Azure AI Foundry Agent Workshop 🚀

Workshop Overview

In this hands-on session, you’ll learn how to build intelligent, domain-specific AI agents using Azure AI Foundry Agent Service.
We’ll go step by step—from creating a basic agent to extending it with custom tools, external data, and live integrations.

By the end of the workshop, you’ll have built your own Contoso PizzaBot, an AI assistant capable of:

• Following tailored system prompts
• Using retrieval-augmented generation (RAG) to answer questions from custom documents
• Calling custom tools like a pizza calculator
• Integrating with an MCP server for live menu and order management

Agenda

• Welcome & Setup
  Introduction, workshop goals, and Azure subscription setup

• Chapter 1: Create Your First Agent
  Log into Azure, install packages, and build a simple GPT-4o agent

• Chapter 2: System Prompts & Instructions
  Learn how prompts shape agent behavior and add custom instructions from instructions.txt

• Chapter 3: Adding Knowledge (RAG)
  Ground your agent in pizza store data using File Search and a vector store

• Chapter 4: Tool Calling
  Extend your agent with a custom pizza calculator function and toolset integration

• Chapter 5: MCP Integration
  Connect to an MCP server for live pizza menus, toppings, and order management

• Testing & Wrap-Up
  Test PizzaBot end-to-end, Q&A, and next steps

What You’ll Need

• A browser and access to the Azure Portal
• An Azure subscription provided or use your own
• A developement environment with Python 3.10+ installed
• Familiarity with Python basics (no deep AI background required!)

Workshop Goal

By the end of this 2-hour session, you’ll know how to:

1. Create and configure an agent in Azure AI Foundry
2. Guide its behavior with system prompts
3. Ground it in real data using RAG
4. Extend its functionality with custom tools
5. Connect it to external services with MCP

You’ll walk away with practical knowledge and a working PizzaBot agent you can build upon for real-world use cases.