Develop AI Agents on Azure (AI-3026)

Learn how to design, build, extend, and deploy AI agents using Microsoft Foundry and Azure AI services.

In this hands-on course, you'll develop AI agents using Microsoft Foundry Agent Service, Visual Studio Code, and the Microsoft Agent Framework. You'll learn how to create agents, extend their capabilities with custom tools and Model Context Protocol (MCP) integrations, connect agents to enterprise knowledge using Foundry IQ, and integrate agents with Microsoft Teams and Microsoft 365 Copilot.

You'll also explore agent-driven workflows, multi-agent orchestration patterns, and Agent-to-Agent (A2A) communication to build intelligent applications that can collaborate, access enterprise knowledge, and automate complex business processes.

Develop AI Agents on Azure (AI-3026) Benefits

• You Will Learn How To

  After completing this course, you will be able to:
  •    Build AI agents using Microsoft Foundry Agent Service 
  •    Extend AI agents with custom tools and MCP integrations 
  •    Connect AI agents to enterprise knowledge using Foundry IQ 
  •    Integrate AI agents with Microsoft Teams and Microsoft 365 Copilot 
  •    Create agent-driven workflows in Microsoft Foundry 
  •    Develop multi-agent solutions using Microsoft Agent Framework 
  •    Enable communication between agents using the A2A protocol

  Prerequisites

  Students should have:
  •    Experience developing applications using Python or C#
  •    Familiarity with Azure services and Azure AI concepts
  •    Basic understanding of generative AI and large language models
  •    Experience with Visual Studio Code is recommended

Develop AI Agents on Azure (AI-3026) Course Outline

Learning Objectives

Develop AI Agents with Microsoft Foundry and Visual Studio Code

• Understand AI agents and Microsoft Foundry Agent Service
• Explore development approaches
• Build your first agent in Microsoft Foundry
• Set up Visual Studio Code for agent development
• Configure and manage agents in Visual Studio Code
• Extend agent capabilities with tools
• Test, deploy, and integrate agents
• Exercise: Build and deploy an AI agent

Integrate Custom Tools into Your Agent

• Why use custom tools
• Options for implementing custom tools
• Integrate custom tools with AI agents
• Exercise: Build an agent with custom tools

Integrate MCP Tools with Azure AI Agents

• Understand MCP tool discovery
• Integrate agent tools using MCP servers and clients
• Use Azure AI agents with MCP servers
• Exercise: Connect MCP tools to Azure AI Agents

Build Knowledge-Enhanced AI Agents with Foundry IQ

• Understand Retrieval Augmented Generation (RAG) for agents
• Explore Foundry IQ
• Configure data sources for knowledge bases
• Configure retrieval using Foundry IQ
• Exercise: Integrate an AI agent with Foundry IQ

Integrate Your Agent with Microsoft 365

• Understand Foundry agent publishing options
• Publish agents to Microsoft Teams
• Use the Microsoft 365 Agents Toolkit
• Access Microsoft 365 data with Work IQ
• Test and refine integrated agents
• Exercise: Publish a Foundry agent to Teams

Build Agent-Driven Workflows Using Microsoft Foundry

• Understand workflow concepts
• Identify workflow patterns
• Create workflows in Microsoft Foundry
• Add agents to workflows
• Apply Power Fx in workflows
• Maintain workflows
• Use workflows in code
• Exercise: Create an agent-driven workflow

Develop an AI Agent with Microsoft Agent Framework

• Understand Microsoft Agent Framework AI agents
• Create an Azure AI agent with Microsoft Agent Framework
• Add tools to Azure AI agents
• Exercise: Develop an Azure AI agent with Microsoft Agent Framework

Orchestrate a Multi-Agent Solution Using Microsoft Agent Framework

• Understand Microsoft Agent Framework
• Understand agent orchestration
• Implement concurrent orchestration
• Implement sequential orchestration
• Implement group chat orchestration
• Implement handoff orchestration
• Implement Magentic orchestration
• Exercise: Develop a multi-agent solution

Discover Azure AI Agents with A2A

• Define an A2A agent
• Implement an agent executor
• Host an A2A server
• Connect to an A2A agent
• Exercise: Connect to remote Azure AI Agents with the A2A protocol