Skip to content

Building a Customer Service AI Agent with Azure AI Foundry

Welcome to this hands-on, 2-hour workshop where you'll build a practical customer service AI agent using Azure AI Foundry! You'll learn how to deploy an AI model, create an intelligent agent, and evaluate its performance - all through a real-world use case.

The Use Case: Smart Customer Support

You'll build an AI agent that can: - Answer common product questions - Handle customer inquiries - Access product documentation - Learn from customer interactions - Provide consistent, accurate responses

Workshop Timeline (2 hours)

  1. Setup and Model Deployment (30 min)
  2. Quick platform overview
  3. Deploy Azure OpenAI model

  4. Basic configuration and testing

  5. Agent Development (45 min)

  6. Create customer service agent
  7. Implement response handling

  8. Add product knowledge base

  9. Evaluation and Monitoring (45 min)

  10. Set up key metrics
  11. Monitor performance
  12. Analyze and improve responses

Prerequisites

  • Azure subscription with AI services access
  • Python 3.8 or later
  • Basic Python knowledge
  • Text editor or IDE

What You'll Learn

Through this practical example, you'll understand: - How to use the AI Foundry SDK - Model deployment and configuration - Agent creation and management - Performance evaluation and monitoring - Best practices for AI applications

Let's start by setting up your environment!