AI search
llms.txt
llms.txt is a proposed standard, published by Jeremy Howard in September 2024, for a Markdown file at the root of a website that gives language models a short summary of the site and links to its most useful pages.
How it works in practice
Web pages are written for people and carry navigation, scripts and layout that make them harder for a model to read. An llms.txt file gives a model a plain map: what the site is, then a list of key pages with a one-line description of each. Some sites also publish llms-full.txt with full page text, and Markdown versions of individual pages.
It is cheap to publish and does no harm, but major AI providers have not confirmed that they use it for search or answers, so it should sit alongside good pages and structured data, never replace them. Developer documentation sites have taken it up most, because coding assistants read them.
A worked example
A software company publishes llms.txt listing its pricing page, API reference and setup guides, each with a Markdown version. A developer pointing an AI coding assistant at the site gets clean, current text instead of rendered HTML.
Examples in this glossary describe typical builds for companies of 1 to 1,000 people. They are not named client results.















