What is llms.txt?
llms.txt is a proposed convention: a plain-text markdown file at a website's root that gives AI systems a curated summary of what the site is, what it claims, and which pages matter. It does for AI assistants roughly what robots.txt does for crawlers and sitemap.xml does for search engines – except it describes meaning, not just structure.
What goes in one
- A one-paragraph description of the organisation or site.
- The key verifiable facts – the claims you'd want an AI to repeat accurately.
- An annotated list of the pages worth reading, with links.
You can read ours at earnedbydesign.com/llms.txt – it's the fastest way to understand the format.
Should you publish one?
Honest answer: adoption by AI providers is still uneven, and nobody can promise a given model reads the file today. But it costs minutes to produce, it can only help models describe you accurately, and it doubles as a useful discipline – forcing you to state, in one page, exactly what you want machines to know about you. We publish one for ourselves and recommend clients do the same, with expectations set accordingly.
Common questions
Does Google use llms.txt?
There's no confirmed use by Google. The file is aimed at AI assistants and their crawlers, and adoption across providers is still uneven – publish it for accuracy, not guarantees.
Where does the llms.txt file go?
At your site root – yourdomain.com/llms.txt – as a plain markdown text file.
Is llms.txt the same as robots.txt?
No. robots.txt controls which crawlers may access which paths; llms.txt describes what your site is and which pages matter. One is access control, the other is a curated summary.