Udemy
    •  
    •  
    •  
    •  
    •  
    •  
    •  
    •  
Turn what you know into an opportunity and reach millions around the world.
Learn More
Your cart is empty.
Keep shopping
LangGraph
Rating: 4.9 out of 5(2 ratings)
23 students

LangGraph

Build AI Agents and Workflows with LangGraph
Created byVenkata Reddy AI Classes
Last updated 6/2026
English

What you'll learn

  • Understand LangGraph fundamentals and build stateful, multi-agent AI workflows using graph-based architectures.
  • Design, develop, and deploy AI agents with memory, decision-making, and tool-calling capabilities using LangGraph.
  • Integrate LangGraph with LLMs, APIs, databases, and external tools to create intelligent agentic applications.
  • Build real-world AI projects including chatbots, autonomous agents, research assistants, and workflow automation systems.

Explore related topics

Course content

2 sections • 16 lectures • 5h 53m total length

  • Prerequisites and Complex LangChain Agents9:28
  • Motivation and Core Graph Concepts22:49

    Students will understand LangChain's limitations, like infinite loops, and learn how LangGraph solves these by modeling AI workflows as highly controlled, stateful graphs with nodes and edges


  • Building Basic State Graphs27:35

    Students will construct foundational state graphs without LLMs. They will define a shared memory state using TypedDict, create Python function nodes, and connect them linearly using basic examples

  • Implementing Conditional Edges35:43

    Students will design dynamic, non-linear workflows by creating routing functions and conditional edges. They will practice dynamically routing execution paths using customer service and ATM exercises

  • Integrating LLM Nodes14:17

    Students will integrate Large Language Models directly into graph architectures. They will define an LLM node to answer user queries from the state and build a Gradio UI chat interface for the workflow

  • First React Agent28:39

    Students will be able to build a LangGraph AI agent combining an LLM with Tavly search. They will learn to bind tools, manage agent state using message reducers, map workflow nodes and conditional edges, and create a Gradio chat interface to test their agent.

  • Memory Management and Checkpointing9:40

    Students will implement conversational memory using LangGraph's MemorySaver checkpointer. They will learn to save workflow states, maintain context, and isolate multi-user chats using thread IDs.

  • Building an AI Agent with Tools13:10

    Students will construct functional AI agents by binding LLMs to external tools, like a Wikipedia search. They will use conditional edges to let the LLM consult tools dynamically before synthesizing answers.

  • Agentic RAG Workflows24:06

    Students will build stateful Agentic RAG systems. They will process documents into vector databases, wrap the retriever as a tool, and write detailed prompts to strictly ground AI answers on retrieved data

Requirements

  • Basic Python programming knowledge is recommended, including variables, functions, loops, and object-oriented concepts.
  • Familiarity with Generative AI concepts and Large Language Models (LLMs) is helpful but not mandatory.
  • No prior experience with LangGraph or LangChain is required. Everything will be taught from scratch through hands-on projects.
  • Basic understanding of APIs, JSON, and Python libraries will help learners follow advanced examples more easily.
  • Enthusiasm to build AI agents, multi-agent systems, and real-world AI applications using modern frameworks.

Description

LangGraph is one of the most powerful frameworks for building intelligent AI agents and workflow-driven applications. This course is designed to help you learn LangGraph from the ground up and apply it to real-world AI projects.

You will start by understanding the foundations of AI agents and LangChain before moving into LangGraph's graph-based architecture. Through hands-on examples, you will learn how to create stateful workflows using nodes, edges, conditional routing, memory, and checkpoints. As the course progresses, you will integrate Large Language Models (LLMs), external tools, databases, web search, and Retrieval-Augmented Generation (RAG) systems into your applications.

The course covers both fundamental and advanced topics, including conversational memory, Agentic RAG, Corrective RAG, reflection-based agents, Human-in-the-Loop workflows, SQL agents, and multi-tool AI systems. You will also learn how to monitor, trace, debug, and optimize AI workflows using LangSmith.

Every concept is explained step by step with practical coding demonstrations and real-world use cases. By the end of the course, you will be able to design, build, and deploy sophisticated AI agents that can reason, use tools, manage memory, and automate complex tasks.

Whether you are a developer, data scientist, AI enthusiast, or student, this course will provide the skills needed to build next-generation AI applications using LangGraph.

Who this course is for:

  • Python developers who want to build AI agents, multi-agent systems, and intelligent workflows using LangGraph.
  • Generative AI enthusiasts looking to create advanced agentic AI applications beyond traditional chatbots.
  • Data scientists, AI engineers, and machine learning practitioners interested in AI orchestration and workflow automation.
  • Students, researchers, and professionals seeking hands-on experience with modern AI agent frameworks and architectures.
  • Anyone interested in learning LangGraph from scratch and building real-world AI projects through practical examples.

Report abuse