AB-100T00: Architecting agentic AI business solutions

Course structure

Module 1: Introduction to agentic AI business solutions

• 1.1.1 Introduction 
• 1.1.2 Drive AI transformation with architect strategies 
• 1.1.3 Explore Microsoft AI technologies for business 
• 1.1.4 Identify Microsoft AI technologies for business solutions 
• 1.1.5 Identify out-of-box Microsoft AI agent resources for business solutions 
• 1.1.6 Identify out-of-box Microsoft AI agents for business 
• 1.1.7 Summary 

Module 2: Analyze requirements for AI-powered business solutions

• 1.2.1 Introduction 
• 1.2.2 Assess the use of agents in task automation, data analytics, and decision-making 
• 1.2.3 Review data for grounding accuracy, relevance, timeliness, cleanliness, and availability 
• 1.2.4 Organize business solution data for AI systems 
• 1.2.5 Summary 

Module 3: Design overall AI strategy for business solutions

• 1.3.1 Introduction 
• 1.3.2 Implement AI adoption process with Azure 
• 1.3.3 Design AI agents for business solutions 
• 1.3.4 Design a multi-agent solution 
• 1.3.5 Develop use cases for prebuilt Microsoft 365 Copilot agents 
• 1.3.6 Define solution rules and constraints for AI components 
• 1.3.7 Determine generative AI knowledge sources for agents built in Copilot Studio 
• 1.3.8 Determine when to build custom agents or extend Microsoft 365 Copilot 
• 1.3.9 Determine when custom AI models should be created 
• 1.3.10 Provide guidelines for creating a prompt library 
• 1.3.11 Develop use cases for customized small language models 
• 1.3.12 Provide prompt engineering guidelines and techniques 
• 1.3.13 Identify key business user roles for AI workloads 
• 1.3.14 Evaluate regional and local AI data regulation compliance requirements 
• 1.3.15 Include elements in a Microsoft AI Center of Excellence 
• 1.3.16 Design AI solutions using multiple Dynamics 365 apps 
• 1.3.17 Design user prompt training for AI solution adoption 
• 1.3.18 Summary 

Module 4: Evaluate costs and benefits of AI solutions

• 1.4.1 Introduction 
• 1.4.2 Evaluate ROI criteria for AI-powered solutions 
• 1.4.3 Create ROI analysis for a proposed AI solution 
• 1.4.4 Analyze whether to build, buy, or extend AI components 
• 1.4.5 Implement a model router to intelligently route requests to the most suitable model 
• 1.4.6 Summary 

Module 5: Design AI agents for business solutions

• 1.5.1 Introduction 
• 1.5.2 Define core tenets of responsible AI guidelines for AI business solutions 
• 1.5.3 Design business terms for Copilot in Dynamics 365 Customer Service 
• 1.5.4 Design customizations for Copilot in Dynamics 365 apps 
• 1.5.5 Design connectors for Copilot in Dynamics 365 Sales 
• 1.5.6 Design AI agents for Dynamics 365 Contact Center 
• 1.5.7 Design task agents in Microsoft Copilot Studio 
• 1.5.8 Design autonomous agents in Copilot Studio 
• 1.5.9 Design prompt-driven agents using Copilot Studio 
• 1.5.10 Propose Foundry tools given a requirement 
• 1.5.11 Propose code first generative pages and agent feed applications 
• 1.5.12 Design topics for Copilot Studio, including fallback 
• 1.5.13 Design data processing workflows for grounded AI 
• 1.5.14 Design business processes with AI in Power Apps canvas apps 
• 1.5.15 Apply the Microsoft Power Platform Well-Architected Framework to intelligent application workloads 
• 1.5.16 Determine the use of standard natural language processing 
• 1.5.17 Design agents and agent flows with Copilot Studio 
• 1.5.18 Design prompt actions in Copilot Studio 
• 1.5.19 Define success criteria and adoption goals for AI business solutions 
• 1.5.20 Summarize AI agent design for business solutions 

Module 6: Design extensibility of AI solutions

• 1.6.1 Introduction 
• 1.6.2 Design AI solutions with custom models in Microsoft Foundry 
• 1.6.3 Design agents in Microsoft 365 Copilot 
• 1.6.4 Design extensible agents in Microsoft Copilot Studio 
• 1.6.5 Design extensible agents using MCP in Copilot Studio 
• 1.6.6 Design agents to automate tasks in apps and websites with Computer Use in Copilot Studio 
• 1.6.7 Design agent behaviors in Copilot Studio 
• 1.6.8 Optimize solution design for agents in Microsoft 365 
• 1.6.9 Summary 

Module 7: Orchestrate configuration of prebuilt agents and apps

• 1.7.1 Introduction 
• 1.7.2 Design AI solutions for Dynamics 365 Customer Service 
• 1.7.3 Propose Microsoft 365 agents for business scenarios 
• 1.7.4 Orchestrate and configure Microsoft 365 Copilot for sales and service 
• 1.7.5 Propose Microsoft Power Platform AI features 
• 1.7.6 Design interoperable agent experiences for Finance and Operations 
• 1.7.7 Recommend process knowledge sources for in-app help in Dynamics 365 
• 1.7.8 Orchestrate AI features in Dynamics 365 Finance and Supply Chain 
• 1.7.9 Summary 

Module 8: Monitor, analyze, and tune AI agents

• 1.8.1 Introduction 
• 1.8.2 Recommend process tools for monitoring agents 
• 1.8.3 Analyze backlog and user feedback for AI agent usage 
• 1.8.4 Apply AI-based tools to analyze, identify issues, and perform tuning 
• 1.8.5 Monitor AI agent performance metrics 
• 1.8.6 Interpret telemetry data to tune AI performance 
• 1.8.7 Ensure reliable AI agent operations 

Module 9: Manage testing AI-powered business solutions

• 1.9.1 Introduction 
• 1.9.2 Recommend process metrics for testing AI agents 
• 1.9.3 Create validation criteria for custom AI models 
• 1.9.4 Validate effective Copilot prompt best practices 
• 1.9.5 Design end-to-end test scenarios for AI solutions using multiple Dynamics 365 apps 
• 1.9.6 Build a strategy for creating test cases using Copilot 
• 1.9.7 Summary 

Module 10: Design ALM process for AI-powered business solutions

• 1.10.1 Introduction 
• 1.10.2 Design an ALM process for data used in AI models and agents 
• 1.10.3 Design an ALM process for Copilot Studio agents, connectors, and actions 
• 1.10.4 Design ALM processes for Microsoft Foundry agents 
• 1.10.5 Design an ALM process for custom AI models 
• 1.10.6 Design an ALM process for AI in Dynamics 365 Finance and Supply Chain 
• 1.10.7 Design ALM processes for AI in Dynamics 365 apps 
• 1.10.8 Summary 

Module 11: Design responsible AI security, governance, risk management, and compliance

• 1.11.1 Introduction 
• 1.11.2 Design security agents for Microsoft clouds 
• 1.11.3 Design governance models for AI agents 
• 1.11.4 Design model security for responsible AI 
• 1.11.5 Analyze AI vulnerabilities and mitigations for prompt manipulation 
• 1.11.6 Review solution adherence to Responsible AI principles 
• 1.11.7 Validate data residency and movement compliance 
• 1.11.8 Design access controls for grounding data and model tuning 
• 1.11.9 Design audit trails for changes to models and data 
• 1.11.10 Summary