Featured resource
2026 Tech Forecast
2026 Tech Forecast

1,500+ tech insiders, business leaders, and Pluralsight Authors share their predictions on what’s shifting fastest and how to stay ahead.

Download the forecast

AB-620: Designing and Building Integrated AI Agent Solutions in Copilot Studio

Course Summary

The AB-620: Designing and Building Integrated AI Agent Solutions in Copilot Studio course is designed to prepare professional developers and advanced builders to design, build, and integrate custom agent solutions for enterprise-grade scenarios in Microsoft Copilot Studio. The course begins by covering how to plan an agent solution, including integration strategy, identity, channels, responsible AI, and governance considerations. Participants then learn to create and monitor agent flows, configure topics, and connect agents to enterprise knowledge sources, tools, and multi-agent orchestration patterns. The course continues with integrating agents with Microsoft Foundry, Model Context Protocol (MCP) servers, Microsoft Fabric, and Azure AI Search. It concludes with testing agent performance and implementing application lifecycle management (ALM) for agents. This course also serves as exam preparation for Microsoft Certification Exam AB-620. 

Prequisites:

  • Experience configuring agents with knowledge sources, instructions, tools, and topics in Microsoft Copilot Studio
  • Intermediate knowledge of generative AI concepts, including models, orchestration, retrieval-augmented generation (RAG), Model Context Protocol (MCP), and Agent2Agent (A2A) protocol
  • Familiarity with Power Fx, Microsoft Dataverse, and Microsoft Power Platform environments and components
  • Experience with prompt engineering, REST APIs, and integration patterns
Purpose
Learn how to design, build, and integrate enterprise-grade AI agent solutions using Microsoft Copilot Studio
Audience
Developers who who build, extend, and integrate custom agents for enterprise-grade solutions
Role
Software Developer | Application Developer | Copilot Studio Architects
Skill level
Intermediate
Style
Lecture | Hands-on Activities | Labs
Duration
3 days
Related technologies
Microsoft Foundry | Power Platform | Microsoft Dataverse | Microsoft Fabric | Azure

 

Learning objectives
  • Plan and configure agent solutions, including integration, identity, channel, and responsible AI strategy
  • Create and monitor agent flows, configure topics, and implement error handling in Copilot Studio
  • Connect agents to enterprise knowledge sources, tools, and custom connectors
  • Configure multi-agent collaboration, including integration with Microsoft Foundry, Fabric data agents, and A2A protocol
  • Integrate agents with Azure services, including Azure AI Search and Application Insights monitoring
  • Evaluate agent performance and implement application lifecycle management (ALM) for agents in Copilot Studio

What you'll learn:

In this AB-620: Designing and Building Integrated AI Agent Solutions in Copilot Studio course, you'll learn:

Introduction to Designing and Building Integrated AI Agent Solutions

  • Overview of Copilot Studio's role in enterprise agent development
  • Audience profile and responsibilities of an agent developer/builder
  • Overview of the three exam skill domains and how they map to real-world solution design
  • Course logistics and hands-on lab environment setup

Plan and Configure Agent Solutions

  • Planning an agent solution
    • Planning integration with enterprise systems
    • Planning identity strategy
    • Planning channels and deployment
    • Planning responsible AI strategy
    • Evaluating security and governance considerations
    • Planning reusable agent components
    • Designing agents for internal or external audiences
  • Creating and monitoring agent flows in Copilot Studio
    • Creating an agent flow
    • Creating a human-in-the-loop agent flow
    • Configuring actions and connectors
    • Monitoring agent flows
    • Adding input and output parameters
    • Implementing error handling in agent flows
  • Configuring topics
    • Adding agent flows to a topic
    • Configuring agent response formatting
    • Adding tools to a topic
    • Configuring advanced agent responses with custom prompts
    • Configuring advanced agent responses with custom knowledge sources
    • Configuring advanced agent responses with API and Send HTTP requests
    • Configuring the generative answers node
    • Configuring adaptive cards
    • Managing variables

Integrate and Extend Agents in Copilot Studio

  • Connecting to enterprise knowledge sources
    • Connecting to Copilot connectors
    • Connecting to Microsoft Power Platform connectors
    • Connecting to Azure AI Search
  • Adding tools to agents
    • Configuring and monitoring computer use for an agent
    • Configuring MCP tools
    • Adding a tool by using an existing custom connector
    • Adding REST APIs to an agent
  • Configuring multi-agent collaboration from Copilot Studio
    • Designing multi-agent solutions in Copilot Studio
    • Integrating a Foundry agent
    • Integrating an existing agent in Copilot Studio
    • Integrating a Fabric data agent
    • Creating a multi-agent solution by using A2A protocol
  • Integrating agents with Azure
    • Configuring generative answers by using Azure AI Search with Foundry
    • Configuring custom prompts to use the Foundry model catalog
    • Monitoring agents by using Application Insights

Test and Manage Agents

  • Evaluating agent performance
    • Creating a test set
    • Choosing an evaluation method
    • Reviewing test results
  • Implementing application lifecycle management (ALM) for agents in Copilot Studio
    • Creating a solution
    • Adding existing agents to a solution
    • Creating and using environment variables
    • Implementing and extending Microsoft Power Platform Pipelines

Dive in and learn more

When transforming your workforce, it’s important to have expert advice and tailored solutions. We can help. Tell us your unique needs and we'll explore ways to address them.

Let's chat

By clicking submit, you agree to our Privacy Policy and Terms of Use, and consent to receive marketing emails from Pluralsight.