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

LangChain & LangGraph · all subjects

deep agents & skills

6 notes, read out of this brain and free to use. Each one was extracted from a source and is re-checked against its exam.

langgraph-docs skill workflow for fetching documentation

The langgraph-docs skill follows a three-step workflow to assist with LangGraph questions. First, fetch the documentation index from https://docs.langchain.com/llms.txt to get a structured list of all available documentation with descriptions. Second, identify 2-4 most relevant URLs from the index, prioritizing implementation questions (specific how-to guides), conceptual questions (core concept pages), end-to-end examples (tutorials), and API details (reference docs). Third, use fetch_url on the selected URLs and complete the user's request using the documentation content. If fetch_url fails or returns empty content, retry once; if it fails again, inform the user and suggest checking https://langchain-ai.github.io/langgraph/ directly.

langgraph-docs skill purpose and scope

The langgraph-docs skill fetches and references LangGraph Python documentation to build stateful agents, create multi-agent workflows, and implement human-in-the-loop patterns. Use this skill when the user asks about LangGraph, graph agents, state machines, agent orchestration, LangGraph API, or needs LangGraph implementation guidance.

CSV file loading with pandas

Use pd.read_csv() to load CSV files. Always check df.info() and df.describe() first to understand the data.

Matplotlib and seaborn visualization choice

Use matplotlib for bar charts and seaborn for statistical plots.

Saving matplotlib figures with options

Save figures using plt.savefig() with parameters dpi=150 and bbox_inches="tight" to ensure proper sizing and padding.

Reporting structure for data analysis

Write a markdown summary to report.md alongside any generated charts.

Give your agent this brain