority) | Priority for alerts within critical threshold (P1-P5, uses monitor defaults if not specified) | `string` | `null` | no |
 | <a name="input_alert_message"></a> [alert\_message](#input\_alert\_message) | Message to prepend to alert notifications | `string` | `"Alert"` | no |
 | <a name="input_alert_nodata_priority"></a> [alert\_nodata\_priority](#input\_alert\_nodata\_priority) | Priority for alerts within warning threshold (P1-P5, uses monitor defaults if not specified) | `string` | `null` | no |
-| <a name="input_base_tags"></a> [base\_tags](#input\_base\_tags) | Base tags (key:value format) to add to this type of check (combined with `local.tags` and `var.additional_tags`, generally you should not change this) | `list(string)` | <pre>[<br>  "resource:alb"<br>]</pre> | no |
+| <a name="input_base_tags"></a> [base\_tags](#input\_base\_tags) | Base tags (key:value format) to add to this type of check (combined with `local.tags` and `var.additional_tags`, generally you should not change this) | `list(string)` | <pre>[<br>  "resource:vpn"<br>]</pre> | no |
 | <a name="input_cost_center"></a> [cost\_center](#input\_cost\_center) | Cost Center of the monitored resource (leave blank to omit tag) | `string` | `null` | no |
 | <a name="input_dashboard_link"></a> [dashboard\_link](#input\_dashboard\_link) | Dashboard link to include in message | `string` | `null` | no |
-| <a name="input_env"></a> [env](#input\_env) | Environment the monitored resource is in (leave blank to omit tag) | `string` | n/a | yes |
+| <a name="input_env"></a> [env](#input\_env) | Environment the monitored resource is in (leave blank to omit tag) | `string` | `null` | no |
 | <a name="input_evaluation_delay"></a> [evaluation\_delay](#input\_evaluation\_delay) | Monitor evaluation delay (see [https://docs.datadoghq.com/monitors/configuration/?tab=thresholdalert#set-alert-conditions](Datadog Docs)) | `number` | `900` | no |
-| <a name="input_http_5xx_responses_enabled"></a> [http\_5xx\_responses\_enabled](#input\_http\_5xx\_responses\_enabled) | Enable HTTP 5xx response monitor | `bool` | `false` | no |
-| <a name="input_http_5xx_responses_evaluation_window"></a> [http\_5xx\_responses\_evaluation\_window](#input\_http\_5xx\_responses\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
-| <a name="input_http_5xx_responses_no_data_window"></a> [http\_5xx\_responses\_no\_data\_window](#input\_http\_5xx\_responses\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
-| <a name="input_http_5xx_responses_threshold_critical"></a> [http\_5xx\_responses\_threshold\_critical](#input\_http\_5xx\_responses\_threshold\_critical) | Critical threshold (percentage, 0-100) | `number` | `75` | no |
-| <a name="input_http_5xx_responses_threshold_warning"></a> [http\_5xx\_responses\_threshold\_warning](#input\_http\_5xx\_responses\_threshold\_warning) | Warning threshold (percentage, 0-100) | `number` | `25` | no |
-| <a name="input_http_5xx_tg_responses_enabled"></a> [http\_5xx\_tg\_responses\_enabled](#input\_http\_5xx\_tg\_responses\_enabled) | Enable HTTP 5xx response monitor (target group) | `bool` | `false` | no |
-| <a name="input_http_5xx_tg_responses_evaluation_window"></a> [http\_5xx\_tg\_responses\_evaluation\_window](#input\_http\_5xx\_tg\_responses\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
-| <a name="input_http_5xx_tg_responses_no_data_window"></a> [http\_5xx\_tg\_responses\_no\_data\_window](#input\_http\_5xx\_tg\_responses\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
-| <a name="input_http_5xx_tg_responses_threshold_critical"></a> [http\_5xx\_tg\_responses\_threshold\_critical](#input\_http\_5xx\_tg\_responses\_threshold\_critical) | Critical threshold (percentage, 0-100) | `number` | `75` | no |
-| <a name="input_http_5xx_tg_responses_threshold_warning"></a> [http\_5xx\_tg\_responses\_threshold\_warning](#input\_http\_5xx\_tg\_responses\_threshold\_warning) | Warning threshold (percentage, 0-100) | `number` | `25` | no |
-| <a name="input_latency_enabled"></a> [latency\_enabled](#input\_latency\_enabled) | Enable latency monitor | `bool` | `false` | no |
-| <a name="input_latency_evaluation_window"></a> [latency\_evaluation\_window](#input\_latency\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
-| <a name="input_latency_no_data_window"></a> [latency\_no\_data\_window](#input\_latency\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
-| <a name="input_latency_threshold_critical"></a> [latency\_threshold\_critical](#input\_latency\_threshold\_critical) | Critical threshold (seconds) | `number` | `null` | no |
-| <a name="input_latency_threshold_warning"></a> [latency\_threshold\_warning](#input\_latency\_threshold\_warning) | Warning threshold (seconds) | `number` | `null` | no |
 | <a name="input_monitor_exclude_tags"></a> [monitor\_exclude\_tags](#input\_monitor\_exclude\_tags) | Tags to be excluded in the monitoring query. Specify in key:value format | `list(string)` | `[]` | no |
 | <a name="input_monitor_include_tags"></a> [monitor\_include\_tags](#input\_monitor\_include\_tags) | Tags to be included in the monitoring query. Specify in key:value format | `list(string)` | `[]` | no |
 | <a name="input_new_group_delay"></a> [new\_group\_delay](#input\_new\_group\_delay) | Delay in seconds before generating alerts for a new resource | `number` | `300` | no |
-| <a name="input_no_healthy_instances_enabled"></a> [no\_healthy\_instances\_enabled](#input\_no\_healthy\_instances\_enabled) | Enable no healthy instances monitor | `bool` | `true` | no |
-| <a name="input_no_healthy_instances_evaluation_window"></a> [no\_healthy\_instances\_evaluation\_window](#input\_no\_healthy\_instances\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
-| <a name="input_no_healthy_instances_no_data_window"></a> [no\_healthy\_instances\_no\_data\_window](#input\_no\_healthy\_instances\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
-| <a name="input_no_healthy_instances_threshold_warning"></a> [no\_healthy\_instances\_threshold\_warning](#input\_no\_healthy\_instances\_threshold\_warning) | Warning threshold (percentage, 0 to disable) | `number` | `0` | no |
 | <a name="input_notify_alert_override"></a> [notify\_alert\_override](#input\_notify\_alert\_override) | List of notifications for alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_crit_override"></a> [notify\_crit\_override](#input\_notify\_crit\_override) | List of notifications for 24x7 alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_default"></a> [notify\_default](#input\_notify\_default) | List of alert notifications (can be overridden based on alert type) | `list(string)` | n/a | yes |
 | <a name="input_notify_no_data"></a> [notify\_no\_data](#input\_notify\_no\_data) | Alert if no matching data is found | `bool` | `false` | no |
 | <a name="input_notify_nodata_override"></a> [notify\_nodata\_override](#input\_notify\_nodata\_override) | List of notifications for no data (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_nonprod_override"></a> [notify\_nonprod\_override](#input\_notify\_nonprod\_override) | List of notifications for non-prod alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
+| <a name="input_notify_prod_override"></a> [notify\_prod\_override](#input\_notify\_prod\_override) | List of notifications for 12x5 prod alerts in critical threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_recovery_override"></a> [notify\_recovery\_override](#input\_notify\_recovery\_override) | List of notifications for alert recovery (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_notify_warn_override"></a> [notify\_warn\_override](#input\_notify\_warn\_override) | List of notifications for alerts in warning threshold (uses `notify_default` otherwise) | `list(string)` | `[]` | no |
 | <a name="input_renotify_interval"></a> [renotify\_interval](#input\_renotify\_interval) | Interval in minutes to re-send notifications about an alert | `number` | `0` | no |
@@ -78,6 +59,9 @@ No modules.
 | <a name="input_timeout_h"></a> [timeout\_h](#input\_timeout\_h) | Auto-resolve alert in specified hours if condition no longer matches | `number` | `0` | no |
 | <a name="input_title_prefix"></a> [title\_prefix](#input\_title\_prefix) | Prefix all alerts with specified value in brackets | `string` | `null` | no |
 | <a name="input_title_suffix"></a> [title\_suffix](#input\_title\_suffix) | Suffix all alerts with specified value in parenthesis | `string` | `null` | no |
+| <a name="input_tunnel_state_enabled"></a> [tunnel\_state\_enabled](#input\_tunnel\_state\_enabled) | Enable VPN tunnel state monitor | `bool` | `false` | no |
+| <a name="input_tunnel_state_evaluation_window"></a> [tunnel\_state\_evaluation\_window](#input\_tunnel\_state\_evaluation\_window) | Evaluation window for monitor (`last_?m` (1, 5, 10, 15, or 30), `last_?h` (1, 2, or 4), or `last_1d`] | `string` | `"last_5m"` | no |
+| <a name="input_tunnel_state_no_data_window"></a> [tunnel\_state\_no\_data\_window](#input\_tunnel\_state\_no\_data\_window) | No data threshold (in minutes, 0 to disable) | `number` | `10` | no |
 | <a name="input_warn_priority"></a> [warn\_priority](#input\_warn\_priority) | Priority for alerts with no data (P1-P5, uses monitor defaults if not specified) | `string` | `null` | no |
 
 ## Outputs
diff --git a/aws/vpn/main.tf b/aws/vpn/main.tf
index 304e91b..bd4df6a 100644
--- a/aws/vpn/main.tf
+++ b/aws/vpn/main.tf
@@ -12,7 +12,7 @@ resource "datadog_monitor" "tunnel_state" {
   count = var.tunnel_state_enabled ? 1 : 0
 
   name         = join("", [local.title_prefix, "VPN tunnel state - {{host.name}}", local.title_suffix])
-  include_tags = true
+  include_tags = false
   message      = local.query_alert_base_message
   tags         = concat(local.common_tags, var.base_tags, var.additional_tags)
   type         = "query alert"
@@ -27,7 +27,7 @@ resource "datadog_monitor" "tunnel_state" {
 
   query = <<END
     min(${var.tunnel_state_evaluation_window}):(
-      min:aws.vpn.tunnel_state${local.query_filter} by {tunnelipaddress,region}
+      min:aws.vpn.tunnel_state${local.query_filter} by {tunnelipaddress,region,env,datadog_managed}
     ) <= 0
 END
 
diff --git a/common/common.tf b/common/common.tf
index 14461a1..878a37c 100644
--- a/common/common.tf
+++ b/common/common.tf
@@ -10,6 +10,7 @@ variable "cost_center" {
 }
 
 variable "env" {
+  default     = null
   description = "Environment the monitored resource is in (leave blank to omit tag)"
   type        = string
 }
@@ -160,6 +161,24 @@ variable "notify_recovery_override" {
   type        = list(string)
 }
 
+variable "notify_crit_override" {
+  default     = []
+  description = "List of notifications for 24x7 alerts in critical threshold (uses `notify_default` otherwise)"
+  type        = list(string)
+}
+
+variable "notify_nonprod_override" {
+  default     = []
+  description = "List of notifications for non-prod alerts in critical threshold (uses `notify_default` otherwise)"
+  type        = list(string)
+}
+
+variable "notify_prod_override" {
+  default     = []
+  description = "List of notifications for 12x5 prod alerts in critical threshold (uses `notify_default` otherwise)"
+  type        = list(string)
+}
+
 locals {
 
   # tag related locals
@@ -213,14 +232,17 @@ locals {
     var.runbook_link != null ? ["**Runbook**: ${var.runbook_link}"] : []
   ))
 
-  alert_priority  = coalesce(var.alert_critical_priority, local.monitor_alert_default_priority, "P2")
-  warn_priority   = coalesce(var.alert_critical_priority, local.monitor_warn_default_priority, "P2")
-  nodata_priority = coalesce(var.alert_critical_priority, local.monitor_nodata_default_priority, "P2")
+  alert_priority  = coalesce(var.alert_critical_priority, "P2")
+  warn_priority   = coalesce(var.warn_priority, "P2")
+  nodata_priority = coalesce(var.alert_nodata_priority, "P2")
 
   notify_on_alert    = join(" ", coalescelist(var.notify_alert_override, var.notify_default))
   notify_on_warn     = join(" ", coalescelist(var.notify_warn_override, var.notify_default))
   notify_on_nodata   = join(" ", coalescelist(var.notify_nodata_override, var.notify_default))
   notify_on_recovery = join(" ", coalescelist(var.notify_recovery_override, var.notify_default))
+  notify_on_crit     = join(" ", coalescelist(var.notify_crit_override, var.notify_default))
+  notify_on_nonprod  = join(" ", coalescelist(var.notify_nonprod_override, var.notify_default))
+  notify_on_prod     = join(" ", coalescelist(var.notify_prod_override, var.notify_default))
 
   log_alert_base_message = <<END
 ${local.alert_context}
@@ -232,29 +254,80 @@ ${local.alert_context}
 * **Message**: {{log.message}}
 * **Direct Link**: {{log.link}}
 {{#is_alert}}
-{{override_priority '${local.alert_priority}'}}
-${local.notify_on_alert}
+{{#is_match "env.name" "prod"}}
+  {{#is_match "datadog_managed" "critical"}}
+    ${local.notify_on_crit}
+  {{/is_match}}
+  {{#is_match "datadog_managed" "true"}}
+    ${local.notify_on_prod}
+  {{/is_match}}
+{{/is_match}}
+{{^is_match "env.name" "prod"}}
+    ${local.notify_on_nonprod}
+  {{/is_match}}
+{{/is_match}}
 {{/is_alert}}
-{{#is_warning}}
-{{override_priority '${local.warn_priority}'}}
-${local.notify_on_warn}
-{{/is_warning}}
-{{#is_no_data}}
-{{override_priority '${local.nodata_priority}'}}
-${local.notify_on_nodata}
-{{/is_no_data}}
 {{#is_recovery}}
-${local.notify_on_recovery}
+{{#is_match "env.name" "prod"}}
+  {{#is_match "datadog_managed" "critical"}}
+    ${local.notify_on_crit}
+  {{/is_match}}
+  {{#is_match "datadog_managed" "true"}}
+    ${local.notify_on_prod}
+  {{/is_match}}
+{{/is_match}}
+{{^is_match "env.name" "prod"}}
+    ${local.notify_on_nonprod}
+  {{/is_match}}
+{{/is_match}}
 {{/is_recovery}}
 END
 
   query_alert_base_message = <<END
 ${local.alert_context}
-**Alert Information**
-{{#is_alert}} ${local.notify_on_alert} {{/is_alert}}
-{{#is_warning}} ${local.notify_on_warn} {{/is_warning}}
-{{#is_no_data}} ${local.notify_on_nodata} {{/is_no_data}}
-{{#is_recovery}} ${local.notify_on_recovery} {{/is_recovery}}
+{{#is_alert}}
+Current value: {{value}}
+Threshold: {{threshold}}
+
+Environment: {{env.name}}
+
+  {{#is_match "env.name" "prod"}}
+    {{#is_match "datadog_managed" "critical"}}
+      ${local.notify_on_crit}
+    {{/is_match}}
+    {{#is_match "datadog_managed" "true"}}
+      ${local.notify_on_prod}
+    {{/is_match}}
+  {{/is_match}}
+  {{^is_match "env.name" "prod"}}
+      ${local.notify_on_nonprod}
+  {{/is_match}}
+
+Please investigate and take necessary actions.
+{{/is_alert}}
+
+{{#is_recovery}}
+Recovery: Monitor has returned to a normal state.
+
+Current value: {{value}}
+Threshold: {{threshold}}
+
+Environment: {{env.name}}
+
+No further action is required.
+
+  {{#is_match "env.name" "prod"}}
+    {{#is_match "datadog_managed" "critical"}}
+      ${local.notify_on_crit}
+    {{/is_match}}
+    {{#is_match "datadog_managed" "true"}}
+      ${local.notify_on_prod}
+    {{/is_match}}
+  {{/is_match}}
+  {{^is_match "env.name" "prod"}}
+      ${local.notify_on_nonprod}
+  {{/is_match}}
+{{/is_recovery}}
 END
 
   synthetic_alert_base_message = <<END