# How We Made Our Docs Test Themselves

DevFeed: [How We Made Our Docs Test Themselves](<https://devfeed.tech/articles/how-we-made-our-docs-test-themselves-86208.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/our-docs-test-themselves>)

Author: LangChain Accounts

Published: 2026-10-13T19:56:07Z

Content type: article

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [Documentation](<https://devfeed.tech/topics/documentation.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [Continuous integration](<https://devfeed.tech/topics/continuous-integration.md>), [AI interaction best practices](<https://devfeed.tech/topics/ai-interaction-best-practices.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ci](<https://devfeed.tech/tags/ci.md>), [cli](<https://devfeed.tech/tags/cli.md>), [docs](<https://devfeed.tech/tags/docs.md>), [test](<https://devfeed.tech/tags/test.md>)

## AI overview

LangChain describes using the Deep Agents CLI and reusable skills to move inline documentation examples into standalone, runnable code files. The workflow adds setup and teardown, checks the examples with linters and tests, and generates snippets for the docs. A GitHub action regularly runs the tests and creates tickets when they fail.

## Source excerpt

Stale code samples are a docs problem nobody prioritizes. Here's how we used the Deep Agents CLI to automate migrating inline code into testable, CI-ready examples