Skip to content

Commit c66f603

Browse files
authored
Merge pull request #17 from MicrosoftCloudEssentials-LearningHub/ai-initial-questions
initial questions for an AI use case
2 parents 3764ec0 + 8739b1c commit c66f603

14 files changed

+76
-40
lines changed

0_RAG_Overview.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,7 @@ Costa Rica
66
[![GitHub](https://img.shields.io/badge/--181717?logo=github&logoColor=ffffff)](https://github.com/)
77
[brown9804](https://github.com/brown9804)
88

9-
Last updated: 2025-08-18
9+
Last updated: 2025-11-03
1010

1111
----------
1212

@@ -147,7 +147,7 @@ graph LR
147147

148148
<!-- START BADGE -->
149149
<div align="center">
150-
<img src="https://img.shields.io/badge/Total%20views-1320-limegreen" alt="Total views">
151-
<p>Refresh Date: 2025-10-03</p>
150+
<img src="https://img.shields.io/badge/Total%20views-1413-limegreen" alt="Total views">
151+
<p>Refresh Date: 2025-11-03</p>
152152
</div>
153153
<!-- END BADGE -->

1_PrivateArchitecture.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,7 @@ Costa Rica
66
[![GitHub](https://img.shields.io/badge/--181717?logo=github&logoColor=ffffff)](https://github.com/)
77
[brown9804](https://github.com/brown9804)
88

9-
Last updated: 2025-08-18
9+
Last updated: 2025-11-03
1010

1111
----------
1212

@@ -289,7 +289,7 @@ graph TD
289289

290290
<!-- START BADGE -->
291291
<div align="center">
292-
<img src="https://img.shields.io/badge/Total%20views-1320-limegreen" alt="Total views">
293-
<p>Refresh Date: 2025-10-03</p>
292+
<img src="https://img.shields.io/badge/Total%20views-1413-limegreen" alt="Total views">
293+
<p>Refresh Date: 2025-11-03</p>
294294
</div>
295295
<!-- END BADGE -->

2_ZeroTrustOverview.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,7 @@ Costa Rica
66
[![GitHub](https://img.shields.io/badge/--181717?logo=github&logoColor=ffffff)](https://github.com/)
77
[brown9804](https://github.com/brown9804)
88

9-
Last updated: 2025-08-18
9+
Last updated: 2025-11-03
1010

1111
----------
1212

@@ -82,7 +82,7 @@ From [Zero Trust Architecture Deployment](https://github.com/Azure/GPT-RAG?tab=r
8282

8383
<!-- START BADGE -->
8484
<div align="center">
85-
<img src="https://img.shields.io/badge/Total%20views-1320-limegreen" alt="Total views">
86-
<p>Refresh Date: 2025-10-03</p>
85+
<img src="https://img.shields.io/badge/Total%20views-1413-limegreen" alt="Total views">
86+
<p>Refresh Date: 2025-11-03</p>
8787
</div>
8888
<!-- END BADGE -->

3_PricingDemos/0_Doc-Intellig.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,7 @@ Costa Rica
66
[![GitHub](https://img.shields.io/badge/--181717?logo=github&logoColor=ffffff)](https://github.com/)
77
[brown9804](https://github.com/brown9804)
88

9-
Last updated: 2025-08-18
9+
Last updated: 2025-11-03
1010

1111
----------
1212

@@ -57,7 +57,7 @@ Last updated: 2025-08-18
5757

5858
<!-- START BADGE -->
5959
<div align="center">
60-
<img src="https://img.shields.io/badge/Total%20views-1320-limegreen" alt="Total views">
61-
<p>Refresh Date: 2025-10-03</p>
60+
<img src="https://img.shields.io/badge/Total%20views-1413-limegreen" alt="Total views">
61+
<p>Refresh Date: 2025-11-03</p>
6262
</div>
6363
<!-- END BADGE -->

3_PricingDemos/1_AI-Search.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,7 @@ Costa Rica
66
[![GitHub](https://img.shields.io/badge/--181717?logo=github&logoColor=ffffff)](https://github.com/)
77
[brown9804](https://github.com/brown9804)
88

9-
Last updated: 2025-08-18
9+
Last updated: 2025-11-03
1010

1111
----------
1212

@@ -66,7 +66,7 @@ Last updated: 2025-08-18
6666

6767
<!-- START BADGE -->
6868
<div align="center">
69-
<img src="https://img.shields.io/badge/Total%20views-1320-limegreen" alt="Total views">
70-
<p>Refresh Date: 2025-10-03</p>
69+
<img src="https://img.shields.io/badge/Total%20views-1413-limegreen" alt="Total views">
70+
<p>Refresh Date: 2025-11-03</p>
7171
</div>
7272
<!-- END BADGE -->

3_PricingDemos/2_AOAI-AIFoundry.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,7 @@ Costa Rica
66
[![GitHub](https://img.shields.io/badge/--181717?logo=github&logoColor=ffffff)](https://github.com/)
77
[brown9804](https://github.com/brown9804)
88

9-
Last updated: 2025-08-18
9+
Last updated: 2025-11-03
1010

1111
----------
1212

@@ -171,7 +171,7 @@ This means with 50 PTUs, you can process 75,000 tokens per minute.
171171

172172
<!-- START BADGE -->
173173
<div align="center">
174-
<img src="https://img.shields.io/badge/Total%20views-1320-limegreen" alt="Total views">
175-
<p>Refresh Date: 2025-10-03</p>
174+
<img src="https://img.shields.io/badge/Total%20views-1413-limegreen" alt="Total views">
175+
<p>Refresh Date: 2025-11-03</p>
176176
</div>
177177
<!-- END BADGE -->

3_PricingDemos/README.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,7 @@ Costa Rica
66
[![GitHub](https://img.shields.io/badge/--181717?logo=github&logoColor=ffffff)](https://github.com/)
77
[brown9804](https://github.com/brown9804)
88

9-
Last updated: 2025-08-18
9+
Last updated: 2025-11-03
1010

1111
----------
1212

@@ -138,7 +138,7 @@ graph TD
138138
139139
<!-- START BADGE -->
140140
<div align="center">
141-
<img src="https://img.shields.io/badge/Total%20views-1320-limegreen" alt="Total views">
142-
<p>Refresh Date: 2025-10-03</p>
141+
<img src="https://img.shields.io/badge/Total%20views-1413-limegreen" alt="Total views">
142+
<p>Refresh Date: 2025-11-03</p>
143143
</div>
144144
<!-- END BADGE -->

4_Which_Copilot_toChoose.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -8,7 +8,7 @@ Costa Rica
88
[![GitHub](https://img.shields.io/badge/--181717?logo=github&logoColor=ffffff)](https://github.com/)
99
[brown9804](https://github.com/brown9804)
1010

11-
Last updated: 2025-08-18
11+
Last updated: 2025-11-03
1212

1313
----------
1414

@@ -159,7 +159,7 @@ From [Cloud computing - Service Models: SAAS, PAAS, IAAS - Which Is Better For B
159159
160160
<!-- START BADGE -->
161161
<div align="center">
162-
<img src="https://img.shields.io/badge/Total%20views-1320-limegreen" alt="Total views">
163-
<p>Refresh Date: 2025-10-03</p>
162+
<img src="https://img.shields.io/badge/Total%20views-1413-limegreen" alt="Total views">
163+
<p>Refresh Date: 2025-11-03</p>
164164
</div>
165165
<!-- END BADGE -->

5_AI_Initial_Questions.md

Lines changed: 36 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,36 @@
1+
# Initial AI Questions - Overview
2+
3+
Costa Rica
4+
5+
[![GitHub](https://badgen.net/badge/icon/github?icon=github&label)](https://github.com)
6+
[![GitHub](https://img.shields.io/badge/--181717?logo=github&logoColor=ffffff)](https://github.com/)
7+
[brown9804](https://github.com/brown9804)
8+
9+
Last updated: 2025-11-03
10+
11+
----------
12+
13+
| **Category** | **Question to Ask** | **Example Response** | **Purpose** |
14+
|--------------------------|-------------------------------------------------------|------------------------------------------------------|-----------------------------------------------------------------------------------------------|
15+
| **Business Objective** | What problem are you trying to solve with AI? | `We want to reduce manual ticket triage time.` | Understand the core use case and business value.|
16+
| **AI Use Case Type** | Is this a predictive, generative, or classification use case? | `We want to predict equipment failure before it happens.` | Helps determine the AI model type and architecture.|
17+
| **Data Availability** | What kind of data do you have access to? | `We have historical logs, sensor data, and incident reports.` | Assesses data readiness and integration needs.|
18+
| **Data Location** | Where is your data stored (cloud, on-prem, hybrid)? | `Most of our data is in Azure Data Lake.` | Determines data pipeline and access strategy.|
19+
| **Real-Time vs Batch** | Do you need real-time insights or is batch processing sufficient? | `Real-time alerts are critical for us.` | Influences infrastructure and model deployment strategy.|
20+
| **Integration Points** | What systems will this AI solution need to integrate with? | `ServiceNow, Jira, and our internal monitoring tools.` | Identifies APIs, connectors, and integration complexity.|
21+
| **User Interaction** | Will end users interact with the AI directly (e.g., chatbot) or indirectly? | `It will be embedded in our internal dashboard.` | Helps define UI/UX and delivery method.|
22+
| **Security & Compliance**| Are there any compliance or data privacy requirements (e.g., HIPAA, GDPR)? | `Yes, we must comply with SOC 2 and GDPR.` | Determines constraints on data handling and model training.|
23+
| **Preferred Cloud** | Do you have a preferred cloud provider or existing cloud contracts? | `We’re primarily an Azure shop.` | Guides service selection (e.g., Azure ML, AWS SageMaker, GCP Vertex AI).|
24+
| **AI Maturity** | Have you used AI/ML in production before? | `We’ve done some POCs but nothing in production.` | Assesses readiness and need for foundational support.|
25+
| **Model Ownership** | Do you plan to build your own models or use prebuilt ones (e.g., OpenAI, Azure AI)? | `We’d prefer to fine-tune a prebuilt model.` | Helps scope the project and choose between custom vs. managed services.|
26+
| **Monitoring Needs** | How will you monitor and evaluate model performance? | `We’ll need dashboards and alerts for drift and accuracy.` | Ensures observability and governance are planned.|
27+
| **Scalability** | How many users or transactions do you expect the AI to handle? | `We expect 10,000+ daily interactions.` | Determines infrastructure sizing and cost implications.|
28+
| **Budget & Timeline** | What’s your budget and timeline for this initiative? | `We have a 3-month window and a $50K budget.` | Helps prioritize scope and feasibility.|
29+
| **Success Metrics** | How will you measure the success of this AI solution? | `Reduction in ticket resolution time by 30%.` | Aligns technical goals with business KPIs.|
30+
31+
<!-- START BADGE -->
32+
<div align="center">
33+
<img src="https://img.shields.io/badge/Total%20views-1413-limegreen" alt="Total views">
34+
<p>Refresh Date: 2025-11-03</p>
35+
</div>
36+
<!-- END BADGE -->

README.md

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -7,7 +7,7 @@ Costa Rica
77
[![GitHub](https://img.shields.io/badge/--181717?logo=github&logoColor=ffffff)](https://github.com/)
88
[brown9804](https://github.com/brown9804)
99

10-
Last updated: 2025-10-03
10+
Last updated: 2025-11-03
1111

1212
----------
1313

@@ -468,13 +468,13 @@ gpt-rag-resource-group: resource not found: 0 resource groups with prefix or suf
468468
> If `main.parameters.json` contains `"location": "westus2"`, make sure your environment has `AZURE_LOCATION=westus2`.
469469
470470
> [!NOTE]
471-
> A `golden dataset` for RAG is your trusted, `curated set of documents or files that the system retrieves from when answering questions`. It’s a clean, accurate, and `representative subset of all possible data free of noise and errors`, so the model always pulls reliable context. Is a `subset of files, for example, and known Q&A pairs chosen from the larger data source.` These are the “benchmark” `questions where the correct answers are already known`, so they can be `used later to measure system accuracy and performance`. Other `expert users are free to ask additional questions during testing, but those will still pull context from the same curated files in the golden dataset (subset datasource) `. In short, it’s the trusted evaluation set for your proof of concept for example.
471+
> A `golden dataset` for RAG is your trusted, `curated set of documents or files that the system retrieves from when answering questions`. It’s a clean, accurate, and `representative subset of all possible data free of noise and errors`, so the model always pulls reliable context. Is a `subset of files, for example, and known Q&A pairs chosen from the larger data source.` These are the “benchmark” `questions where the correct answers are already known`, so they can be `used later to measure system accuracy and performance`. Other `expert users are free to ask additional questions during testing, but those will still pull context from the same curated files in the golden dataset (subset datasource)`. In short, it’s the trusted evaluation set for your proof of concept for example.
472472
473473
<img width="411" height="243" alt="Untitled Diagram drawio" src="https://github.com/user-attachments/assets/40682ec2-77e4-4413-88e5-d343f036f084" />
474474
475475
<!-- START BADGE -->
476476
<div align="center">
477-
<img src="https://img.shields.io/badge/Total%20views-1320-limegreen" alt="Total views">
478-
<p>Refresh Date: 2025-10-03</p>
477+
<img src="https://img.shields.io/badge/Total%20views-1413-limegreen" alt="Total views">
478+
<p>Refresh Date: 2025-11-03</p>
479479
</div>
480480
<!-- END BADGE -->

0 commit comments

Comments
 (0)