Micro Free Course — 100% Free Learning
All lessons in this module are free to learn. Sign in with Google to save your progress.
Live Agent Cases
Six end-to-end walkthroughs: customer support agent with LangGraph, multi-agent research system, long-term memory for conversational agent, human-in-the-loop approval for high-stakes actions, production deployment with LangSmith observability, migrating a linear chain to a state machine.
Module Content
Case 1 — Build a Customer Support Agent with LangGraph
End-to-end support agent with tools, memory, and a clean state graph.
Case 2 — Multi-Agent Research System (Researcher + Writer + Reviewer)
Three specialized agents coordinated by a supervisor. The classic multi-agent pattern done right.
Case 3 — Add Long-Term Memory to a Conversational Agent
Beyond short-term conversation context. Build an agent that remembers users across sessions.
Case 4 — Human-in-the-Loop Approval Flow for High-Stakes Actions
Build the pause-approve-resume pattern for an agent that takes irreversible actions.
Case 5 — Deploy a LangGraph Agent to Production with Observability
From notebook to deployed service. LangSmith, FastAPI, Postgres, structured logging, monitoring.
Case 6 — Migrate a Linear Chain to a LangGraph State Machine
You have a working LCEL chain. It needs loops, retries, and human review. Refactor to LangGraph properly.