LearnLangGraph

A hands-on LangGraph course in three waves: graphs without an LLM, then agents, then production patterns.

Active · join meAI Engineering

5 of 10 tasks done

1 · Purpose

LearnLangGraph teaches the LangGraph library by doing, one small runnable lesson at a time. Wave 1 uses no language model at all, so state, nodes, routing and loops are learned on plain code. Wave 2 adds a free open-weight model, and the agent loop becomes just one more node. It is for engineers who want to build agents on a clear mental model rather than copy examples.

For: Python developers and data engineers starting with agent workflows.

2 · Business benefits

Faster onboardingA new engineer can go from zero to a tool-using agent with memory in a few evenings.
Fewer fragile agentsLearning routing and loops on deterministic code first makes later agent bugs easier to find.
Zero model spend while learningLessons run on a free model tier, and tests use a scripted fake model with no network.
A reusable teaching assetEvery lesson is a runnable file plus a test, so a team can use it as its own internal course.

3 · Status and how to join

Active · join me. Under way: pick a task below, or tell me what you'd like to learn and I'll suggest one. Lead: Basant Choudhary.

Good first tasks this week:

  • Write lesson 15: an agent proposes a fix and pauses for approve or reject.
  • Add 'try this' answers to a Wave 2 lesson.
  • Run the course on a fresh machine and fix any setup step that breaks.

The code is not public yet; joiners get access.

4 · Requirements

What it must do

How well it must do it

5 · Architecture, very high level

Lesson filesOne runnable file per concept,with a docstring and 'try this'Shared toolsSample Spark jobs and tools theagent lessons call.Model adapterOne place that picks the modeland provider.Scripted fake modelReplays fixed answers so testsrun offline.TestsTable-driven checks for everylesson.Page builderTurns lessons, diagrams andcaptured output into one HTMLcall tools
Components and what each is responsible for, with no tool names: the tools come in the next section.

Also: Lesson files → Model adapter: ask the model · Tests → Scripted fake model: replay answers · Tests → Lesson files: check behaviour · Page builder → Lesson files: read code and output

6 · Tech stack, per platform

ComponentOpen stackAzureAWS
Lesson filesPython 3.12 + LangGraph 1.x ✓Azure Container Apps for a hosted agentAWS Lambda or ECS for a hosted agent
Shared toolsPlain Python ✓——
Model adapterOpenAI-compatible client on Groq free tier ✓Azure OpenAI / Azure AI FoundryAmazon Bedrock
Scripted fake modelCustom LangChain chat model ✓——
Testspytest, table-driven ✓——
Page builderPython script + HTML template ✓——

Bold with ✓ = built and running today. Everything else is the planned or possible binding: the components stay the same, only the tools change.

7 · What needs to be done

Wave 1: basics without an LLM 2 of 2 done

TaskStatusSizeSkill
Lessons 01 to 07 with testsdoneMPython
Spark triage capstonedoneSPython

Wave 2: agents 3 of 3 done

TaskStatusSizeSkill
Lessons 08 to 14 on a free modeldoneMLLM agents
Offline fake model and cached real outputdoneStesting
Single-page HTML coursedoneStechnical writing

Wave 3: production patterns 0 of 5 done

TaskStatusSizeSkill
Lesson 15: pause for human approval and resumetodoSLangGraph
Lesson 16: time travel and forking a runtodoSLangGraph
Lessons 17 to 18: subgraphs and map-reducetodoMLangGraph
Lesson 19: supervisor with worker agentstodoMmulti-agent
Lessons 20 to 22: durable storage, evals and capstonetodoLLangGraph

Size: S = an evening or two, M = about a week part-time, L = a few weeks.

8 · Roles

RoleHow manyHours / weekWhat they do
Lesson author13-4Writes one Wave 3 lesson at a time with its test.
Tester / reviewer11-2Runs every lesson fresh and reports where it confuses.

9 · What you'll learn

Level-up questions

10 · Links