Fixing acrolinx

Author: Randall-Knapp

learn-pr/wwl/analyze-requirements-for-ai-powered-business-solutions/5-knowledge-check.yml

@@ -11,20 +11,20 @@ metadata:
   ai-usage: ai-assisted
   module_assessment: false
 durationInMinutes: 3
-content: "Choose the best response for each of the following questions."
+content: "Choose the best response for each of the questions."
 quiz:
   questions:
-  - content: "Which of the following is a primary way AI agents enhance productivity in business workflows?"
+  - content: "Which of the following answers is a primary way AI agents enhance productivity in business workflows?"
     choices:
     - content: "Replacing all manual processes with fully autonomous systems"
       isCorrect: false
-      explanation: "Incorrect. While AI can automate certain tasks, it does not replace all manual processes with fully autonomous systems."
+      explanation: "Incorrect. While AI can automate certain tasks, it doesn't replace all manual processes with fully autonomous systems."
     - content: "Drafting content and summarizing information using generative AI"
       isCorrect: true
       explanation: "Correct. Generative AI accelerates productivity by drafting content, summarizing information, and enabling natural language interaction with data and systems. This allows employees to work faster and more efficiently, directly enhancing productivity in business workflows."
     - content: "Eliminating the need for employee training"
       isCorrect: false
-      explanation: "Incorrect. AI does not eliminate the need for employee training; rather, it complements employee efforts."
+      explanation: "Incorrect. AI doesn't eliminate the need for employee training; rather, it complements employee efforts."
     - content: "Removing the requirement for business context in automation"
       isCorrect: false
       explanation: "Incorrect. Business context is essential for effective automation and AI implementation."
@@ -35,35 +35,35 @@ quiz:
       explanation: "Incorrect. Cleanliness refers to the accuracy and quality of data, not its alignment with the business scenario."
     - content: "Availability"
       isCorrect: false
-      explanation: "Incorrect. Availability ensures data is accessible but does not guarantee it matches the intended business scenario."
+      explanation: "Incorrect. Availability ensures data is accessible but doesn't guarantee it matches the intended business scenario."
     - content: "Relevance"
       isCorrect: true
       explanation: "Correct. Relevance ensures that grounding data matches the intended use case of the agent. This dimension is critical for surfacing information that is contextually appropriate for the user's scenario, workflow, or business domain."
     - content: "Timeliness"
       isCorrect: false
-      explanation: "Incorrect. Timeliness ensures data is up-to-date but does not address its alignment with the business scenario."
+      explanation: "Incorrect. Timeliness ensures data is up-to-date but doesn't address its alignment with the business scenario."
   - content: "What is the role of semantic indexing in Microsoft Copilot solutions?"
     choices:
     - content: "Customizing user interfaces"
       isCorrect: false
-      explanation: "Incorrect. Semantic indexing is not related to customizing user interfaces."
+      explanation: "Incorrect. Semantic indexing isn't related to customizing user interfaces."
     - content: "Mapping enterprise content for precise data retrieval"
       isCorrect: true
       explanation: "Correct. Semantic indexing is used to map enterprise content across Microsoft Graph into rich lexical and semantic representations. This enables AI agents to retrieve contextually precise and permissioned information, supporting trustworthy outputs."
     - content: "Managing email distribution lists"
       isCorrect: false
-      explanation: "Incorrect. Semantic indexing does not involve managing email distribution lists."
+      explanation: "Incorrect. Semantic indexing doesn't involve managing email distribution lists."
     - content: "Automating financial transactions"
       isCorrect: false
-      explanation: "Incorrect. Semantic indexing is not related to automating financial transactions."
+      explanation: "Incorrect. Semantic indexing isn't related to automating financial transactions."
   - content: "Why is it important to centralize and structure business solution data before deploying AI agents?"
     choices:
     - content: "To reduce the number of employees needed"
       isCorrect: false
-      explanation: "Incorrect. Centralizing and structuring data is not aimed at reducing the workforce."
+      explanation: "Incorrect. Centralizing and structuring data isn't aimed at reducing the workforce."
     - content: "To ensure AI systems can access high-quality, reliable data"
       isCorrect: true
-      explanation: "Correct. AI systems require high-quality, structured, and accessible data. Centralizing and structuring data ensures it is reliable and ready for AI processing."
+      explanation: "Correct. AI systems require high-quality, structured, and accessible data. Centralizing and structuring data ensures it's reliable and ready for AI processing."
     - content: "To allow data to remain in scattered silos"
       isCorrect: false
       explanation: "Incorrect. Scattered silos hinder AI systems from accessing and processing data effectively."

learn-pr/wwl/analyze-requirements-for-ai-powered-business-solutions/includes/1-introduction.md

@@ -6,6 +6,6 @@ Generative AI further accelerates productivity by drafting content, summarizing
 
 To ensure reliable and responsible AI adoption, it is essential to understand how agents interact with business data. High-quality, well-organized, and accessible data is the foundation for effective AI solutions. Concepts such as grounding—where AI agents respond using trusted, domain-specific organizational data—are critical to minimizing errors and maintaining security and compliance. Technologies like semantic indexing and the Copilot Retrieval API ensure that AI agents retrieve contextually precise and permissioned information, supporting trustworthy outputs.
 
-This module also emphasizes the importance of organizing business solution data for AI readiness. Leveraging platforms such as Azure, Microsoft databases, and modern data architecture patterns enables organizations to centralize, structure, and govern their data, making it discoverable and usable for a wide range of AI systems, including Copilot, autonomous agents, and custom AI applications.
+This module also emphasizes the importance of organizing business solution data for AI readiness. Using platforms such as Azure, Microsoft databases, and modern data architecture patterns enables organizations to centralize, structure, and govern their data, making it discoverable and usable for a wide range of AI systems, including Copilot, autonomous agents, and custom AI applications.
 
-Throughout this module, learners will explore best practices for implementing AI agents, ensuring data quality across accuracy, relevance, timeliness, cleanliness, and availability, and structuring enterprise data for scalable AI consumption. By mastering these principles, organizations can unlock measurable value, drive transformation, and support responsible decision-making with AI-powered solutions.
+Throughout this module, learners will explore best practices for implementing AI agents, ensuring data quality across accuracy, relevance, timeliness, cleanliness, and availability, and structuring enterprise data for scalable AI consumption. When organizations apply these principles, they unlock measurable value, drive transformation, and support responsible decision-making with AI-powered solutions.

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

@@ -94,6 +94,6 @@ These principles reinforce reliable, secure AI adoption at scale.
 
 Use these links as the primary sources for this unit:
 
-**Explore Copilot Experiences**<br>[Explore Copilot Experiences](/training/modules/business-value-microsoft-copilot-solutions/3-explore-copilot-experiences) 
+- **Explore Copilot Experiences**[Explore Copilot Experiences](/training/modules/business-value-microsoft-copilot-solutions/3-explore-copilot-experiences) 
 
-**Unlock Productivity with Generative AI - Microsoft Learn**<br>[Unlock Productivity with Generative AI](/training/modules/generative-ai-productivity/)
+- **Unlock Productivity with Generative AI - Microsoft Learn**[Unlock Productivity with Generative AI](/training/modules/generative-ai-productivity/)

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

@@ -26,7 +26,9 @@ Organizing business solution data is not only a technical requirement but a busi
 Retrieval-Augmented Generation (REG) is an architecture that separates prototypes from trustworthy systems. A RAG pipeline is the system that performs all the steps required to make RAG work in a production environment, handling the data ingestion, streaming, cleaning, chunking, embedding, indexing, retrieval, prompt assembly, orchestration, and monitoring that allow an LLM to use retrieved context when generating an answer There are several advantages of leveraging RAG pipelines:
 
 - Empowering LLM solutions with real-time data access
+
 - Preserving data privacy
+
 - Mitigating LLM hallucinations
 
 This unit explains how to organize your business data to become **usable, discoverable, secure, and optimized for AI consumption across the organization**.
@@ -146,8 +148,8 @@ Timeliness is essential—AI systems must reference the latest information.
 
 Use these links for this unit:
 
-[Drive Transformation with Azure Platforms](/training/modules/leverage-ai-tools/6-drive-transformation-azure-platforms)
+- [Drive Transformation with Azure Platforms](/training/modules/leverage-ai-tools/6-drive-transformation-azure-platforms)
 
-[Building intelligent AI apps with Microsoft databases](https://techcommunity.microsoft.com/blog/azuredatablog/building-intelligent-ai-apps-with-microsoft-databases/4413833)
+- [Building intelligent AI apps with Microsoft databases](https://techcommunity.microsoft.com/blog/azuredatablog/building-intelligent-ai-apps-with-microsoft-databases/4413833)
 
-[Data architecture for AI agents](/azure/cloud-adoption-framework/ai-agents/data-architecture-plan) 
+- [Data architecture for AI agents](/azure/cloud-adoption-framework/ai-agents/data-architecture-plan) 

learn-pr/wwl/analyze-requirements-for-ai-powered-business-solutions/includes/6-summary.md

@@ -4,42 +4,42 @@ This module provides foundational knowledge for analyzing, designing, and implem
 
 _AI Agents in Business Solutions:_
 
-AI agents automate routine tasks, deliver data-driven insights, and support decision-making by integrating enterprise context with generative AI.
+- AI agents automate routine tasks, deliver data-driven insights, and support decision-making by integrating enterprise context with generative AI.
 
-Tools like Microsoft Copilot enhance productivity in Word, Outlook, Teams, and Dynamics 365 by drafting content, summarizing information, and enabling natural language interactions.
+- Tools like Microsoft Copilot enhance productivity in Word, Outlook, Teams, and Dynamics 365 by drafting content, summarizing information, and enabling natural language interactions.
 
 _Generative AI Capabilities:_
 
-Generative AI accelerates productivity by creating original content (text, images, videos, audio, code) and supporting natural language queries.
+- Generative AI accelerates productivity by creating original content (text, images, videos, audio, code) and supporting natural language queries.
 
-It enables employees to work faster and with greater confidence, enhancing creativity and efficiency.
+- It enables employees to work faster and with greater confidence, enhancing creativity and efficiency.
 
 _Task Automation, Analytics, and Decision-Making:_
 
-AI agents streamline communication, documentation, process automation, and knowledge retrieval.
+- AI agents streamline communication, documentation, process automation, and knowledge retrieval.
 
-In data analytics, agents summarize complex datasets, identify trends, generate visualizations, and suggest actions.
+- In data analytics, agents summarize complex datasets, identify trends, generate visualizations, and suggest actions.
 
-For decision-making, they provide scenario recommendations, risk identification, and context-driven insights.
+- For decision-making, they provide scenario recommendations, risk identification, and context-driven insights.
 
 _Grounding Data for Reliable AI:_
 
-Grounding ensures AI agents use trusted, domain-specific data, increasing accuracy and reducing hallucinations (confidently incorrect answers).
+- Grounding ensures AI agents use trusted, domain-specific data, increasing accuracy and reducing hallucinations (confidently incorrect answers).
 
 Five dimensions of grounding data quality:
 
-- Accuracy: Data is correct and verified.
-- Relevance: Data matches the intended use case.
-- Timeliness: Data is current and up to date.
-- Cleanliness: Data is structured and free from noise.
-- Availability: Data is accessible and indexable per user permissions.
+1. Accuracy: Data is correct and verified.
+2. Relevance: Data matches the intended use case.
+3. Timeliness: Data is current and up to date.
+4. Cleanliness: Data is structured and free from noise.
+5. Availability: Data is accessible and indexable per user permissions.
 
 Technologies like semantic indexing and the Copilot Retrieval API support precise, permissioned data retrieval.
 
 _Organizing Business Solution Data:_
 
-Well-organized, centralized, and structured data is essential for AI readiness and high-quality agent outputs.
+- Well-organized, centralized, and structured data is essential for AI readiness and high-quality agent outputs.
 
-Key architectural components include Azure platforms, Microsoft databases, semantic indexing, and governance tools (e.g., Microsoft Purview).
+- Key architectural components include Azure platforms, Microsoft databases, semantic indexing, and governance tools (e.g., Microsoft Purview).
 
-Retrieval-Augmented Generation (RAG) pipelines empower AI systems with real-time, trustworthy data while preserving privacy and mitigating
+- Retrieval-Augmented Generation (RAG) pipelines empower AI systems with real-time, trustworthy data while preserving privacy and mitigating

learn-pr/wwl/analyze-requirements-for-ai-powered-business-solutions/index.yml

@@ -25,17 +25,13 @@ iconUrl: /learn/achievements/generic-badge.svg
 levels:
 - advanced
 roles:
-- database-administrator
-- developer
-- administrator
 - solution-architect
-- technology-manager
 products:
 - microsoft-365-copilot
-- m365
 - microsoft-365-copilot-chat
 - power-platform
 - microsoft-copilot-studio
+- dynamics-365
 subjects:
 - generative-ai
 - data-analytics