Skip to content

Commit fd236b7

Browse files
committed
Fixing PR Review issues.
1 parent 62ecb45 commit fd236b7

20 files changed

Lines changed: 915 additions & 925 deletions

learn-pr/wwl/design-ai-agents-business-solutions/includes/1-introduction.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
1-
Artificial Intelligence (AI) continues to transform business operations, enabling organizations to deliver enhanced customer experiences, streamline workflows, and drive innovation. Within the Microsoft ecosystem, Dynamics 365 and Copilot offer robust platforms for integrating AI-powered agents and solutions across sales, service, and contact center environments.
1+
Artificial Intelligence (AI) continues to transform business operations, enabling organizations to deliver enhanced customer experiences, streamline workflows, and drive innovation. Within the Microsoft ecosystem, Dynamics 365 and Copilot offer robust platforms for integrating AI-powered agents and solutions across sales, service, and contact center environments.
22

33
This module provides an overview of foundational concepts and practical approaches for designing AI and agents tailored to business needs. Learners will explore the principles of Responsible AI, ensuring that solutions are developed and deployed in ways that are safe, trustworthy, and aligned with organizational values. Special attention is given to Microsoft's Responsible AI guidelines, which establish a framework for fairness, reliability, privacy, inclusiveness, transparency, and accountability throughout the AI lifecycle.
44

Lines changed: 59 additions & 59 deletions
Original file line numberDiff line numberDiff line change
@@ -1,124 +1,124 @@
1-
## Learning objectives
1+
## Learning objectives
22

33
By the end of this unit, learners will be able to:
4-
- Identify the categories of Azure AI Foundry tools available for agent development and orchestration.
5-
- Match business or technical requirements to the correct tool in the Foundry tool catalog.
6-
- Recommend appropriate Foundry tools for building, grounding, extending, or operationalizing AI agents.
7-
- Evaluate constraints such as data access, API type, compute needs, and integration patterns.
4+
- Identify the categories of Azure AI Foundry tools available for agent development and orchestration
5+
- Match business or technical requirements to the correct tool in the Foundry tool catalog
6+
- Recommend appropriate Foundry tools for building, grounding, extending, or operationalizing AI agents
7+
- Evaluate constraints such as data access, API type, compute needs, and integration patterns
88

9-
## 1. Introduction
9+
## Introduction
1010

1111
Azure AI Foundry provides a **catalog of tools** that agents can use to perform tasks such as retrieving data, calling APIs, grounding responses, orchestrating workflows, and triggering actions across applications.
1212

1313
When designing an AI agent, selecting the correct tool is essential. The goal is to choose tools that:
1414

15-
- **Meet the requirement with minimal complexity.**
15+
- **Meet the requirement with minimal complexity**
1616

17-
- **Ensure security and compliance.**
17+
- **Ensure security and compliance**
1818

19-
- **Leverage existing enterprise systems.**
19+
- **Leverage existing enterprise systems**
2020

21-
- **Reduce integration overhead.**
21+
- **Reduce integration overhead**
2222

23-
- **Support accurate, grounded outputs.**
23+
- **Support accurate, grounded outputs**
2424

25-
## 2. Categories of Foundry tools
25+
## Categories of Foundry tools
2626

2727
_Based on Azure AI Foundry tool catalog organization_.
2828

2929
Azure AI Foundry tools fall into several functional categories commonly used when designing AI agents.
3030

31-
### 2.1 Retrieval and grounding tools
31+
### Retrieval and grounding tools
3232

33-
Used when the agent must **access enterprise knowledge** or **retrieve relevant documents**.Typical capabilities include:
33+
Used when the agent must **access enterprise knowledge** or **retrieve relevant documents**. Typical capabilities include:
3434

35-
- Vector search.
35+
- Vector search
3636

37-
- Hybrid (keyword + semantic) search.
37+
- Hybrid (keyword + semantic) search
3838

39-
- Indexing structured or unstructured sources.
39+
- Indexing structured or unstructured sources
4040

41-
- Querying enterprise knowledge bases.
41+
- Querying enterprise knowledge bases
4242

43-
### 2.2 Data and application connectors
43+
### Data and application connectors
4444

4545
Used when the agent must interact with business applications or databases:
4646

47-
- CRM systems.
47+
- CRM systems
4848

49-
- ERP or financial systems.
49+
- ERP or financial systems
5050

51-
- Line-of-business appsofbusiness apps.
51+
- Line-of-business apps
5252

53-
- SQL databases or Cosmos DB.
53+
- SQL databases or Cosmos DB
5454

55-
- REST or Graph API endpoints.
55+
- REST or Graph API endpoints
5656

57-
### 2.3 Workflow and action tools
57+
### Workflow and action tools
5858

5959
Used to trigger **automated business actions**, such as:
6060

61-
- Creating records.
61+
- Creating records
6262

63-
- Updating cases.
63+
- Updating cases
6464

65-
- Sending notifications.
65+
- Sending notifications
6666

67-
- Triggering Power Automate flows.
67+
- Triggering Power Automate flows
6868

69-
- Calling custom API operations.
69+
- Calling custom API operations
7070

71-
### 2.4 Reasoning, planning, and execution tools
71+
### Reasoning, planning, and execution tools
7272

7373
Used when the agent must:
7474

75-
- Evaluate conditions.
75+
- Evaluate conditions
7676

77-
- Break tasks into steps.
77+
- Break tasks into steps
7878

79-
- Select the right action.
79+
- Select the right action
8080

81-
- Handle branching logic.
81+
- Handle branching logic
8282

83-
### 2.5 Specialized tools
83+
### Specialized tools
8484

85-
Used for purpose specific capabilities:specific capabilities:
85+
Used for purpose-specific capabilities:
8686

87-
- Document summarization.
87+
- Document summarization
8888

89-
- Classification.
89+
- Classification
9090

91-
- Custom ML model execution.
91+
- Custom ML model execution
9292

93-
- Safe completion and validation toolscompletion and validation tools.
93+
- Safe completion and validation tools
9494

95-
## 3. Proposing tools for requirements
95+
## Proposing tools for requirements
9696

9797
Below are examples of how to map business requirements to the correct Foundry tools.
9898

99-
### 3.1 Requirement type: Retrieve policies, guidelines, or knowledge
99+
### Requirement type: Retrieve policies, guidelines, or knowledge
100100

101101
**Recommended Tools:**
102102

103-
- **Retrieval tools** (vector search).
103+
- **Retrieval tools** (vector search)
104104

105105
- **Hybrid search connectors**
106106

107107
- **SharePoint / OneDrive document ingestion tools**
108108

109109
**Why:** These tools ground an agent in enterprise knowledge while respecting security controls.
110110

111-
### 3.2 Requirement type: Integrate with business systems (CRM, ERP, HR)
111+
### Requirement type: Integrate with business systems (CRM, ERP, HR)
112112

113113
**Recommended Tools:**
114114

115-
- **Native application connectors** (Dynamics, SAP, ServiceNow, custom APIs).
115+
- **Native application connectors** (Dynamics, SAP, ServiceNow, custom APIs)
116116

117117
- **Custom REST/Graph API connectors**
118118

119119
**Why:** Allow agents to read/write data in enterprise-approved systems.
120120

121-
### 3.3 Requirement type: Execute multistep workflows
121+
### Requirement type: Execute multistep workflows
122122

123123
**Recommended Tools:**
124124

@@ -128,33 +128,33 @@ Below are examples of how to map business requirements to the correct Foundry to
128128

129129
- **Custom action tools**
130130

131-
**Why:** These tools let agents trigger actions reliably and repeatably.
131+
**Why:** These tools let agents trigger actions reliably and repeatedly.
132132

133-
### 3.4 Requirement type: Analyze or transform data
133+
### Requirement type: Analyze or transform data
134134

135135
**Recommended Tools:**
136136

137-
- **Azure Functions** (lightweight compute tasks).
137+
- **Azure Functions** (lightweight compute tasks)
138138

139-
- **ML model tools** (classification, extraction, scoring).
139+
- **ML model tools** (classification, extraction, scoring)
140140

141-
- **Data transformation connectors**.
141+
- **Data transformation connectors**
142142

143143
**Why:** They enable structured, controlled processing before returning results.
144144

145-
### 3.5 Requirement type: Build advanced reasoning or task decomposition
145+
### Requirement type: Build advanced reasoning or task decomposition
146146

147147
**Recommended Tools:**
148148

149149
- **Planner / Reasoning tools**
150150

151-
- **LLM based decision toolsbased decision tools**
151+
- **LLM-based decision tools**
152152

153153
- **Context evaluators**
154154

155155
**Why:** These tools help agents choose the right next step safely.
156156

157-
## 4. Chart: Mapping requirements to Foundry tools
157+
## Chart: Mapping requirements to Foundry tools
158158

159159
| **Requirement Type** | **Recommended Tool Category** | **Examples** |
160160
|---|---|---|
@@ -164,10 +164,10 @@ Below are examples of how to map business requirements to the correct Foundry to
164164
| Data processing | Compute Tools | Azure Functions, ML Tools |
165165
| Decision and planning | Reasoning Tools | Planner, rule evaluators |
166166

167-
## 5. References
167+
## References
168168

169-
(Use these for learner follow-up).
169+
(Use these for learner follow-up)
170170

171-
Propose tools for Azure AI Foundry agents tool catalog[Azure AI Foundry tool catalog](/azure/ai-foundry/agents/concepts/tool-catalog).
171+
- [Azure AI Foundry tool catalog](/azure/ai-foundry/agents/concepts/tool-catalog)
172172

173-
Azure AI Foundry Tools <https://azure.microsoft.com/products/ai-foundry/tools/>.
173+
- Azure AI Foundry Tools <https://azure.microsoft.com/products/ai-foundry/tools/>
Lines changed: 36 additions & 35 deletions
Original file line numberDiff line numberDiff line change
@@ -1,34 +1,35 @@
1-
## Unit Overview
1+
## Unit Overview
22

33
Generative capabilities in Power Apps now allow makers—especially code-first developers—to create model-driven app pages using natural language. Combined with an **agent feed**, organizations can deliver dynamic, personalized, and adaptive app experiences that respond in real-time to business data, user actions, and AI-generated insights. This unit introduces how generative pages work, how developers can architect "code-first" enhancements, and how agent feeds add intelligence to business applications.
44

55
## Learning objectives
66

77
By the end of this unit, learners will be able to:
8-
- Describe the purpose of **generative pages** in model-driven apps.
9-
- Propose when to use **code-first extensions** with generative pages.
10-
- Explain the role and value of an **agent feed** in responsive app experiences.
8+
9+
- Describe the purpose of **generative pages** in model-driven apps
10+
- Propose when to use **code-first extensions** with generative pages
11+
- Explain the role and value of an **agent feed** in responsive app experiences
1112
- Recommend appropriate use cases for generative pages and agent driven functionality
1213

13-
## 1. Understanding generative pages in model-driven apps
14+
## Understanding generative pages in model-driven apps
1415

1516
Generative pages allow app makers to **describe a requirement in natural language**, and Power Apps automatically creates a page layout, data experiences, and UI structure. This accelerates solution development by removing repetitive scaffolding steps.
1617

17-
**How it works**
18+
### How it works
1819

1920
Maker enters natural language prompt: *"Create a customer overview page showing recent orders, open cases, and a satisfaction score."*
2021

21-
- Power Apps analyzes available Dataverse data.
22+
- Power Apps analyzes available Dataverse data
2223

23-
- A generative engine creates a page layout, bindings, and forms.
24+
- A generative engine creates a page layout, bindings, and forms
2425

25-
- Maker optionally adjusts the page using codefirst or low-code features.
26+
- Maker optionally adjusts the page using code-first or low-code features
2627

27-
- The system generates content aligned with enterprise-grade security and governance.
28+
- The system generates content aligned with enterprise-grade security and governance
2829

29-
## 2. Code-first extensions for generative pages
30+
## Code-first extensions for generative pages
3031

31-
Even though generative pages reduce design time, many enterprise apps require deeper customization. Codefirst developers enhance generated pages using:
32+
Even though generative pages reduce design time, many enterprise apps require deeper customization. Code-first developers enhance generated pages using:
3233

3334
- **JavaScript event handlers**
3435

@@ -38,66 +39,66 @@ Even though generative pages reduce design time, many enterprise apps require de
3839

3940
- **Reusable components and services**
4041

41-
- **Security aware data pipelines aware data pipelines**
42+
- **Security-aware data pipelines**
4243

43-
- **Why use code-first with generative pages?**
44+
### Why use code-first with generative pages?
4445

45-
| **Need** | **Code-first BenefitFirst Benefit** |
46+
| **Need** | **Code-first benefit** |
4647
|---|---|
4748
| Complex business rules | Implement logic not expressible through prompts alone |
4849
| Highly customized UI | Add PCF components, advanced layouts |
49-
| Cross system integrationsystem integration | Build connectors, plugins, service calls |
50-
| Performance optimization| Finetune load patterns, caching, batching |
51-
| Compliance and governance | Embed rules, validations, safe compute patterns compute patterns |
50+
| Cross-system integration | Build connectors, plugins, service calls |
51+
| Performance optimization | Finetune load patterns, caching, batching |
52+
| Compliance and governance | Embed rules, validations, safe compute patterns |
5253

53-
## 3. The role of an agent feed in apps
54+
## The role of an agent feed in apps
5455

5556
An **agent feed** introduces an AI-powered layer that provides real-time insight and recommendations inside apps.
5657

57-
**Agent feed capabilities**
58+
### Agent feed capabilities
5859

59-
- Summaries of records or processes.
60+
- Summaries of records or processes
6061

61-
- Suggestions for actions such as *"follow-up with this customer"*.
62+
- Suggestions for actions such as *"follow-up with this customer"*
6263

63-
- Notifications when anomalies are detected.
64+
- Notifications when anomalies are detected
6465

65-
- Contextual insights based on model driven app data.
66+
- Contextual insights based on model driven app data
6667

67-
- Guided steps and automation triggers.
68+
- Guided steps and automation triggers
6869

69-
**How an agent feed works**
70+
### How an agent feed works
7071

7172
The agent monitors app context, user actions, and records.
7273

7374
It surfaces insights directly in the app.
7475

7576
The agent provides next-best actions aligned with business goals.
7677

77-
## 4. When to use generative pages + agent feed together
78+
## When to use generative pages + agent feed together
7879

7980
| **Scenario** | **Recommended Use** |
8081
|---|---|
81-
| Need rapid creation of data driven screensdriven screens | Use generative pages |
82+
| Need rapid creation of data-driven screens | Use generative pages |
8283
| Require dynamic, insight-driven agent guidance | Add agent feed |
8384
| App needs automated suggestions | Agent feed triggers |
84-
| Developer must extend or override generated UI | Code-first enhancements-first |
85-
| High-volume workflow automation volume workflow automation | Combine all three (generative + agent + code-first) |
85+
| Developer must extend or override generated UI | Code-first enhancements |
86+
| High-volume workflow automation | Combine all three (generative + agent + code-first) |
8687

8788
Together, they create intelligent, fast to build, enterprise-ready apps.
8889

89-
## 5. Chart: Comparing prompt-first vs code-first vs agent-driven apps
90+
## Chart: Comparing prompt-first vs code-first vs agent-driven apps
9091

9192
| **Approach** | **Strengths** | **Best Use Cases** |
9293
|---|---|---|
93-
| Prompt First (Generative) | Fast creation, natural language, guided layouts | Rapid prototyping, early drafts, citizen developer apps-developer apps |
94+
| Prompt First (Generative) | Fast creation, natural language, guided layouts | Rapid prototyping, early drafts, citizen developer apps |
9495
| Code-first | Full control, extensibility, complex logic | Enterprise apps with custom workflows |
9596
| Agent Driven | Insightful, adaptive, AI-assisted | Decision support, operational intelligence |
9697

97-
## 6. References
98+
## References
9899

99100
Use these links for more detail and hands on practice:
100101

101-
- **Introducing the new Power Apps generative experiences** <https://www.microsoft.com/power-platform/blog/power-apps/introducing-the-new-power-apps-generative-power-meets-enterprise-grade-trust/>.
102+
- **Introducing the new Power Apps generative experiences** <https://www.microsoft.com/power-platform/blog/power-apps/introducing-the-new-power-apps-generative-power-meets-enterprise-grade-trust/>
102103

103-
- **Generative Pages FAQ (GitHub)** <https://github.com/MicrosoftDocs/powerapps-docs/blob/main/powerapps-docs/maker/common/faq-generative-pages-model-driven.md>.
104+
- **Generative Pages FAQ (GitHub)** <https://github.com/MicrosoftDocs/powerapps-docs/blob/main/powerapps-docs/maker/common/faq-generative-pages-model-driven.md>

0 commit comments

Comments
 (0)