Building AI Agents with Langchain and Microsoft Azure

About this course

In this hands-on course, you will learn how to build modern AI agents from scratch using LangChain and Microsoft Azure. Instead of focusing only on theory, this course is designed as a practical journey where every concept is demonstrated through real implementations you can run and adapt in your own projects.

We start by understanding why AI agents are the next evolution beyond simple LLM applications, and how they combine reasoning with action using tools, memory, and external systems. From there, you will deploy your first model in Azure AI Foundry using Terraform and build a working ReAct agent capable of making decisions and executing tasks.

As the course progresses, you will extend your agents with powerful capabilities such as tool and function calling, integration with Model Context Protocol (MCP) servers, and real-time access to external data like Microsoft documentation and web search. You will also explore how to give your agents execution capabilities using sandboxed environments with Python and shell tools.

You will learn how to implement memory using Azure Cosmos DB, manage multi-turn conversations, and introduce human-in-the-loop workflows to safely control agent behavior. Advanced topics include middleware hooks, observability with LangSmith, and designing multi-agent architectures where specialized agents collaborate to solve complex problems.

By the end of this course, you will be able to design, build, and operate production-grade AI agents that integrate seamlessly with enterprise-grade Azure services.

What you’ll build:

• ReAct-based AI agents on AzureAgents with tools, memory, and MCP integrations
• Multi-agent orchestration systems
• Production-ready observable

Prices, discounts and availability are set by Udemy. We may earn a commission when you purchase through links on this site.