---
type: "raw_signal"
id: "how-we-made-our-docs-test-themselves-69af7f"
slug: "how-we-made-our-docs-test-themselves-69af7f"
title: "How We Made Our Docs Test Themselves"
description: "LangChain published a description of a workflow for converting inline documentation code samples into runnable, testable files."
retrieval_nugget: "LangChain published a description of a workflow for converting inline documentation code samples into runnable, testable files."
observed_at: "2026-10-13"
record_date: "2026-10-13"
date_kind: "observed_at"
why_it_matters: "LangChain published a description of a workflow for converting inline documentation code samples into runnable, testable files. The company says it used the Deep Agents CLI and a reusable skill to move examples into standalone files, add setup and teardown, lint them, mark extractable snippets, run them, and regenerate documentation snippets. A GitHub Action then runs the samples regularly and cre"
novelty: "notable"
verification_level: "source-linked"
signal_type: "update"
source_platform: "langchain.com"
topics: []
entities: ["LangChain","Deep Agents CLI","GitHub Actions","Bluehawk","Mintlify"]
related_patterns: ["skills-become-portable-capability-layer"]
source_url: "https://www.langchain.com/blog/our-docs-test-themselves"
source_urls: ["https://www.langchain.com/blog/our-docs-test-themselves"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:how-we-made-our-docs-test-themselves-69af7f"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/signals/how-we-made-our-docs-test-themselves-69af7f/","markdown":"https://newruntime.com/signals/how-we-made-our-docs-test-themselves-69af7f.md","json":"https://newruntime.com/signals/how-we-made-our-docs-test-themselves-69af7f.json"}
---

# How We Made Our Docs Test Themselves

## Retrieval answer

LangChain published a description of a workflow for converting inline documentation code samples into runnable, testable files.

LangChain published a description of a workflow for converting inline documentation code samples into runnable, testable files. The company says it used the Deep Agents CLI and a reusable skill to move examples into standalone files, add setup and teardown, lint them, mark extractable snippets, run them, and regenerate documentation snippets. A GitHub Action then runs the samples regularly and creates tickets when a test fails. The post presents this as LangChain's own implementation; it does not report comparative measurements or independently verified effects.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)