An llms.txt file is a plain-text file at your domain root, at yourdomain.com/llms.txt, written to tell AI assistants what your business is, in your own words. It is a proposal modeled on robots.txt, not a standard. As of September 2026 no major AI platform has documented reading it, and an Ahrefs study (15 Jun 2026, 137,210 domains) found 97% of llms.txt files got zero requests in May 2026.
- A plain-text file at yourdomain.com/llms.txt.
- It tells AI what you are, in your words, not guesses.
- Cheap to publish, and a fact sheet you control.
- No major AI platform has documented reading it (September 2026).
The basics: what an llms.txt file is
When an AI assistant tries to describe your business, it assembles a picture from whatever it can find: your homepage, scattered mentions, old listings, sometimes contradictory facts. If that picture is fuzzy, the model hesitates, and models do not confidently recommend what they are unsure about. An llms.txt file fixes the fuzziness at the source. It is a single plain-text file, written in simple Markdown, that states clearly who you are, what you do, who you serve, your proof, and where to verify it.
The name and idea echo robots.txt, the file that tells search crawlers what they can access. llms.txt does the parallel job for language models: a predictable file, at a predictable address, written to be read by machines that assemble answers.
Why it matters for AI visibility
Here is the honest framing, because there is hype to cut through. An llms.txt file is not a magic ranking factor. You can be cited by AI without one, and having one does not guarantee citation. Google said in June 2026 that it is not needed for Google Search, and John Mueller called it "purely speculative for now" on 2 Jun 2026. Ahrefs (15 Jun 2026, 137,210 domains) found 97% of llms.txt files received zero requests in May 2026.
So the value today is internal. Writing it is a useful check: one plain list of your facts, compared line by line with your pages, schema and profiles, the places AI systems do read. The pages stay the source; the file copies them. Keep it because it is cheap and harmless. Do not count it as a visibility lever.
What goes in a strong llms.txt
A weak llms.txt is a thin paragraph that says nothing. A strong one answers the questions a buyer, and therefore a model, actually has.
- Summary: who you are, in the terms the model should match you on.
- What makes you different: a differentiator a competitor cannot copy.
- Who it is for: the buyer and the problem, in their words.
- Proof with mechanism: results, why they happened, and where to verify.
- FAQ: the exact questions buyers ask, answered plainly.
- Authority signals: the hard-to-fake facts that build trust.
- Contact and verification links: where the model can confirm it all.
If you want to see one in the wild, mine is public at yossaumar.com/llms.txt. I keep it as a copy of the facts my pages and schema state. The pages are what AI search actually reads.
The advanced layer
- Write it for the question, not the brochure. Each section should answer a real buyer question, because that is what a model is trying to satisfy. Marketing language gets ignored; clear facts get used.
- Mirror your entity. The names, categories and claims in your llms.txt should match your schema, your entity and your site exactly. Contradictions cost you trust.
- Make claims verifiable. A model trusts what it can confirm. Link to the third-party sources, profiles and proof that back your claims, so the file is checkable, not just assertive.
- Keep it current. Stale facts in an llms.txt are worse than none, because they actively mislead. Treat it as a living file, not a set-and-forget.
- Pair it with an HTML version. A plain file is for crawlers; a human-readable page covering the same ground is indexable and reaches the surfaces a raw file does not. Doing both gives you double coverage.
Common questions
Does an llms.txt file actually help with AI visibility?
Not measurably, as of September 2026. No major AI platform has documented reading it, and Ahrefs found 97% of 137,210 llms.txt files got zero requests in May 2026. Google says it is not needed for Search but fine to keep. Keep one if it is cheap to maintain, and put the real effort into pages, schema and third-party mentions.
Where does the llms.txt file go?
At the root of your domain, reachable at yourdomain.com/llms.txt, the same way robots.txt sits at the root. That predictable location is part of the proposal, though no major AI platform has documented fetching it as of September 2026.
What format should llms.txt use?
Plain text in simple Markdown. Clear headings, short statements, and links to verify claims. That format comes from the llms.txt proposal. No AI platform has published evidence that it changes how models use your content.
Is llms.txt the same as robots.txt?
No, they do different jobs. robots.txt tells crawlers what they may access. llms.txt gives AI models a clear summary of what your business is. robots.txt is a standard the major crawlers document honoring. llms.txt is a proposal no major AI platform has documented reading as of September 2026.
Want to see what AI reads about you?
Send me your business and category. I will check what AI currently understands about you, with or without an llms.txt, and where it goes wrong. Free.
Run my visibility check