Fix blocking review feedback for module 8

Author: msdavidram

learn-pr/wwl/analyze-monitor-tune-ai-powered-business-solutions/includes/2-recommend-process-tools-monitoring-agents.md

@@ -4,9 +4,9 @@ This unit equips solution architects with the expertise to define, recommend, an
 
 You will explore monitoring processes, recommended tools, observability patterns, dashboards, alerting approaches, and analytical insights that support continuous improvement of agent behavior.
 
-## 1. Understanding Monitoring Requirements for AI Agents
+## Understanding Monitoring Requirements for AI Agents
 
-### Monitoring AI agents requires a multilayered approach. Solution architects must consider:
+### Monitoring AI agents requires a multilayered approach. Solution architects must consider
 
 **Operational Health**<br>Uptime, availability, error frequency, throttling conditions, processing delays.
 
@@ -18,19 +18,15 @@ You will explore monitoring processes, recommended tools, observability patterns
 
 **Risk, Compliance, and Security**<br>Guardrail violations, sensitivedata handling, suspicious activity spikes, adherence to organizational policies.
 
-### AI Agent Monitoring Layers
-
-:::image type="content" source="../media/ai-agent-monitoring-layers.png" alt-text="AI agent monitoring layers":::
-
-## 2. Recommended Processes for Monitoring AI Agents
+## Recommended Processes for Monitoring AI Agents
 
 Solution architects should recommend the processes for monitoring AI Agents across an organization. When an existing framework is in place, the architect should look for missing components or improvements. 
 
-### 2.1 Establish a Monitoring Operating Model
+### Establish a Monitoring Operating Model
 
 * A strong operational model ensures consistency, ownership, and accountability.
 
-#### Key components:
+#### Key components
 
 * Defined roles (Ops team, product owners, data engineers, architects)
 
@@ -44,15 +40,15 @@ Solution architects should recommend the processes for monitoring AI Agents acro
 
 * Documentation of expected agent behaviors and constraints
 
-### 2.2 Configure Guardrails and Threshold Alerts
+### Configure Guardrails and Threshold Alerts
 
 * Set thresholds for latency, exception volume, and unusual activity.
 
 * Create automated alerts for guardrail triggers or tool invocation failures.
 
 * Monitor for unexpected spikes in prompts indicating potential misuse.
 
-### 2.3 Conduct Regular Quality Evaluations
+### Conduct Regular Quality Evaluations
 
 * Humanintheloop spot checks
 
@@ -62,7 +58,7 @@ Solution architects should recommend the processes for monitoring AI Agents acro
 
 * Validate alignment with business rules or compliance requirements
 
-### 2.4 Continuously Improve Based on Insights
+### Continuously Improve Based on Insights
 
 * Analyze logs and telemetry to find failure patterns.
 
@@ -72,13 +68,13 @@ Solution architects should recommend the processes for monitoring AI Agents acro
 
 * Propose workflow adjustments or retraining of custom models (if applicable).
 
-## 3. Recommended Tools for Monitoring AI Agents
+## Recommended Tools for Monitoring AI Agents
 
 Solution architects should recommend the toolset that covers **observability**, **analytics**, and **administrative insights**.
 
-### 3.1 Azure Monitor (Core Telemetry + Alerts)
+### Azure Monitor (Core Telemetry + Alerts)
 
-#### Azure Monitor provides:
+#### Azure Monitor provides
 
 * Application and agent telemetry
 
@@ -88,17 +84,17 @@ Solution architects should recommend the toolset that covers **observability**,
 
 * Integration with Log Analytics Workspaces
 
-#### Use cases:
+#### Use cases
 
 * Monitor agent workflows built with Power Platform or custom services.
 
 * Track errors, latency, throughput, connector failures.
 
 * Build KQL-based queries for deep diagnostics.
 
-### 3.2 Microsoft 365 Admin Analytics (Usage & Adoption Trends)
+### Microsoft 365 Admin Analytics (Usage & Adoption Trends)
 
-#### Useful for:
+#### Useful for
 
 * Understanding agent usage volume
 
@@ -108,9 +104,9 @@ Solution architects should recommend the toolset that covers **observability**,
 
 * Measuring improvements week-over-week
 
-### 3.3 Copilot & Agent Analytics Dashboards
+### Copilot & Agent Analytics Dashboards
 
-#### When available in an organization's tenant, Copilot analytics can provide:
+#### When available in an organization's tenant, Copilot analytics can provide
 
 * Agent invocation frequency
 
@@ -122,9 +118,9 @@ Solution architects should recommend the toolset that covers **observability**,
 
 * Error or guardrail-trigger events
 
-### 3.4 Power Platform Admin Center (Environment-Level Monitoring)
+### Power Platform Admin Center (Environment-Level Monitoring)
 
-#### Provides:
+#### Provides
 
 * Environment health
 
@@ -134,9 +130,9 @@ Solution architects should recommend the toolset that covers **observability**,
 
 * DLP rule impact visibility
 
-### 3.5 Foundry or Organizational Observability Platforms
+### Foundry or Organizational Observability Platforms
 
-#### Enterprises may adopt centralized observability platforms (example: Foundry-like solutions, if present in the environment) to unify:
+#### Enterprises may adopt centralized observability platforms (example: Foundry-like solutions, if present in the environment) to unify
 
 * Multisystem logs
 
@@ -148,9 +144,9 @@ Solution architects should recommend the toolset that covers **observability**,
 
 * These platforms reduce fragmentation and provide a single-pane-of-glass view for complex agent ecosystems.
 
-### 3.6 Custom Dashboards for Enterprise AI Agents
+### Custom Dashboards for Enterprise AI Agents
 
-#### Solution architects often design:
+#### Solution architects often design
 
 * KPI dashboards in Power BI
 
@@ -160,19 +156,14 @@ Solution architects should recommend the toolset that covers **observability**,
 
 * Compliance trend reports
 
-#### Example: Agent Health Summary
+#### Example Agent Health Summary
 
 | Agent Name | Success Rate | Avg. Response Time | Errors Today | Usage Trend |
 | --- | --- | --- | --- | --- |
 | Sales Helper | 98% | 1.8 sec | 3 | ↑ Increasing |
 | Ops Agent | 92% | 2.5 sec | 17 | → Steady |
 | Finance Advisor | 86% | 3.2 sec | 28 | ↓ Decreasing |
 
-### 4. Designing an Enterprise Monitoring Architecture for Agents
-
-:::image type="content" source="../media/designing-enterprise-monitoring-architecture-for-agents.png" alt-text="Designing enterprise monitoring architecture for AI agents":::
-
-
 #### Best Practices
 
 * Always centralize logs.
@@ -187,10 +178,10 @@ Solution architects should recommend the toolset that covers **observability**,
 
 ## References
 
-[https://learn.microsoft.com/en-us/training/modules/describe-monitoring-tools-azure/4-describe-azure-monitor](/training/modules/describe-monitoring-tools-azure/4-describe-azure-monitor)
+[https://learn.microsoft.com/training/modules/describe-monitoring-tools-azure/4-describe-azure-monitor](/training/modules/describe-monitoring-tools-azure/4-describe-azure-monitor)
 
-[https://learn.microsoft.com/en-us/training/modules/perform-admin-tasks-microsoft-365-copilot/](/training/modules/perform-admin-tasks-microsoft-365-copilot/)
+[https://learn.microsoft.com/training/modules/perform-admin-tasks-microsoft-365-copilot/](/training/modules/perform-admin-tasks-microsoft-365-copilot/)
 
-[https://learn.microsoft.com/en-us/azure/ai-foundry/observability/how-to/how-to-monitor-agents-dashboard?view=foundry](/azure/ai-foundry/observability/how-to/how-to-monitor-agents-dashboard)
+[https://learn.microsoft.com/azure/ai-foundry/observability/how-to/how-to-monitor-agents-dashboard?view=foundry](/azure/ai-foundry/observability/how-to/how-to-monitor-agents-dashboard)
 
 [https://learn.microsoft.com/power-platform/admin/analytics-copilot](/power-platform/admin/analytics-copilot)

learn-pr/wwl/analyze-monitor-tune-ai-powered-business-solutions/includes/3-analyze-backlog-user-feedback-ai-agent-usage.md

@@ -4,9 +4,9 @@ This unit teaches solution architects how to evaluate, interpret, and act on bac
 
 Solution architects play a critical role in translating insights from telemetry, backlog queues, and conversation transcripts into architectural decisions, iterative improvements, and governance recommendations. This unit provides a repeatable framework for analyzing data and driving continuous improvement cycles for AIpowered agents.
 
-## 1. Understanding AI Backlogs and User Feedback Loops
+## Understanding AI Backlogs and User Feedback Loops
 
-### A backlog in AI and agent operations typically contains:
+### A backlog in AI and agent operations typically contains
 
 * Enhancement requests
 
@@ -20,7 +20,7 @@ Solution architects play a critical role in translating insights from telemetry,
 
 * Governance or policy misalignment concerns
 
-### User feedback may originate from:
+### User feedback may originate from
 
 * Conversation transcripts
 
@@ -34,7 +34,7 @@ Solution architects play a critical role in translating insights from telemetry,
 
 * Observability dashboards
 
-### Effective backlog analysis helps solution architects:
+### Effective backlog analysis helps solution architects
 
 * Prioritize improvements based on impact
 
@@ -46,13 +46,13 @@ Solution architects play a critical role in translating insights from telemetry,
 
 * Identify opportunities for automation and process redesign
 
-## 2. Framework for Backlog Analysis
+## Framework for Backlog Analysis
 
 Use a structured, repeatable model to elevate analysis to a solutionarchitecture level.
 
-### 2.1 Categorize the Backlog by Domain
+### Categorize the Backlog by Domain
 
-#### Organize items into categories such as:
+#### Organize items into categories such as
 
 * **Accuracy and Reasoning**: Incorrect, missing, or lowconfidence responses
 
@@ -77,15 +77,15 @@ Use a structured, repeatable model to elevate analysis to a solutionarchitecture
 | Integration | API failures; broken actions |
 | Governance | Data access blocked; DLP alerts |
 
-### 2.2 Prioritize by Impact and Effort
+### Prioritize by Impact and Effort
 
 Use a matrix to classify items based on business impact and required effort.
 
 :::image type="content" source="../media/impact-effort-prioritization-matrix.png" alt-text="Impact effort prioritization matrix":::
 
-### 2.3 Leverage User Feedback Signals
+### Leverage User Feedback Signals
 
-#### Solution architects should analyze:
+#### Solution architects should analyze
 
 * Frequency of similar feedback (volume signals)
 
@@ -102,9 +102,9 @@ Use a matrix to classify items based on business impact and required effort.
 :::image type="content" source="../media/user-feedback-funnel.png" alt-text="User feedback funnel":::
 
 
-## 3. Using Conversation Transcripts to Identify Patterns
+## Using Conversation Transcripts to Identify Patterns
 
-### Conversation transcripts reveal:
+### Conversation transcripts reveal
 
 * Where the agent misunderstood intent
 
@@ -116,7 +116,7 @@ Use a matrix to classify items based on business impact and required effort.
 
 * Workflows requiring human intervention
 
-### Solution architects should:
+### Solution architects should
 
 * Extract common failure paths
 
@@ -128,11 +128,11 @@ Use a matrix to classify items based on business impact and required effort.
 
 * Agent Improvement Plan
 
-## 4. Monitoring Agent Usage and Behavior
+## Monitoring Agent Usage and Behavior
 
 Monitoring ensures agents operate as intended and scale properly.
 
-### Key items for architects to monitor:
+### Key items for architects to monitor
 
 * Usage trends and adoption
 
@@ -158,11 +158,11 @@ Monitoring ensures agents operate as intended and scale properly.
 | Supply Chain Helper | 91% | 2.8 sec | 14 |
 | Analytics Coach | 88% | 3.2 sec | 21 |
 
-## 5. Closing the Loop: Turning Insights into Action
+## Closing the Loop Turning Insights into Action
 
 Solution architects drive improvement cycles by:
 
-### 5.1 Designing a FeedbacktoImprovement Pipeline
+### Designing a FeedbacktoImprovement Pipeline
 
 * Consolidate backlog and user feedback
 
@@ -176,7 +176,7 @@ Solution architects drive improvement cycles by:
 
 * Monitor drift and regression
 
-### 5.2 Embedding Continuous Improvement
+### Embedding Continuous Improvement
 
 * Refresh knowledge sources regularly
 
@@ -188,9 +188,9 @@ Solution architects drive improvement cycles by:
 
 * Implement new guardrails based on risk patterns
 
-### 5.3 Reporting and Stakeholder Communication
+### Reporting and Stakeholder Communication
 
-#### Communicate:
+#### Communicate
 
 * Top backlog themes
 
@@ -204,7 +204,7 @@ Solution architects drive improvement cycles by:
 
 ## References
 
-[https://learn.microsoft.com/en-us/microsoft-copilot-studio/guidance/kit-agent-inventory](/microsoft-copilot-studio/guidance/kit-agent-inventory)
+[https://learn.microsoft.com/microsoft-copilot-studio/guidance/kit-agent-inventory](/microsoft-copilot-studio/guidance/kit-agent-inventory)
 
 [https://learn.microsoft.com/power-platform/admin/analytics-copilot](/power-platform/admin/analytics-copilot)