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.
How We Made Our Docs Test Themselves
In one minute
LangChain published a description of a workflow for converting inline documentation code samples into runnable, testable files.