Udemy
    •  
    •  
    •  
    •  
    •  
    •  
    •  
    •  
Subscribe
Turn what you know into an opportunity and reach millions around the world.
Learn More
Your cart is empty.
Keep shopping
Building AI Agents with Langchain and Microsoft Azure
New
Rating: 4.4 out of 5(6 ratings)
248 students

Building AI Agents with Langchain and Microsoft Azure

Build production-ready AI agents with LangChain, Azure AI Foundry, MCP servers, tools, memory, and orchestration
New
Created byHoussem Dellai
Last updated 6/2026
English

What you'll learn

  • Build AI agents using LangChain and LangGraph with Azure AI Foundry
  • Deploy and configure LLMs on Azure using Terraform and secure API access
  • Design agents with tools, function calling, and the ReAct reasoning loop
  • Connect agents to data using MCP (Microsoft Learn + web search)
  • Execute Python and shell code safely using sandboxed environments
  • Add memory to agents using Azure Cosmos DB for multi-turn conversations
  • Implement human-in-the-loop workflows and model guardrails
  • Observe, debug, and optimize agents using LangSmith tracing

Course content

12 sections • 22 lectures • 1h 24m total length

  • Introduction3:55

    Why we need AI Agents - an LLM can think and an AI Agent can act. an AI Agent wraps an LLM and add features like function calling, memory, human in the loop, calling MCP Servers, atc.

  • Houssem Dellai, the author0:29

Requirements

  • Basic knowledge of Python (functions, APIs, packages)
  • Familiarity with REST APIs and JSON is helpful
  • Azure account (free tier works) to deploy models and services
  • Basic understanding of AI/LLMs concepts is a plus (not required)
  • Development environment (VS Code or Jupyter Notebook)
  • Curiosity to build real-world AI agents

Description

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 Azure

  • Agents with tools, memory, and MCP integrations

  • Multi-agent orchestration systems

  • Production-ready observable AI workflows

Who this course is for:

  • Python developers who want to build real AI agents
  • Azure engineers and cloud architects exploring AI workloads
  • AI/ML practitioners looking to move from prompts to autonomous agents
  • Developers interested in LangChain, MCP, and agent orchestration
  • Anyone curious about building production-ready AI systems on Azure

Report abuse