Fixing PR Review issues

Author: Randall-Knapp

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

@@ -35,6 +35,6 @@ You'll be introduced to a unified process map that links CAF's strategic and ope
 
 You'll learn how to design operating models that align with enterprise landing zones, data estates, and security frameworks.
 
-**Azure enterprise landing zones** are pre-configured, secure, and scalable multi-account cloud environments designed to provide a foundational setup for deploying workloads. For more information, see [/azure/cloud-adoption-framework/ready/landing-zone/](/azure/cloud-adoption-framework/ready/landing-zone/)
+**Azure enterprise landing zones** are pre-configured, secure, and scalable multi-account cloud environments designed to provide a foundational setup for deploying workloads. For more information, see [Azure enterprise landing zones](/azure/cloud-adoption-framework/ready/landing-zone/)
 
 **Azure data estates** are the comprehensive, integrated ecosystem of an organization's data assets, spanning on-premises, cloud, and hybrid environments, managed, secured, and analyzed using Microsoft Azure tools.

learn-pr/wwl/design-overall-ai-strategy-business-solutions/includes/10-provide-guidelines-creating-prompt-library.md

@@ -70,7 +70,7 @@ These principles form the foundation of every prompt in the library.
 
 Microsoft recommends structured patterns that improve predictability and accuracy.
 
-### Pattern 1 — Instruction + Context + Output
+### Pattern 1 — Instruction + context + output
 
 **Instruction:** What the model must do
 
@@ -210,6 +210,6 @@ Prompts should be:
 
 ## References
 
-- Write effective prompts for Microsoft Copilot. [/azure/copilot/write-effective-prompts](/azure/copilot/write-effective-prompts)
+- [Write effective prompts for Microsoft Copilot](/azure/copilot/write-effective-prompts)
 
-- Microsoft Copilot example prompts. [/azure/copilot/example-prompts](/azure/copilot/example-prompts)
+- [Microsoft Copilot example prompts](/azure/copilot/example-prompts)

learn-pr/wwl/design-overall-ai-strategy-business-solutions/includes/11-develop-use-cases-customized-small-language-models-solution.md

@@ -14,7 +14,7 @@ Customized SLMs allow organizations to:
 
 - Enable offline or near-edge operation for compliance or performance
 
-SLMs have the advantage with specific factors such as cost, latency, and control. But it's a common misconception that they're always safer than LLMs and always reduce hallucinations. It's important as an architect to determine when an SLM will make more sense than a large model and considerations such as risks of over-using SLMs in an organization. 
+SLMs have the advantage with specific factors such as cost, latency, and control. But it's a common misconception that they're always safer than LLMs and always reduce incorrect information. It's important as an architect to determine when an SLM will make more sense than a large model and considerations such as risks of over-using SLMs in an organization. 
 
 ## Understanding customized small language models
 
@@ -24,7 +24,7 @@ Customized SLMs can be built by:
 
 - **Behavior tuning** - Controlling style, reasoning depth, safety behavior, or operational constraints
 
-- **Task optimization** - Specializing the model for retrieval, classification, summarization, planning, or tooluse patterns
+- **Task optimization** - Specializing the model for retrieval, classification, summarization, planning, or tool-use patterns
 
 SLMs provide value because they deliver high performance while maintaining small memory footprints and low latency. They excel where **large models are too costly or unnecessary**, such as focused customer workflows, decision-support tasks, or embedded product AI features. 
 
@@ -44,7 +44,7 @@ Examples:
 
 - Manufacturing troubleshooting playbooks
 
-SLMs minimize hallucinations by constraining model behavior around enterprisevalidated data.
+SLMs minimize incorrect information by constraining model behavior around enterprise-validated data.
 
 ### Operationally constrained environments
 
@@ -58,7 +58,7 @@ When latency, cost, or compute footprint matters:
 
 - Scenarios with intermittent or restricted connectivity
 
-SLMs reduce memory footprint significantly and ensure inference remains costpredictable.
+SLMs reduce memory footprint significantly and ensure inference remains cost-predictable.
 
 ### Enterprise security & safety requirements
 
@@ -112,7 +112,7 @@ It's important to keep common pitfalls and risks in mind when identifying whethe
 
 - Underestimating data curation and evaluation effort
 
-- Treating SLMs as a silver bullet for hallucinations
+- Treating SLMs as a silver bullet for incorrect information
 
 - Using SLMs for broad, creative reasoning tasks better suited to LLMs
 
@@ -178,8 +178,8 @@ When evaluating an SLM, architects can measure its success through specific metr
 
 **References (URLs you provided)**
 
-- <https://arxiv.org/pdf/2405.20347>
+- [Small Language Models for Application Interactions: A Case Study](https://arxiv.org/pdf/2405.20347)
 
-- <https://mljourney.com/small-language-model-use-cases-applications-in-2025-and-beyond/>
+- [Small language model use cases and applications in 2025 and beyond](https://mljourney.com/small-language-model-use-cases-applications-in-2025-and-beyond/)
 
-- <https://azure.microsoft.com/blog/introducing-phi-3-redefining-whats-possible-with-slms/>
+- [Introducing Phi-3 — redefining what's possible with SLMs](https://azure.microsoft.com/blog/introducing-phi-3-redefining-whats-possible-with-slms/)

learn-pr/wwl/design-overall-ai-strategy-business-solutions/includes/12-provide-prompt-engineering-guidelines-techniques.md

@@ -20,7 +20,7 @@ Prompt engineering is the deliberate design of instructions that guide AI models
 
 In business environments, effective prompt engineering ensures:
 
-- **Accuracy** of content and reduced hallucinations
+- **Accuracy** of content and reduced incorrect information
 
 - **Consistency** of responses across teams and workflows
 
@@ -152,13 +152,10 @@ Asking the model to show steps or reasoning improves correctness in:
 
 Large tasks should be decomposed into smaller interactions:
 
-- Step 1: Extract
-
-- Step 2: Analyze
-
-- Step 3: Recommend
-
-- Step 4: Summarize
+1. Extract
+1. Analyze
+1. Recommend
+1. Summarize
 
 Improves quality and reduces model error propagation.
 
@@ -208,7 +205,7 @@ Avoid the following when creating prompts as best practices:
 
 - Prompts that accidentally leak sensitive data
 
-- Prompts that cause hallucinations
+- Prompts that cause incorrect information
 
 ## Visual aids (text-based charts)
 
@@ -230,15 +227,15 @@ Avoid the following when creating prompts as best practices:
 | **Level 1 - Basic** | Simple questions; no structure |
 | **Level 2 - Guided** | Clear intent + basic constraints |
 | **Level 3 - Structured** | Full pattern (instruction + context + output) |
-| **Level 4 - Optimized** | Fewshot examples, formatting rules |
+| **Level 4 - Optimized** | Few-shot examples, formatting rules |
 | **Level 5 - Enterprise** | Reusable templates, version control, governed library |
 
 ## References
 
-- Prompt engineering concepts. [/concepts/prompt-engineering](/concepts/prompt-engineering)
+- [Prompt engineering concepts](/concepts/prompt-engineering)
 
-- Generative AI prompt engineering labs. [/training/collections/generative-ai-prompt-engineering-labs/](/training/collections/generative-ai-prompt-engineering-labs/)
+- [Generative AI prompt engineering labs](/training/collections/generative-ai-prompt-engineering-labs/)
 
-- Copilot Studio prompt tool. [/microsoft-copilot-studio/prompt-tool](/microsoft-copilot-studio/prompt-tool)
+- [Copilot Studio prompt tool](/microsoft-copilot-studio/prompt-tool)
 
-- Effective prompts for generative AI. [/training/modules/effective-prompts-generative-ai](/training/modules/effective-prompts-generative-ai)
+- [Effective prompts for generative AI](/training/modules/effective-prompts-generative-ai)

learn-pr/wwl/design-overall-ai-strategy-business-solutions/includes/13-identify-key-business-user-roles-ai-workloads.md

@@ -36,7 +36,7 @@ Coordinates AI strategy, ensures governance, and orchestrates organizational ali
 
 - Develop enterprise AI maturity and workflow standards
 
-A lack of an Center of Excellence lead can lead to organizational impacts such as a lack of technological oversight, failure to adhere to a unified architectural strategy, or a breakdown in one or more of the key AI Responsibility pillars such as transparency. 
+A lack of a Center of Excellence lead can lead to organizational impacts such as a lack of technological oversight, failure to adhere to a unified architectural strategy, or a breakdown in one or more of the key AI Responsibility pillars such as transparency.
 
 ### Product owner for AI workloads
 
@@ -68,7 +68,7 @@ Provides domain expertise required for model grounding, evaluation, and performa
 
 - Identify operational pain points suitable for AI augmentation
 
-A lack of qualified business domain specialists can lead to a failure for AI workloads to perform reliably and to specification through issues such as hallucinations risks.
+A lack of qualified business domain specialists can lead to a failure for AI workloads to perform reliably and to specification through issues such as incorrect information risks.
 
 ### Data owner / data steward
 
@@ -166,8 +166,8 @@ Additional roles not listed may be discovered such as the below for example:
 
 ## References
 
-- Scale AI — organize for AI success. [/training/modules/scale-ai/3-organize-ai-success](/training/modules/scale-ai/3-organize-ai-success)
+- [Scale AI — organize for AI success](/training/modules/scale-ai/3-organize-ai-success)
 
-- Scale AI transformation with Azure Essentials — AI Center of Excellence guidance. [https://azure.microsoft.com/blog/scale-ai-transformation-with-azure-essentials-ai-center-of-excellence-guidance/](https://azure.microsoft.com/blog/scale-ai-transformation-with-azure-essentials-ai-center-of-excellence-guidance/)
+- [Scale AI transformation with Azure Essentials — AI Center of Excellence guidance](https://azure.microsoft.com/blog/scale-ai-transformation-with-azure-essentials-ai-center-of-excellence-guidance/)
 
-- Introduction to AI Center of Excellence — determining organizational roles and responsibilities. [/training/modules/intro-ai-center-excellence/4-determining-organizational-roles-responsibilities](/training/modules/intro-ai-center-excellence/4-determining-organizational-roles-responsibilities)
+- [Introduction to AI Center of Excellence — determining organizational roles and responsibilities](/training/modules/intro-ai-center-excellence/4-determining-organizational-roles-responsibilities)

learn-pr/wwl/design-overall-ai-strategy-business-solutions/includes/14-evaluate-regional-local-ai-data-regulation-compliance-requirements.md

@@ -56,12 +56,10 @@ Microsoft's AI CoE guidance emphasizes that regulatory alignment is a foundation
 
 ## Regulatory domains solution architects must evaluate
 
-### A. Data protection & privacy regulations
+### Data protection & privacy regulations
 
 Examples include:
 
-- GDPR (EU)
-
 - CCPA/CPRA (California)
 
 - Colorado Privacy Act
@@ -82,7 +80,7 @@ Key considerations:
 
 - Cross-border data transfer
 
-### B. AI-specific regulations
+### AI-specific regulations
 
 Many regions are introducing AI-focused laws.
 
@@ -108,7 +106,7 @@ Key considerations:
 
 - Safety and misuse prevention
 
-### C. Industry-specific regulations
+### Industry-specific regulations
 
 Depending on the workload:
 
@@ -130,7 +128,7 @@ Key considerations:
 
 - Access controls
 
-### D. Local jurisdiction requirements
+### Local jurisdiction requirements
 
 Cities, states, and provinces may impose:
 
@@ -146,15 +144,15 @@ Cities, states, and provinces may impose:
 
 Based on Microsoft's AI CoE guidance, the CoE must:
 
-#### A. Establish governance frameworks
+#### Establish governance frameworks
 
 - Define enterprise AI standards
 
 - Document compliance guardrails
 
 - Create risk assessment workflows
 
-#### B. Evaluate AI workloads for regulatory impact
+#### Evaluate AI workloads for regulatory impact
 
 - Classify risk level
 
@@ -164,7 +162,7 @@ Based on Microsoft's AI CoE guidance, the CoE must:
 
 - Validate model evaluation requirements
 
-#### C. Enable cross-functional collaboration
+#### Enable cross-functional collaboration
 
 - Legal
 
@@ -176,7 +174,7 @@ Based on Microsoft's AI CoE guidance, the CoE must:
 
 - Business domain teams
 
-#### D. Provide templates and tools
+#### Provide templates and tools
 
 - Regulatory checklists
 
@@ -264,22 +262,12 @@ The AI CoE should maintain:
 
 - Approval workflows
 
-## Professional visuals (text-based)
-
-### Visual 1 — Regulatory evaluation flow
-
-Identify Jurisdictions ↓ Identify Regulations ↓ Classify AI Risk ↓ Assess Data Requirements ↓ Evaluate AI Obligations ↓ Map to Microsoft Controls ↓ Document & Approve 
-
-### Visual 2 — AI CoE compliance responsibilities
-
-Governance Standards Risk Assessment Data Protection Model Evaluation Responsible AI Audit & Monitoring 
-
 ## References
 
-- Implementing AI data residency and sovereignty strategies on Microsoft Azure. [https://just4cloud.com/implementing-ai-data-residency-and-sovereignty-strategies-on-microsoft-azure/](https://just4cloud.com/implementing-ai-data-residency-and-sovereignty-strategies-on-microsoft-azure/)
+- [Implementing AI data residency and sovereignty strategies on Microsoft Azure](https://just4cloud.com/implementing-ai-data-residency-and-sovereignty-strategies-on-microsoft-azure/)
 
-- Security for AI — governance. [/security/security-for-ai/govern](/security/security-for-ai/govern)
+- [Security for AI — governance](/security/security-for-ai/govern)
 
-- Know your boundaries — navigating data sovereignty and residency in Microsoft 365. [https://www.cloudessentials.com/blog/know-your-boundaries-navigating-data-sovereignty-and-residency-in-microsoft-365/](https://www.cloudessentials.com/blog/know-your-boundaries-navigating-data-sovereignty-and-residency-in-microsoft-365/)
+- [Know your boundaries — navigating data sovereignty and residency in Microsoft 365](https://www.cloudessentials.com/blog/know-your-boundaries-navigating-data-sovereignty-and-residency-in-microsoft-365/)
 
-- Data residency and compliance in the Microsoft Cloud — Microsoft 365 governance guide. [https://dellenny.com/data-residency-and-compliance-in-the-microsoft-cloud-microsoft-365-governance-guide/](https://dellenny.com/data-residency-and-compliance-in-the-microsoft-cloud-microsoft-365-governance-guide/)
+- [Data residency and compliance in the Microsoft Cloud — Microsoft 365 governance guide](https://dellenny.com/data-residency-and-compliance-in-the-microsoft-cloud-microsoft-365-governance-guide/)

learn-pr/wwl/design-overall-ai-strategy-business-solutions/includes/15-include-elements-microsoft-ai-center-excellence.md

@@ -182,8 +182,8 @@ When a CoE is missing or inadequate within an organization, the following can oc
 
 ## References
 
-- Introduction to generative AI Center of Excellence. [/training/modules/intro-ai-center-excellence/1-introduction-generative-ai-center-excellence](/training/modules/intro-ai-center-excellence/1-introduction-generative-ai-center-excellence)
+- [Introduction to generative AI Center of Excellence](/training/modules/intro-ai-center-excellence/1-introduction-generative-ai-center-excellence)
 
-- Cloud Adoption Framework — AI Center of Excellence (GitHub). [https://github.com/MicrosoftDocs/cloud-adoption-framework/blob/main/docs/scenarios/ai/center-of-excellence.md](https://github.com/MicrosoftDocs/cloud-adoption-framework/blob/main/docs/scenarios/ai/center-of-excellence.md)
+- [Cloud Adoption Framework — AI Center of Excellence (GitHub)](https://github.com/MicrosoftDocs/cloud-adoption-framework/blob/main/docs/scenarios/ai/center-of-excellence.md)
 
-- Azure Cloud Adoption Framework. [/azure/cloud-adoption-framework/](/azure/cloud-adoption-framework/)
+- [Azure Cloud Adoption Framework](/azure/cloud-adoption-framework/)

learn-pr/wwl/design-overall-ai-strategy-business-solutions/includes/16-design-ai-solutions-use-multiple-dynamics-365-apps.md

@@ -102,13 +102,13 @@ Intent-driven architectures allow AI to determine the user's goal and route the
 
 ### Core principles
 
-**Intent parsing**: Determine if the ask belongs to Sales, Service, or another workload
+- **Intent parsing**: Determine if the ask belongs to Sales, Service, or another workload.
 
-**Context routing**: Map the intent to the correct app and entity
+- **Context routing**: Map the intent to the correct app and entity.
 
-**Adaptive actions**: Use business rules to adjust next steps dynamically
+- **Adaptive actions**: Use business rules to adjust next steps dynamically.
 
-**Event-based triggers**: Use Dataverse events while minimizing point-to-point integrations
+- **Event-based triggers**: Use Dataverse events while minimizing point-to-point integrations.
 
 ### Architectural benefits
 
@@ -154,6 +154,6 @@ Intent-driven architectures allow AI to determine the user's goal and route the
 
 ## References
 
-- Bridging AI and Dynamics — a scalable architecture for intent-driven applications. [https://dev.to/deep_sharma/bridging-ai-and-dynamics-a-scalable-architecture-for-intent-driven-applications-30jp](https://dev.to/deep_sharma/bridging-ai-and-dynamics-a-scalable-architecture-for-intent-driven-applications-30jp)
+- [Bridging AI and Dynamics — a scalable architecture for intent-driven applications](https://dev.to/deep_sharma/bridging-ai-and-dynamics-a-scalable-architecture-for-intent-driven-applications-30jp)
 
-- Dynamics 365 Customer Service — enable customers to create multisession apps (2025 wave 1). [/dynamics365/release-plan/2025wave1/service/dynamics365-customer-service/enable-customers-create-multisession-apps](/dynamics365/release-plan/2025wave1/service/dynamics365-customer-service/enable-customers-create-multisession-apps)
+- [Dynamics 365 Customer Service — enable customers to create multisession apps (2025 wave 1)](/dynamics365/release-plan/2025wave1/service/dynamics365-customer-service/enable-customers-create-multisession-apps)

learn-pr/wwl/design-overall-ai-strategy-business-solutions/includes/17-design-user-prompt-training-ai-solution-adoption.md

@@ -112,7 +112,7 @@ Your training program should teach users:
 
 - Context improves accuracy
 
-- Constraints reduce hallucinations
+- Constraints reduce incorrect information
 
 ### Prompt patterns users should learn
 
@@ -238,8 +238,8 @@ Examples:
 
 ## References
 
-- Empower educators to explore the potential of AI — AI tools and accessibility. [/training/modules/empower-educators-explore-potential-artificial-intelligence/ai-tools-educators-accessibility](/training/modules/empower-educators-explore-potential-artificial-intelligence/ai-tools-educators-accessibility)
+- [Empower educators to explore the potential of AI — AI tools and accessibility](/training/modules/empower-educators-explore-potential-artificial-intelligence/ai-tools-educators-accessibility)
 
-- Leverage AI tools — drive transformation with Azure platforms. [/training/modules/leverage-ai-tools/6-drive-transformation-azure-platforms](/training/modules/leverage-ai-tools/6-drive-transformation-azure-platforms)
+- [Leverage AI tools — drive transformation with Azure platforms](/training/modules/leverage-ai-tools/6-drive-transformation-azure-platforms)
 
-- Create business value with AI — AI governance. [/training/modules/create-business-value/6-ai-governance](/training/modules/create-business-value/6-ai-governance)
+- [Create business value with AI — AI governance](/training/modules/create-business-value/6-ai-governance)