new·The score now tells you which way it movedA brain's exam only ever grows: its own material writes questions, and so does every question a real caller asked and did not get answered. The score is a percentage over that growing set, so a brain that learned more could post a smaller number — and this week three did. One of them answered two MORE questions than the week before and showed eighteen points less. Printed as a single percentage, that reads as decline to a reader and as punishment to anyone who contributes material.all news →
mozg.beta
Sign in

explore / AI & agents / mozg

LangChain & LangGraph

Answer questions about LangChain, LangGraph and Deep Agents as documented today: the v1 agent abstraction, models and messages, tools and structured output, LangGraph graphs with state, nodes and edges, persistence and human-in-the-loop, and deployment — the current API, not the 0.x chains API.

4,161 notes across 4 brains · updated 2026-08-14 · trained 88%

since last sitting: +88 newly passed — this brain is learning · the verified changelog →

use this brain
# sign in to get a token
$ claude mcp add --transport http mozg \
https://mozg.sh/mcp --header "Authorization: Bearer …"
> use mozg/langchain — …
Sign in — get this command with your token in it

New here? Sign in and this exact command appears with your token already inside — copy, paste into your terminal, done.

Or just add it

Sign in and add it, and every agent you have connected can read it — nothing to download, and it stays current as the author updates it.

Sign in to add it

Ask it things like

answers 88/100 on its latest exam
What is required to enable human-in-the-loop functionality in LangGraph?Persistence & Memory✓
What are the main stages in the agent development lifecycle?Agent Fundamentals & Lifecycle✓
What is the agent definition loop?Agent Fundamentals & Lifecycle✓
What is the purpose of StateGraph in LangGraph?Graph Architecture & Edges✓
How do you implement conditional routing between nodes?Graph Architecture & Edges✓
How do you pause agent execution for human review?Human-in-the-Loop & Interrupts✓
How do you compile a graph to support persistence and interrupts?Persistence & Memory✓
What is the purpose of MessagesState in LangGraph?State & Checkpointing✓

What is inside

asking this brain searches all 3
LangChain · AgentsAnswer questions about LangChain as documented today: building agents, model initialisation and message types, tool calling, structured output, streaming, context engineering and the middleware and retrieval patterns.1355 notes80%LangChain · Deep AgentsAnswer questions about Deep Agents as documented: creating an agent, subagents, backends and filesystem tools, context engineering, human-in-the-loop and customisation options.1174 notes85%LangChain · LangGraphAnswer questions about LangGraph exactly as documented: defining graphs with state, nodes and edges, persistence and checkpointing, human-in-the-loop, memory, streaming, subgraphs and deployment.1018 notes80%

What it can answer

100 coverage checks
88%
Answers 88 of the exam's 100 questionsIt answers 88 questions, 88 more than last time, out of an exam that grew by 100.Nothing it used to answer has stopped working.
✓Middleware & Advanced Patterns8 / 8
▲Persistence & Memory8 / 10
✓Models & Messages6 / 6
✓Testing & Evaluation6 / 6
▲Deployment & Configuration5 / 6
✓Error Handling & Fault Tolerance5 / 5
▲Graph Architecture & Edges5 / 6
✓Human-in-the-Loop & Interrupts5 / 5
✓Memory Types & Implementation5 / 5
✓Nodes & Tools5 / 5
✓State & Checkpointing5 / 5
▲System Prompts & Context Engineering5 / 6
▲Tool Calling & Structured Output5 / 6
▲Agent Fundamentals & Lifecycle4 / 5
✓RAG & Context Retrieval4 / 4
▲Streaming & Observability4 / 6
▲Subgraphs & Composition3 / 6
exam badge — share this score →

Attacks survived

re-run weekly · 2026-08-10
✓gate-battery12/12 known hostile payloads caught by the ingest gate
✓injection-corpusevery active note scanned — no steering language
✓secret-corpusevery active note scanned — no keys or credentials

heuristic scans against known attack classes — measured and dated, not a promise of unpoisonability

Inside

  • instructions.md file location in Managed Deep Agents project · deep agents & deployment
  • Instructions synced to Context Hub on deploy · deep agents & deployment
  • Example instructions.md content for Managed Deep Agent · deep agents & deployment
  • How instructions are used in Managed Deep Agents · deep agents & deployment
  • Relationship between instructions, skills, and memory in Managed Deep Agents · deep agents & deployment
  • Instructions define Managed Deep Agent system prompt · deep agents & deployment
  • Supabase JWT verification in Managed Deep Agents · deep agents & deployment
  • Supabase identity migration warning for existing deployments · deep agents & deployment
  • Authenticate end users with Supabase in Managed Deep Agents · deep agents & deployment
  • Identity file location in Managed Deep Agents project · deep agents & deployment
  • Define identity with Supabase in JavaScript · deep agents & deployment
  • Authentication failure response codes · errors/deep agents
  • Define identity with LangSmith API key in JavaScript · deep agents & deployment
  • Default identity authentication for Managed Deep Agents · deep agents & deployment

Licence

CC BY-NC-SA 4.0

Use it, copy it, build on it, with credit. Selling it is not allowed.