The following exercises are designed to provide you with a hands-on learning experience in which you’ll explore common tasks that developers do when building AI agents on Microsoft Azure.

Note: To complete the exercises, you’ll need an Azure subscription in which you have sufficient permissions and quota to provision the necessary Azure resources and generative AI models. If you don’t already have one, you can sign up for an Azure account. There’s a free trial option for new users that includes credits for the first 30 days.

Exercises

Build AI agents with portal and VS Code

Create an AI agent using both Microsoft Foundry portal and VS Code extension with built-in tools like file search and code interpreter.

Use a custom function in an AI agent

Learn how to use functions to add custom capabilities to your agents.

Extend agents with Model Context Protocol (MCP) tools

Extend agent capabilities by integrating Model Context Protocol (MCP) server tools.

Integrate an AI agent with Foundry IQ

Use Azure AI Agent Service to develop an agent that uses Foundry IQ to search knowledge bases.

Deploy agents to Microsoft Teams and Copilot

Publish AI agents to Microsoft Teams and Microsoft 365 Copilot for enterprise access

Work IQ - Workplace intelligence for AI agents (optional)

Build AI agents that access Microsoft 365 workplace data using Work IQ and the Model Context Protocol for meeting prep, project tracking, and action items.

Build a workflow in Microsoft Foundry

Use the Microsoft Foundry portal to create workflows for AI agents.

Develop an Azure AI agent with the Microsoft Agent Framework SDK

Learn how to use the Microsoft Agent Framework SDK to create and use an Azure AI chat agent.

Develop a multi-agent solution with Microsoft Agent Framework

Learn to configure multiple agents to collaborate using the Microsoft Agent Framework SDK

Connect to remote agents with A2A protocol

Use the A2A protocol to collaborate with remote agents.

Note: While you can complete these exercises on their own, they’re designed to complement modules on Microsoft Learn; in which you’ll find a deeper dive into some of the underlying concepts on which these exercises are based.