llms.txt
llms.txt is a proposed standard for a plain Markdown file at the root of a website (/llms.txt) that gives large language models a short, curated summary of the site and links to its most important pages.
The format was proposed in September 2024 by Jeremy Howard of Answer.AI. It works a bit like a sitemap for AI: instead of listing every URL, it describes what the site is about and points to the pages that answer the most important questions.
What goes into an llms.txt file
A title and a one-paragraph summary of the company or project.
Sections with links to key pages, each with a short description.
Optionally, links to Markdown versions of longer documentation.
Does it matter?
llms.txt is not an official web standard, and AI companies have not confirmed that they use it for ranking or citations. It is cheap to add, but it does not replace structured data, clear content or the other basics of AEO.
FAQ
Where does llms.txt go?
At the root of the domain, for example example.com/llms.txt, as a plain text file written in Markdown.
Is llms.txt the same as robots.txt?
No. robots.txt tells crawlers what they may access. llms.txt is an optional summary that helps language models understand a site.
Related terms
Answer Engine Optimization (AEO)
Answer Engine Optimization (AEO) is the practice of structuring a website's content so that AI assistants and answer engines, such as ChatGPT, Perplexity, Gemini and Google's AI Overviews, can find it, understand it and cite it in their answers.
Generative Engine Optimization (GEO)
Generative Engine Optimization (GEO) is the practice of making content more likely to be used and cited by generative AI systems, such as ChatGPT, Claude, Gemini or Perplexity, when they write an answer.
JSON-LD (structured data)
JSON-LD is a format for adding structured data to a web page: a small block of code, using the schema.org vocabulary, that tells search engines and AI systems exactly what the page is about, such as an organisation, article, product or FAQ.
Related at Trueform:
