Advanced 6 hours 12 lessons

Advanced LangGraph Engineering

Persistence, interrupts, streaming, subgraphs, and multi-agent systems.

A rigorous advanced course on persistent, interruptible, streaming, multi-agent LangGraph systems built from reusable subgraphs and operated in production. The curriculum is grounded in the curated technical references and preserves their technical depth, code, diagrams, decision rules, and failure analysis. Every lesson adds objectives, an applied lab, review questions, and concrete completion evidence. The course closes with a substantial capstone: Deploy a persistent multi-agent workflow with checkpoints, human approval, streaming updates, recovery tests, and operational metrics.

What you will learn

Leave with a working mental model.

  • Persist, resume, replay, and inspect state with production checkpoint backends
  • Design human approval and correction flows with interrupts
  • Compose subgraphs and multi-agent supervisors without routing ambiguity
  • Stream and deploy stateful workflows with operational safeguards

Before you begin

Prerequisites

  • Ability to build and debug a StateGraph
  • Typed state and conditional routing
  • LLM tool-calling experience

Curriculum

Course contents

7 modules · 12 lessons

01 Architecture and State Contracts 2 lessons
  1. 01 LangGraph Architecture Overview Preview
  2. 02 LangGraph State Management Preview
02 Persistence and Time Travel 1 lesson
  1. 01 LangGraph Persistence and Checkpoints
03 Human in the Loop 1 lesson
  1. 01 LangGraph Human-in-the-Loop
04 Subgraphs and Multi-Agent Patterns 2 lessons
  1. 01 LangGraph Subgraphs
  2. 02 LangGraph Multi-Agent Patterns
05 Streaming Interfaces 1 lesson
  1. 01 LangGraph Streaming
06 Production Deployment 3 lessons
  1. 01 LangGraph Production and Deployment
  2. 02 LangGraph Common Pitfalls
  3. 03 LangGraph Real-World Use Cases
07 Capstone Studio 2 lessons
  1. 01 Capstone Brief and Architecture
  2. 02 Validation, Review, and Definition of Done