llms.txt: What It Is and Whether You Need One
llms.txt is a proposed convention: a plain text file at the root of a domain that summarises what the site is and lists the pages worth reading, written for a language model rather than a person. It is a proposal rather than a standard, and Google states that Search does not use files of this kind. It costs about an hour, does no harm, and may one day help. That is the honest position, and anyone selling it as essential is overstating it.
Rated 5.0 from 20 Google reviews · A local SEO agency based in Haywards Heath
Start with what Google says, because it is unambiguous
“You don’t need to create new machine readable files, AI text files, markup, or Markdown to appear in Google Search (including its generative AI capabilities), as Google Search itself doesn’t use them.”
Google Search Central, guide to optimising for generative AI features, updated 10 July 2026
That covers the largest surface by a wide margin. No other major provider documents reading llms.txt from third party sites either. Several of the AI labs publish one for their own documentation, which is often cited as evidence of adoption and is not the same thing at all: publishing a file for your own docs says nothing about whether your crawler reads other people’s.
What the file actually contains
A heading with the site name, a short summary in a blockquote, then linked lists of the pages that matter, grouped by section, each with a one line description. It is markdown in a .txt file, served as plain text from the root of the domain. That is the whole proposal.
# Example Ltd > Independent marketing agency in Sussex. SEO, paid media, content and AI visibility for UK businesses. ## Services - [Search engine optimisation](/services/seo/): technical SEO, content and digital PR - [AI search visibility](/ai-search/): being cited by ChatGPT, AI Overviews and Perplexity ## About - [About us](/about-us/): who we are, where we are, who we work with - [Contact](/contact-us/): how to reach us
What it is not
- It is not robots.txt. robots.txt controls access and is honoured by the major crawlers. llms.txt controls nothing and is honoured by nobody. Confusing the two is common and consequential.
- It is not a ranking signal. There is nothing for it to be a signal within.
- It is not a way to hide anything. Listing your best pages does not deprioritise the rest.
- It is not a substitute for the page being good. A file that points at a badly structured page has pointed at a badly structured page.
The honest state of adoption
As at September 2026 the position is unchanged from a year earlier in the only way that matters: no major provider documents reading it from third party sites, and Google has stated in writing that it does not. Adoption among site owners has grown considerably, which is a fact about site owners rather than about assistants.
The case for doing it anyway is a cheap option on a future in which something like it becomes conventional. An hour of work, no risk, no downside beyond the hour. That is a reasonable trade and it is a very different sentence from the one used to sell it.
If you do write one, write it usefully
- Serve it as genuine plain text at https://yourdomain/llms.txt. Not a redirect, not a rendered page with your site navigation around it.
- Keep it short. Twenty to forty links, not your whole sitemap. The point is selection.
- Write the one line descriptions as descriptions, not as marketing lines.
- Date it, and put a review reminder in the calendar, because a file listing pages that no longer exist is worse than none.
- Check it in a browser after publishing and confirm the content type is text/plain.
A mistake we made ourselves
Until 3 September 2026 our own /llms.txt was not a text file at all. It was a WordPress page rendered with the full site header, footer and navigation, reached through a redirect, and it pointed at a URL that returned a 404. Our redirect log shows it had been requested 74 times since May and had returned HTML on every one of them. It was, in other words, exactly the failure this page warns about, sitting on the site of the agency writing the warning.
It now returns a genuine file with a content type of text/plain, listing thirty-five pages, every one of which was checked and resolves. One imperfection remains and it is fair to name it rather than let you find it: the file is reached through a redirect from the root rather than sitting at the root itself, because moving it needs a change at the hosting level rather than in WordPress. It is on the list for the site rebuild.
We are describing all of that because a supplier who has never published one of their own mistakes is asking you to take their standards on trust. If your own file has the same problem, it takes about ten minutes to check and it is worth doing before anything else on this page.
Frequently asked questions
Related guides
This page is one of our AI search and GEO guides. Start with the complete guide to AI search visibility or see our AI search and GEO services.
- AI crawlers: which to allow and block
- Schema markup for AI search
- How to appear in Google AI Overviews
Browse all AI search and GEO guides. Would you rather we did it for you? Start with an AI visibility audit.
Sources
- Google Search Central. Optimizing for Generative AI Features on Google Search. Updated 10 July 2026. Google’s statement that no machine readable AI text files are needed and that Google Search does not use them.
- llms.txt. The /llms.txt file proposal. Read 3 September 2026. The proposal itself, including the expected file structure and its status as a proposal rather than a standard.
- Google Search Central. Google Common Crawlers. Updated 14 July 2026. The controls that do affect Google’s crawling, as distinct from files that do not.
Every figure on this page was read on the source page listed above. This page is reviewed monthly and the last checked date is updated when it is.
Frequently asked questions
Is llms.txt an official standard?
No. It is a proposal put forward by an individual and adopted informally. It has not been ratified by any standards body and no major AI provider has committed to reading it from third party sites.
Does anyone actually read it?
No major provider documents doing so, and Google states in writing that Search does not use files of this kind. Several AI companies publish one for their own documentation, which is frequently misread as evidence that their crawlers consume other people’s.
Where does the file go?
At the root of the domain, served as plain text with a content type of text/plain. If it arrives as a rendered web page or through a redirect, it is not doing the one thing the proposal asks of it.
What is the difference between llms.txt and robots.txt?
robots.txt is a long established convention that controls crawler access and is honoured by the major crawlers. llms.txt is a recent proposal that summarises a site for a reader and controls nothing. Only one of them changes what happens to your site.
Ask us how your business shows up in AI search
A friendly 15 minute call, no obligation.
or call 01444 523105