Fixing diagram and bullet issues.

Author: Randall-Knapp

learn-pr/wwl/analyze-requirements-for-ai-powered-business-solutions/includes/2-assess-use-agents-task-automation-data-analytics-decision-making.md

@@ -19,17 +19,17 @@ Generative AI accelerates productivity by drafting content, summarizing informat
 
 Agents help organizations streamline and automate tasks that traditionally require manual work.
 
-**Key Capabilities**
+**Key Capabilities:**
 
-Drafting documents, emails, or responses based on context.
+- Drafting documents, emails, or responses based on context.
 
-Summarizing large volumes of data—emails, meetings, chats.
+- Summarizing large volumes of data—emails, meetings, chats.
 
-Automating workflows through technologies such as Microsoft 365, Copilot Studio, Azure Foundry, and Power Platform. 
+- Automating workflows through technologies such as Microsoft 365, Copilot Studio, Azure Foundry, and Power Platform. 
 
-Triggering multi-step processes (approvals, notifications, content generation).
+- Triggering multi-step processes (approvals, notifications, content generation).
 
-These capabilities reduce cognitive load and help teams focus on strategic, not repetitive, work.<br>
+- These capabilities reduce cognitive load and help teams focus on strategic, not repetitive, work.
 
 **Examples of Agent-Driven Task Automation**
 
@@ -44,17 +44,17 @@ These capabilities reduce cognitive load and help teams focus on strategic, not
 
 AI agents simplify and accelerate data analysis by converting natural language questions into insightful answers.
 
-**Core Agent Capabilities**
+**Core Agent Capabilities:**
 
-Summarizing complex datasets into actionable insights
+- Summarizing complex datasets into actionable insights
 
-Identifying trends, outliers, and patterns
+- Identifying trends, outliers, and patterns
 
-Generating visualizations on demand
+- Generating visualizations on demand
 
-Interpreting dashboards and suggesting next-step actions
+- Interpreting dashboards and suggesting next-step actions
 
-Copilot experiences help employees make sense of data without requiring advanced analytics skills.
+- Copilot experiences help employees make sense of data without requiring advanced analytics skills.
 
 **Visual Diagram: AI Agents in the Analytics Workflow**
 
@@ -64,31 +64,31 @@ Copilot experiences help employees make sense of data without requiring advanced
 
 Agents support strategic and operational decisions through:
 
-**AI-Supported Decision Inputs**
+**AI-Supported Decision Inputs:**
 
-Scenario recommendations based on historical data
+- Scenario recommendations based on historical data
 
-Risk identification through pattern recognition
+- Risk identification through pattern recognition
 
-Summaries of business context from documents, meetings, and datasets
+- Summaries of business context from documents, meetings, and datasets
 
-Recommendations backed by enterprise knowledge
+- Recommendations backed by enterprise knowledge
 
-Generative AI enables leaders to explore alternatives, evaluate impacts, and move faster with confidence.<br>
+- Generative AI enables leaders to explore alternatives, evaluate impacts, and move faster with confidence.<br>
 
 ## 5. Best Practices for Using AI Agents
 
-**Start with the business outcome** you want to improve.
+1. **Start with the business outcome** you want to improve.
 
-**Use agent automation** to reduce repetitive work, not replace critical thinking.
+2. **Use agent automation** to reduce repetitive work, not replace critical thinking.
 
-**Maintain responsible AI principles**— Fairness, Reliability and Safety, Privacy and Security, Inclusiveness, Transparency, Accountability.
+3. **Maintain responsible AI principles**— Fairness, Reliability and Safety, Privacy and Security, Inclusiveness, Transparency, Accountability.
 
-**Monitor performance** and refine prompts, workflows, and data inputs.
+4. **Monitor performance** and refine prompts, workflows, and data inputs.
 
-**Empower teams** with training to use Copilot effectively.
+5. **Empower teams** with training to use Copilot effectively.
 
-These principles reinforce reliable, secure AI adoption at scale.<br>
+These principles reinforce reliable, secure AI adoption at scale.
 
 **References**
 

learn-pr/wwl/analyze-requirements-for-ai-powered-business-solutions/includes/3-review-data-grounding-accuracy-relevance-timeliness-cleanliness-availability.md

@@ -9,11 +9,13 @@ After completing this unit, learners will be able to:
 
 ## 1. Understanding Grounding in AI Agents
 
-Grounding ensures that an AI agent responds using **trusted, domainspecific organizational data**, increasing accuracy and reducing hallucinations.<br>Microsoft Copilot and Copilot Studio use **semantic indexing** to map enterprise content across Microsoft Graph into rich lexical and semantic representations. This enables more contextually precise retrieval.<br>
+Grounding ensures that an AI agent responds using **trusted, domainspecific organizational data**, increasing accuracy and reducing hallucinations.
 
-AI systems must be connected to **approved, accesscontrolled data** so they produce trustworthy outcomes that respect organizational security boundaries.<br>
+Microsoft Copilot and Copilot Studio use **semantic indexing** to map enterprise content across Microsoft Graph into rich lexical and semantic representations. This enables more contextually precise retrieval.
 
-To support advanced grounding, the **Copilot Retrieval API** retrieves relevant text passages from SharePoint, OneDrive, and connected sources, honoring user permissions.<br>
+AI systems must be connected to **approved, accesscontrolled data** so they produce trustworthy outcomes that respect organizational security boundaries.
+
+To support advanced grounding, the **Copilot Retrieval API** retrieves relevant text passages from SharePoint, OneDrive, and connected sources, honoring user permissions.
 
 ## 2. The Five Dimensions of Grounding Data Quality
 
@@ -43,7 +45,7 @@ AI outputs degrade when data is stale.
 
 The **semantic index** in Microsoft 365 continuously updates as content changes, ensuring the grounding layer reflects the latest documents, conversations, and knowledge.
 
-Timeliness includes:
+**Timeliness includes:**
 
 - Modified dates
 
@@ -59,7 +61,7 @@ Data Pollution in AI refers to the degradation of data quality that negatively i
 
 Cleaner data improves embedding quality and helps the agent retrieve the most appropriate content.
 
-Clean data characteristics:
+**Clean data characteristics:**
 
 - Clear structure
 
@@ -75,7 +77,7 @@ Agents can only ground responses from **data the user has access to**.
 
 The Retrieval API respects permissions and will not return content beyond a user's access scope.
 
-Availability depends on:
+**Availability depends on:**
 
 - Storage in SharePoint/OneDrive or connected systems
 
@@ -95,19 +97,19 @@ Availability depends on:
 
 ## 4. Diagram: How Microsoft Copilot Grounds AI Responses
 
-  _Diagram grounded in documentation describing semantic index + Retrieval API pipeline.
+:::image type="content" source="../media/copilot-grounds-ai-responses.png" alt-text="Diagram showing how Microsoft Copilot grounds AI responses using the semantic index and Retrieval API pipeline.":::
 
 ## 5. Best Practices for Reviewing Grounding Data
 
-**Evaluate content quality before upload**: remove outdated or conflicting information.
+1. **Evaluate content quality before upload**: remove outdated or conflicting information.
 
-**Store authoritative content in SharePoint or OneDrive** so it becomes part of the semantic index.
+2. **Store authoritative content in SharePoint or OneDrive** so it becomes part of the semantic index.
 
-**Ensure consistent formatting** to improve data cleanliness and retrieval precision.
+3. **Ensure consistent formatting** to improve data cleanliness and retrieval precision.
 
-**Review permissions regularly** so agents ground from valid data sources only.
+4. **Review permissions regularly** so agents ground from valid data sources only.
 
-**Collaborate with domain SMEs** to validate accuracy and contextual fit.
+5. **Collaborate with domain SMEs** to validate accuracy and contextual fit.
 
 **References**
 

learn-pr/wwl/analyze-requirements-for-ai-powered-business-solutions/includes/4-organize-business-solution-data-available-other-ai-systems.md

@@ -39,15 +39,15 @@ _(From: Leverage AI tools - Drive Transformation on Azure)_
 
 Azure provides the foundational components necessary to **centralize, transform, and govern data** before AI systems consume it.Key concepts include:
 
-**Unified data estate**: Consolidate data from apps, logs, CRM, ERP, operations, and documents.
+- **Unified data estate**: Consolidate data from apps, logs, CRM, ERP, operations, and documents.
 
-**Modern data services**: Azure Cosmos DB, Azure SQL, Azure PostgreSQL, Fabric Lakehouse.
+- **Modern data services**: Azure Cosmos DB, Azure SQL, Azure PostgreSQL, Fabric Lakehouse.
 
-**Intelligence layers**: Azure AI Search, semantic ranking, embeddings, vector search.
+- **Intelligence layers**: Azure AI Search, semantic ranking, embeddings, vector search.
 
-**Interoperability**: APIs, event hubs, and data streaming allow multiple AI systems to use the same data.
+- **Interoperability**: APIs, event hubs, and data streaming allow multiple AI systems to use the same data.
 
-**Azure Data Estate for AI**
+**Azure Data Estate for AI:**
 
 | **Layer** | **Purpose** |
 |---|---|