llms.txt is a plain-text Markdown file placed at the root of a website (for example example.com/llms.txt) that gives language models a short summary of the site and a list of its most useful pages. It was proposed by Jeremy Howard of Answer.AI in September 2024. It is easy to add and does no harm, but as of 2026 there is no public evidence that it changes how AI assistants choose sources.
Why it was proposed
Web pages are built for browsers: navigation, scripts, cookie banners and layout code surround the actual content. A language model reading a site within a limited context window has to filter all of that out. The llms.txt proposal offers a shortcut: a single, clean file that says what the site is and where the important content is.
The format
The proposal, published at llmstxt.org, defines a simple structure:
- An H1 heading with the name of the site or project (the only required part)
- A blockquote with a one or two sentence summary
- Optional paragraphs with more detail
- H2 sections, each containing a list of links in the form “[Page name](URL): short description”
- An optional section headed “Optional” for links that can be skipped when space is short
A shortened example:
# Brilad
> SEO, AEO, GEO and AI development consultancy in India.
## Services
- [SEO Services](https://www.brilad.com/services/seo/): Technical SEO, Core Web Vitals, site structure and keyword mapping
- [GEO Services](https://www.brilad.com/services/geo/): AI crawler access, entity consistency and citable content
## AI Search Academy
- [How AI search works](https://www.brilad.com/learn/ai-search-mechanics/): RAG, query fan-out, embeddings and re-ranking
llms-full.txt
llms-full.txt is a companion file that contains the full text of the listed pages in one Markdown document, so a model can read everything without following links. It is useful for documentation sites where a developer wants to paste a whole manual into an AI tool. For a business website it is rarely needed.
The proposal also suggests offering a Markdown version of each page at the same URL with .md added. Few sites outside developer documentation do this.
Who uses it
Adoption is strongest among developer documentation sites, where people often feed documentation directly into coding assistants. Several documentation platforms generate the file automatically, and some AI companies publish one for their own developer docs.
On the other side, no major AI search product has confirmed that it reads llms.txt when deciding which pages to retrieve or cite. Google’s search representatives have said publicly that Google does not use it. AI crawlers do request the file on some sites, which can be seen in server logs, but a request is not evidence that the contents influence answers.
Should you add one?
Our recommendation is yes, with realistic expectations:
- It takes little effort, especially if it is generated automatically from your pages
- It is useful when people paste your site into an AI tool, or when an agent explores your site
- It will not fix crawler blocks, JavaScript rendering problems or weak content, which have far more effect on AI visibility
This website generates its llms.txt from its service pages, guides and latest articles, and refreshes it whenever a page changes. You can see it at brilad.com/llms.txt.
How to add llms.txt to WordPress
- Decide which pages matter most: services, key guides, pricing, contact.
- Write a one-line description for each. The page excerpt is a good source.
- Either upload a static llms.txt file to the site root, or generate it from WordPress so it stays up to date. Several plugins do this, and a theme or small custom plugin can do it too.
- Check that your caching or security plugin does not block or redirect the file.
- Open the URL in a browser to confirm it returns plain text.
Frequently asked questions
Is llms.txt the same as robots.txt?
No. robots.txt tells crawlers what they may and may not fetch. llms.txt only suggests what is worth reading. It has no power to allow or block anything.
Can llms.txt get my site cited by ChatGPT?
There is no evidence that it does. Citations depend on whether OpenAI’s search crawler can reach your pages and whether those pages answer the question well.
Will it hurt my SEO?
No. Search engines treat it as an ordinary text file.