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

LangChain · Deep Agents

Answer questions about Deep Agents as documented: creating an agent, subagents, backends and filesystem tools, context engineering, human-in-the-loop and customisation options.

1,174 notes · updated 2026-08-14 · trained 85%

since last sitting: +37 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/deepagents — …
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 37/43 on its latest exam · anti-bluff 0/1
What does RAG stand for and what is its purpose in Deep Agents?Context Engineering
What is the required parameter to pass to create_deep_agent when initializing a new agent?Creating Agents
What type of model does a Deep Agent require to function?Creating Agents
What is required to enable human-in-the-loop interrupts in an agent?Human-in-the-Loop
What is the security risk with LocalShellBackend?Backends & Filesystem
What required methods must a backend protocol implement?Backends & Filesystem
How do you set up provider credentials for Deep Agents Code?Configuration
What are the two common RAG architectures in Deep Agents?Context Engineering

What it can answer

43 coverage checks
85%
Answers 37 of the exam's 44 questionsIt answers 37 questions, 37 more than last time, out of an exam that grew by 44.Nothing it used to answer has stopped working.
Backends & Filesystem6 / 7
Human-in-the-Loop6 / 6
Fault Tolerance5 / 5
Configuration4 / 4
Context Engineering4 / 5
Creating Agents4 / 4
Customization4 / 7
Subagents4 / 5
exam badge — share this score →

Attacks survived

re-run weekly · 2026-08-11
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

  • Slack conversation mapping modes · deep agents/customization
  • runtime.channel availability · deep agents/customization
  • Slack app manifest workflow - files and structure · deep agents/customization
  • channels.slack() configuration options - TypeScript · deep agents/customization
  • runtime.channel.post() method for Slack · deep agents/customization
  • Send Slack channel reply tool example - TypeScript · deep agents/customization
  • Slack unsupported features · deep agents/customization
  • Slack channel creation with channels.slack() · deep agents/customization
  • Deploy Managed Deep Agent to activate Slack · deep agents/customization
  • Slack credentials configuration · deep agents/customization
  • Slack event subscription behavior · deep agents/customization
  • Slack duplicate message handling · deep agents/customization
  • Send Slack channel reply tool example - Python · deep agents/customization
  • Slack caller identity format · deep agents/customization

Licence

CC BY-NC-SA 4.0

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