Course Description

In today’s AI-driven world, advanced frameworks like LangGraph are redefining how we build intelligent systems. This course offers a structured approach to mastering LangGraph, focusing on graph-based architectures for advanced AI agents.

Through comprehensive modules and practical exercises, you will:

  • Learn the fundamentals of LangGraph and its applications in AI agent design.

  • Understand how graph-based architectures enable efficient workflows and decision-making.

  • Explore real-world use cases and implement complex, scalable AI agents.

Whether you're a seasoned professional or a learner looking to expand your expertise, this course equips you with the tools and knowledge to harness the power of LangGraph for building next-generation AI agents. 

Course curriculum

  • 1
    Course Introduction
    • Course Objectives
    • Why LangGraph?
    • Recap of Building your First AI Agent with LangGraph
    • Course Handouts
    • Quiz
    • Reading Resource
  • 2
    Core Components of Agentic Systems & LangGraph
    • Essential LangGraph Components and Functions - Part I - Key Components
    • Essential LangGraph Components and Functions - Part II - Key Functions
    • Simple Agentic Graph and State Management in LangGraph - Part I - Simple Graph and State
    • Simple Agentic Graph and State Management in LangGraph - Part II - Custom State Schema
    • Simple Agentic Graph and State Management in LangGraph - Part III - State Reducers
    • Conditional Routing in LangGraph - Part I - Concepts
    • Conditional Routing in LangGraph - Part II - Hands-On Demo
    • Build a LLM - powered Chatbot with LangGraph
    • Invoking vs. Streaming in LangGraph
    • Augmented LLMs with Tools - Part I - Concepts
    • Augmented LLMs with Tools - Part II - Hands-On Demo
    • Build Simple Tool-use AI Agents - Part I - Concepts
    • Build Simple Tool-use AI Agents - Part II - Hands-On Demo
    • Quiz
    • Reading Resources
  • 3
    Building Tool-Use Agentic AI Systems
    • Recap of Tool-use Agentic AI Systems
    • Recap of the ReAct Agentic Pattern
    • Quiz
    • Reading Resources
  • 4
    Project: Build a Financial Analyst Tool-Use AI Agent
    • Project Introduction
    • Financial Analysis Essentials
    • Key Financial Data Platforms
    • Setup Access to Financial Data Platforms
    • OpenBB Platform: Introduction by the OpenBB Team
    • Project Architecture
    • Project Implementation: Part I - Project and Tools Setup
    • Project Implementation: Part II - Create Agent
    • Assignment: Create an Agent Using LLM and Custom Mathematical Functions
  • 5
    Memory & Conversational Agentic AI Systems
    • Recap of Conversational Systems & Memory
    • Memory & Threads in LangGraph for Multi-User Conversations
    • Memory Management for Long Conversations
    • Quiz
    • Reading Resources
  • 6
    Projects: Multi-User Conversational Financial Analyst Tool-Use AI Agents with Memory
    • Project Introduction and Architecture
    • Project Implementation: AI Agent with In-Memory Persistence
    • Project Implementation: AI Agent with On-Disk Memory Persistence
  • 7
    Router Agentic AI Systems
    • Introduction to Router Agents
    • Recap of RAG - Agentic RAG Systems
    • Quiz
    • Reading Resources
  • 8
    Project: Build a Customer Support Router Agentic RAG System
    • Project Introduction and Architecture
    • Project Implementation: Part I - Create RAG Database
    • Project Implementation: Part II - Create Node Functions
    • Project Implementation: Part III - Create Agent
    • Reading Resources
  • 9
    Reflection Agentic AI Systems
    • Recap of Reflection Agentic AI Systems
    • Quiz
    • Reading Resources
  • 10
    Project: Build a Reflective Self-Correcting Code Generation AI Agent
    • Project Introduction and Architecture
    • Project Implementation: Part I - Setup Code Generator
    • Project Implementation: Part II - Create Node Functions
    • Project Implementation: Part III - Create Agent
    • Reading Resources
  • 11
    Planning Agentic AI Systems
    • Recap of Planning Agentic AI Systems
    • Static Planning vs. Reflective Dynamic Planning Agentic AI Systems
    • Parallel Steps Execution in Agentic Systems in LangGraph
    • The Send construct in LangGraph - Dynamic Parallel Execution with Map-Reduce - Part I - Concepts
    • The Send construct in LangGraph - Dynamic Parallel Execution with Map-Reduce - Part II - Create Node Functions
    • The Send construct in LangGraph - Dynamic Parallel Execution with Map-Reduce - Part III - Create Agent
    • Quiz
  • 12
    Project: Build a Planning Agent for Deep Research & Structured Report Generation
    • Project Introduction and Architecture
    • Project Implementation - Part I - Project Setup
    • Project Implementation - Part II - Create Utility Functions
    • Project Implementation - Part III - Create Report Planner Node
    • Project Implementation - Part IV - Create Section Builder Sub-Agent
    • Project Implementation - Part V - Create Format Sections Node
    • Project Implementation - Part VI - Create Final Section Writer Node
    • Project Implementation - Part VII - Create Compile Final Report Node
    • Project Implementation - Part VIII - Create Planning Agent
  • 13
    Project: Build a Reflective Dynamic Planning Agent for Multi-Step Complex Query Analysis
    • Project Introduction and Architecture
    • Project Implementation - Part I - Project & Tools Setup
    • Project Implementation - Part II - Create Sub-Agent, Planner, Replanner
    • Project Implementation - Part III - Create Node Functions and Agent
  • 14
    Multi-Agent AI Systems
    • Recap of Multi-Agent AI Systems
    • Common Multi-Agent System Architectures
    • The Command construct in LangGraph - Dynamic Agent Navigation
    • Quiz
    • Reading Resources
  • 15
    Project: Build a Supervisor Multi-Agent System for Financial Research and Data Analysis
    • Project Introduction and Architecture
    • Project Implementation
    • Assignment: Multi-Agent Research and Summarization System

Who Should Enroll

  • Developers, engineers, and data scientists seeking to build advanced, graph-based AI agents using LangGraph.

  • Individuals eager to explore cutting-edge frameworks for creating scalable and intelligent AI systems.

  • Learners with a foundation in AI who want to deepen their understanding of advanced agent architectures.

Key Takeaways from the Course

  • Master the LangGraph framework for building advanced, graph-based AI agents.

  • Learn how to design scalable and efficient workflows using graph architectures.

  • Gain hands-on experience in implementing complex AI agents for real-world applications.

  • Understand decision-making processes and workflow optimization using LangGraph.

  • Explore practical use cases to enhance problem-solving with dynamic AI systems.

About the Instructors

Dipanjan Sarkar - Head of Community and Principal AI Scientist, Analytics Vidhya

Dipanjan Sarkar is a distinguished Lead Data Scientist, Published Author, and Consultant, having a decade of extensive expertise in Machine Learning, Deep Learning, Generative AI, Computer Vision, and Natural Language Processing. His leadership spans Fortune 100 enterprises to startups, crafting end-to-end data products and pioneering Generative AI upskilling programs. A seasoned mentor, Dipanjan advises a diverse clientele, from novices to C-suite executives and PhDs, across Advanced Analytics, Product Development, and Artificial Intelligence. His recognitions include "Top 10 Data Scientists in India, 2020," "40 under 40 Data Scientists, 2021," "Google Developer Expert in Machine Learning, 2019," and "Top 50 AI Thought Leaders, Global AI Hub, 2022," alongside global accolades and a Google Champion Innovator title in Cloud AI/ML, 2022.
About the Instructors

FAQ

  • What is LangGraph, and why is it essential for building advanced AI agents?

    LangGraph is a graph-based framework designed for building complex, dynamic AI agents. It enables efficient workflow management and decision-making, making it ideal for advanced AI applications.

  • What will I learn in this course?

    You will gain in-depth knowledge of LangGraph's core components, graph-based architectures, state management, and conditional routing, along with practical applications of these concepts.

  • Do I need prior experience with AI agents to take this course?

    A basic understanding of AI agents and Python programming is recommended. Familiarity with tools like LangChain may be helpful.

  • How does LangGraph differ from Autogen and CrewAI?

    LangGraph uses graph-based architectures for scalable workflows and dynamic decision-making, ideal for complex tasks. Autogen focuses on multi-agent orchestration but requires more programming, while CrewAI simplifies team-based agent tasks but lacks advanced workflow optimization.

  • Will this course cover real-world applications of LangGraph?

    Yes, the course includes practical exercises and case studies to demonstrate how LangGraph can be applied to solve complex, real-world problems.

  • What makes LangGraph suitable for building scalable AI systems?

    Its graph-based design allows for modular, dynamic workflows and conditional routing, making it ideal for building scalable, efficient AI systems capable of handling intricate tasks.