MCP Mastery
About

LangChain & LangGraph Chapters

LangChain ^0.3 · LangGraph ^0.2 · Python ≥3.11

#1
warmup

What LangChain Actually Is — And why you stopped calling OpenAI directly.

~25 min

And why you stopped calling OpenAI directly.
#2
warmup

Models, Prompts, Parsers — The holy trinity, and the part where we stop pretending regex works.

~30 min

The holy trinity, and the part where we stop pretending regex works.
#3
mid

LCEL — The pipe that actually earns its keep.

~35 min

The pipe that actually earns its keep.
#4
mid

Retrieval Fundamentals — Why your first RAG app was a glorified substring search.

~40 min

Why your first RAG app was a glorified substring search.
#5
boss

Advanced RAG — Hybrid search, re-ranking, and the parent-document trick the demos skipped.

~45 min

Hybrid search, re-ranking, and the parent-document trick the demos skipped.
#6
mid

Tools and Function Calling — Stop pretending the model picks for you.

~35 min

Stop pretending the model picks for you.
#7
mid

LangGraph Fundamentals — Graphs, because AgentExecutor finally got the memo.

~40 min

Graphs, because AgentExecutor finally got the memo.
#8
mid

Stateful Agents — Messages, reducers, and memory that does not lie to itself.

~40 min

Messages, reducers, and memory that does not lie to itself.
#9
boss

Multi-Agent Patterns — Supervisor, swarm, and knowing when one agent was fine, actually.

~50 min

Supervisor, swarm, and knowing when one agent was fine, actually.
#10
boss

Human-in-the-Loop — Interrupts, approvals, and the time-travel debugger you did not know you had.

~45 min

Interrupts, approvals, and the time-travel debugger you did not know you had.
#11
boss

Persistence and Checkpointers — How to survive a pod restart without a customer noticing.

~45 min

How to survive a pod restart without a customer noticing.
#12
boss

Streaming, Async, and Concurrency — Sync code in 2026 is a personality choice.

~40 min

Sync code in 2026 is a personality choice.
#13
boss

Security and Guardrails — Your agent is an untrusted browser with a wallet.

~45 min

Your agent is an untrusted browser with a wallet.
#14
boss

Cost and Token Budgets — How to not wake up to a five-figure bill you cannot explain in Slack.

~40 min

How to not wake up to a five-figure bill you cannot explain in Slack.
#15
boss

Observability with LangSmith — Traces that save you at 3 AM, plus the self-hosting argument.

~40 min

Traces that save you at 3 AM, plus the self-hosting argument.
#16
boss

Evaluations — LLM-as-judge without lying to yourself.

~45 min

LLM-as-judge without lying to yourself.
#17
boss

Deployment — LangServe, FastAPI, and why your serverless function is about to time out.

~45 min

LangServe, FastAPI, and why your serverless function is about to time out.
#18
nightmare

Capstone — Ship a production multi-agent research assistant, or admit you are still doing demos.

~75 min

Ship a production multi-agent research assistant, or admit you are still doing demos.