updates m06

pablorodMS · web-flow · commit 8cfe54f2716c · 2026-03-27T08:20:18.000-06:00
diff --git a/learn-pr/wwl/design-extensibility-ai-solutions/includes/1-introduction.md b/learn-pr/wwl/design-extensibility-ai-solutions/includes/1-introduction.md
@@ -1,5 +1,5 @@
 Welcome to Module 6, which focuses on the design extensibility of AI solutions in enterprise environments. This module introduces solution architects to the foundational concepts, architectural patterns, and best practices for building scalable, secure, and customizable AI solutions using Microsoft platforms. Extensibility is a critical capability that enables organizations to tailor AI systems to their unique business processes, compliance requirements, and operational constraints.
 
-Throughout this module, you will explore how to leverage custom models in Microsoft Foundry, design and operationalize agents within Microsoft 365 Copilot, and extend agent capabilities using Copilot Studio—including advanced integration through the Model Context Protocol (MCP). The unit will guide you through structured approaches for model and agent design, integration with enterprise systems, governance, lifecycle management, and professional visualizations that can be adapted for documentation and presentations.
+Throughout this module, you explore how to use custom models in Microsoft Foundry, design and operationalize agents within Microsoft 365 Copilot, and extend agent capabilities using Copilot Studio—including advanced integration through the Model Context Protocol (MCP). The unit guide you through structured approaches for model and agent design, integration with enterprise systems, governance, lifecycle management, and professional visualizations that can be adapted for documentation and presentations.
 
-By the end of this module, you will be equipped with expert-level guidance and practical frameworks to architect AI solutions that are not only robust and compliant, but also extensible to meet evolving business needs across diverse scenarios and platforms.
+By the end of this module, aren't equipped with expert-level guidance and practical frameworks to architect AI solutions that are not only robust and compliant, but also extensible to meet evolving business needs across diverse scenarios and platforms.
diff --git a/learn-pr/wwl/design-extensibility-ai-solutions/includes/2-design-ai-solutions-custom-models-microsoft-foundry.md b/learn-pr/wwl/design-extensibility-ai-solutions/includes/2-design-ai-solutions-custom-models-microsoft-foundry.md
@@ -53,21 +53,21 @@ Integration with Azure Kubernetes Service and Foundry runtime environments
 
 Solution architects should follow a structured, repeatable design approach to ensure models align with business objectives.
 
-### Step 1 — Define the business objectives
+### Step 1 Define the business objectives
 
 Identify measurable outcomes (accuracy goals, time-saved targets, cost-efficiency goals).
 
 Map objectives to use cases where custom models outperform standard copilots.
 
-### Step 2 — Assess data requirements
+### Step 2 Assess data requirements
 
 Evaluate available proprietary datasets.
 
 Identify gaps in labeling, quality, diversity, or structure.
 
 Ensure governance policies allow data to be used in model training.
 
-### Step 3 — Select the custom model path
+### Step 3 Select the custom model path
 
 #### Typical options include
 
@@ -77,7 +77,7 @@ Ensure governance policies allow data to be used in model training.
 
 **Hybrid architectures**<br>Combining custom models with prebuilt copilots for augmented reasoning.
 
-### Step 4 — Integration with enterprise systems
+### Step 4 Integration with enterprise systems
 
 #### Custom models should integrate with
 
@@ -91,7 +91,7 @@ Azure AI Search and data stores
 
 Business process automation pipelines
 
-### Step 5 — Validation and evaluation
+### Step 5 Validation and evaluation
 
 #### Establish a rigorous testing plan
 
@@ -117,11 +117,7 @@ Modern AI systems require robust operational frameworks, especially with custom
 
 **Deployment Automation (MLOps/GenAIOps)**<br>Automate validations, approval workflows, and environment-specific deployments.
 
-## Professional visuals (text-based)
-
-These visuals can be directly converted into diagrams for Word or PowerPoint.
-
-### Visual A — Custom model decision matrix
+### Custom model decision matrix
 
 Decision Factor             | Standard Copilot | Custom Model (Foundry)
 
@@ -139,34 +135,6 @@ Workflow complexity          | Low/Medium       | High
 
 Inference cost optimization  | Moderate         | High (small language models)
 
-### Visual B — Custom model development lifecycle
-
-Business Goal → Data Collection → Data Preparation →
-
-Model Selection → Training/Fine-Tuning → Evaluation →
-
-Deployment → Monitoring & Optimization
-
-### Visual C — AI solution architecture (Foundry)
-
-User Request
-
-    ↓
-
-Foundry Agent Orchestration
-
-    ↓
-
-Custom Model Inference Engine
-
-    ↓
-
-Enterprise Data Connectors & Tools
-
-    ↓
-
-Business Outcome Returned to Application
-
 ## References
 
 [https://learn.microsoft.com/en-us/training/modules/choose-ai-agent-development-path/](/training/modules/choose-ai-agent-development-path/)
diff --git a/learn-pr/wwl/design-extensibility-ai-solutions/includes/4-design-agent-extensibility-copilot-studio.md b/learn-pr/wwl/design-extensibility-ai-solutions/includes/4-design-agent-extensibility-copilot-studio.md
@@ -26,7 +26,7 @@ Instruction-level extensibility defines the behavior, tone, boundaries, and reas
 
 **Purpose** (why the agent exists).
 
-**Role and constraints** (what it is allowed and not allowed to do).
+**Role and constraints** (what it's allowed and not allowed to do).
 
 **Action patterns** (preferred workflows and decision points).
 
@@ -104,7 +104,7 @@ Better isolation for compliance and secure design.
 
 #### Pattern 2: Multiagent collaboration pattern
 
-In complex environments, one agent should not do everything. Architects create multiple specialized agents that collaborate through defined protocols.
+In complex environments, one agent shouldn't do everything. Architects create multiple specialized agents that collaborate through defined protocols.
 
 Examples:
 
@@ -116,7 +116,7 @@ A "communication agent" drafts and formats content.
 
 #### Pattern 3: Domain-context pattern
 
-The agent adapts its reasoning based on the system, environment, or domain it is working within.
+The agent adapts its reasoning based on the system, environment, or domain it's working within.
 
 A domain-context pattern defines:
 
@@ -150,76 +150,10 @@ Microsoft has developed the Architecting agent solutions content that provides f
 - [Operability](/microsoft-copilot-studio/guidance/architecture/determine-operability)
 - [Trust, traceability, and transparency](/microsoft-copilot-studio/guidance/architecture/determine-trust)
 
-This framework does not cover content already addressed by established standards such as [Azure Well-Architected Framework](/azure/well-architected/), [Power Platform Well-Architected](/power-platform/well-architected), [National Institute of Standards and Technology (NIST)](https://www.nist.gov/cyberframework), or other recognized security frameworks. 
+This framework doesn't cover content already addressed by established standards such as [Azure Well-Architected Framework](/azure/well-architected/), [Power Platform Well-Architected](/power-platform/well-architected), [National Institute of Standards and Technology (NIST)](https://www.nist.gov/cyberframework), or other recognized security frameworks. 
 
 For more information see the following principles and patterns for architecting agent solutions: [https://learn.microsoft.com/microsoft-copilot-studio/guidance/architecture/](/microsoft-copilot-studio/guidance/architecture/) 
 
-## Professional visuals (text-based for Word)
-
-### Visual A — Extensibility layers model
-
-+---------------------------------------+
-
-|      Instruction-Level Extensibility  |
-
-+---------------------------------------+
-
-|        Skills & Capability Layer      |
-
-+---------------------------------------+
-
-|         Integration Extensibility     |
-
-+---------------------------------------+
-
-|  Pro-Code Extensibility (VS Code)     |
-
-+---------------------------------------+
-
-### Visual B — Modular agent architecture
-
-Agent Core Instruction Set
-
-        |
-
-        +-- Skills Library
-
-        |
-
-        +-- Integration Connectors
-
-        |
-
-        +-- Domain Knowledge Packs
-
-        |
-
-        +-- Pro-Code Extensions (VS Code)
-
-### Visual C — Agent interaction flow
-
-User Request
-
-   ↓
-
-Agent Instruction Engine
-
-   ↓
-
-Skill / Tool Selection
-
-   ↓
-
-Integration or Knowledge Retrieval
-
-   ↓
-
-Response Generation + Controls
-
-   ↓
-
-Return to User
-
 ## References
 
 [https://learn.microsoft.com/microsoft-copilot-studio/extensibility](/microsoft-copilot-studio/extensibility)
diff --git a/learn-pr/wwl/design-extensibility-ai-solutions/includes/5-design-agent-extensibility-model-context-protocol-copilot-studio.md b/learn-pr/wwl/design-extensibility-ai-solutions/includes/5-design-agent-extensibility-model-context-protocol-copilot-studio.md
@@ -28,15 +28,15 @@ Agents must be designed with modular, layered instructions:
 
 #### Core components
 
-_Purpose statement_ — Clarifies primary function
+_Purpose statement_ Clarifies primary function
 
-_Role definition_ — Sets tone and perspective
+_Role definition_ Sets tone and perspective
 
-_Behavior rules_ — Compliance, safety, and guardrails
+_Behavior rules_ Compliance, safety, and guardrails
 
-_Context consumption logic_ — How MCP data is used
+_Context consumption logic_ How MCP data is used
 
-_Action boundaries_ — Defines approved capabilities
+_Action boundaries_ Defines approved capabilities
 
 ### 2.2 Context extensibility using MCP
 
@@ -62,7 +62,7 @@ Generate explanations aligned with business rules
 
 ## Integration patterns for MCP-enabled agents
 
-### Pattern A — Context-driven reasoning
+### Pattern A Context-driven reasoning
 
 Agents retrieve real-time MCP context to ensure responses reflect authoritative business rules.
 
@@ -74,11 +74,11 @@ Finance workflows
 
 Procurement and vendor mgmt scenarios
 
-### Pattern B — Workflow-integrated agents
+### Pattern B Workflow-integrated agents
 
 Agents augment workflows by using MCP to drive approvals, escalate exceptions, and summarize status.
 
-### Pattern C — Multi-agent collaboration via MCP
+### Pattern C Multi-agent collaboration via MCP
 
 Use MCP to standardize data each agent can reference, improving cross-domain collaboration (e.g., HR + Finance + Supply Chain AI processes).
 
@@ -96,68 +96,6 @@ Agent instructions must enforce responsible AI behavior
 
 Business and IT ownership established through an AI CoE model
 
-## Professional visuals (text-based for Word copying)
-
-### Visual 1 — MCP Context Architecture
-
-Copilot Studio Agent
-
-       │
-
-       ▼
-
-Model Context Protocol Layer
-
-       │
-
-       ▼
-
-Dynamics 365 F&O Context Models
-
-(Entity Metadata · Business Rules · Taxonomies)
-
-       │
-
-       ▼
-
-Enterprise Data & Applications
-
-**Visual 2 — Extensibility Layer Model**
-
-[Instruction Layer]
-
-     ↓
-
-[Behavior & Guardrails]
-
-     ↓
-
-[Context Layer — MCP]
-
-     ↓
-
-[Integration Layer — Actions & Connectors]
-
-**Visual 3 — Agent Workflow with MCP**
-
-User Prompt
-
-   ↓
-
-Agent Instruction Engine
-
-   ↓
-
-MCP Context Retrieval
-
-   ↓
-
-Reasoning + Business Rule Alignment
-
-   ↓
-
-Action / Response Generation
-
 ## References
 
 [https://learn.microsoft.com/dynamics365/fin-ops-core/dev-itpro/copilot/copilot-mcp](/dynamics365/fin-ops-core/dev-itpro/copilot/copilot-mcp)
diff --git a/learn-pr/wwl/design-extensibility-ai-solutions/includes/8-optimize-solution-design-agents-microsoft-365-teams-sharepoint.md b/learn-pr/wwl/design-extensibility-ai-solutions/includes/8-optimize-solution-design-agents-microsoft-365-teams-sharepoint.md
@@ -86,7 +86,7 @@ Examples:
 
 When installed on a SharePoint site, the agent:
 
-Knows which site it is on
+Knows which site it's on
 
 Uses that site's content as its primary grounding source
 
@@ -180,7 +180,7 @@ Alignment with AI CoE governance
 
 ## Solution patterns for Microsoft 365 agents
 
-### Pattern 1 — SharePoint Knowledge Assistant
+### Pattern 1 SharePoint Knowledge Assistant
 
 #### Purpose:
 
@@ -190,7 +190,7 @@ Help users find documents
 
 Provide summaries and insights
 
-### Pattern 2 — Teams Project Assistant
+### Pattern 2 Teams Project Assistant
 
 #### Purpose:
 
@@ -202,7 +202,7 @@ Retrieve documents from SharePoint
 
 Automate task creation
 
-### Pattern 3 — Organizational Policy Assistant
+### Pattern 3 Organizational Policy Assistant
 
 #### Purpose:
 
@@ -212,7 +212,7 @@ Provide grounded answers
 
 Ensure compliance and accuracy
 
-### Pattern 4 — Site Owner Support Agent
+### Pattern 4 Site Owner Support Agent
 
 #### Purpose:
 
@@ -222,20 +222,6 @@ Suggest improvements
 
 Draft pages and content
 
-## Professional visuals (text-based)
-
-### Visual 1 — Microsoft 365 Agent Architecture
-
-User Request ↓ Teams or SharePoint Interface ↓ Copilot Studio Agent ↓ Microsoft Graph + SharePoint Content ↓ Grounded Response 
-
-### Visual 2 — SharePoint Agent Context Model
-
-Site Context → Site Content → Metadata → Permissions → Agent Response 
-
-### Visual 3 — Optimization Framework
-
-Grounding Strategy → Permissions → Prompt Design → Governance → Monitoring 
-
 ## References
 
 <https://spknowledge.com/2026/01/05/creating-and-managing-sharepoint-agents-in-copilot-studio/> 
