top of page

Design and build integrated AI agent solutions in Copilot Studio

Duration

Course Code

3 days

AB-620T00

About the Course

THIS COURSE WILL BE AVAILABLE ON 7/31/2026.


In this course, you learn how to design, build, and manage production‑ready AI agent solutions using Microsoft Copilot Studio with a focus on building agents that integrate across systems and operate reliably at enterprise scale. You’ll go beyond creating standalone agents and learn how to deliver end‑to‑end solutions that automate real business processes, connect to enterprise data, and take meaningful action across platforms. Throughout the course, you’ll apply best practices for integration, governance, security, and responsible AI, so your agents are ready for real‑world deployment.


By the end of this course, you’ll be able to:

  • Design Copilot Studio agents that integrate with enterprise systems and data using connectors, APIs, Azure AI Search, and Model Context Protocol (MCP).

  • Build and orchestrate advanced workflows and multi‑agent solutions

  • Automate complex scenarios, including human‑in‑the‑loop and computer‑use workflows.

  • Apply identity, security, governance, and responsible AI considerations during solution design and implementation.

  • Test, monitor, and manage agents as enterprise‑grade solutions.


What will you learn with AB-620 training?


Module 1: Deliver rich agent responses using Adaptive Cards in Microsoft Copilot Studio

  • Introduction.

  • Configure message formatting in agent topics.

  • Design information Adaptive Cards for agent responses.

  • Collect user inputs with interactive Adaptive Cards.

  • Apply channel-specific considerations for Adaptive Cards.


Module 2: Take action from agent conversations using topics and tools in Microsoft Copilot Studio

  • Call tools from agent topics.

  • Call agent flows from agent topics

  • Retrieve and send data using the HTTP request mode.


Module 3: Generate AI-powered agent responses using generative answers in Microsoft Copilot Studio

  • Configure the generative answers node in a topic.

  • Connect custom knowledge sources to a generative answers node.

  • Shape AI responses with custom instructions.

  • Author and configure custom prompts in topics.


Module 4: Design multi-agent solutions in Microsoft Copilot Studio

  • Understand multi-agent architectures in Copilot Studio.

  • Design multi-agent solutions using child agents.

  • Design multi-agent solutions using connected agents.


Module 5: Delegate agent tasks using child agents in Copilot Studio

  • Understand child agents in Copilot Studio.

  • Create and configure a child agent.

  • Configure child agent inputs, outputs, and trigger behaviour.

  • Test and manage child agents.


Module 6: Build multi-agent solutions using connected agents in Copilot Studio

  • Understand connected agents in Copilot Studio.

  • Connect an existing Copilot Studio agent.

  • Connect a Microsoft Foundry agent.

  • Connect a Microsoft Fabric Data agent.

  • Manage and test your connected agent solution.


Module 7: Build cross-platform multi-agent solutions using the Agent2Agent protocol in Microsoft Copilot Studio

  • Understand the Agent2Agent (A2A) protocol.

  • Connect a Copilot Studio agent to an A2A-enabled agent.

  • Test and validate an A2A agent connection.


Module 8: Design integration strategies for agents in Microsoft Copilot Studio

  • Explore the Copilot Studio integration landscape.

  • Compare action integration patterns.

  • Authenticate and govern agent integrations.

  • Select integration patterns for enterprise scenarios.


Module 9: Take action in external systems using connector and REST API agent tools in Microsoft Copilot Studio

  • Understand connector and REST API tools in Copilot Studio.

  • Add prebuilt and custom connector tools to an agent.

  • Configure authentication for connector tools.

  • Add a REST API using an OpenAI specification.


Module 10: Ground agents with enterprise knowledge using connectors and Azure AI Search in Microsoft Copilot Studio

  • Choose between Copilot connector and Power Platform connector knowledge sources.

  • Add Copilot connectors as knowledge sources.

  • Configure Power Platform connectors as real-time knowledge sources.

  • Connect an agent to Azure AI Search.


Module 11: Integrate agents with external systems via MCP in Microsoft Copilot Studio

  • Understand MCP and its role in Copilot integration.

  • Connect an agent to an existing MCP server.

  • Configure authentication for MCP server connections.

  • Enable and manage MCP tools on an agent.


Enroll now

Assessed on this exam

  • Plan and configure agent solutions.

  • Integrate and extend agents in Copilot Studio.

  • Test and manage agents.


Book your exam now

bottom of page