Key takeaways
- llms.txt is a plain Markdown file at the root of a website that summarises the business and links to its key pages for AI tools.
- It’s a proposed convention, not an official standard, and not every AI tool reads it.
- It’s quick to add and helps keep your business described consistently, so it’s usually worth doing, but it won’t get you into AI answers on its own.
Where did llms.txt come from?
It was proposed in 2024 as a simple way for websites to give large language models a short, curated guide to their content. Web pages are full of menus, scripts and layout that make them hard for AI tools to read in full, so the idea is to offer a clean summary at a predictable address: yoursite.com/llms.txt.
What goes in the file?
The proposal suggests a heading with the business name, a short summary, a few key facts, then links to the most important pages, grouped under headings, each with a one-line description. It is plain Markdown, readable by people and machines, and some sites also publish a longer llms-full.txt with their key pages’ full text.
What does a simple example look like?
For a clinic, the file might start with the clinic’s name, a two-sentence description of its specialties and location, then the address, phone and opening hours. Below that, a ‘Treatments’ section linking to each treatment page, a ‘Doctors’ section linking to each profile, and a ‘Patient information’ section linking to insurance, prices and booking.
How is it different from robots.txt?
robots.txt tells crawlers what they may and may not access. llms.txt doesn’t grant or block anything; it offers a summary for tools that choose to read it. If you want to control which AI crawlers can access your site, that’s still done in robots.txt.
How is it different from a sitemap?
An XML sitemap lists every page you want search engines to know about, with no descriptions. llms.txt is a short, hand-picked guide to the pages that matter most, with a sentence on each. They do different jobs, and most sites benefit from both.
Will it get you into AI answers?
Not on its own. AI tools rely mostly on your pages themselves, how consistently your business is described across the web, and mentions on sources they trust. llms.txt is a small, low-effort addition to that work, not a shortcut around it.
How do you keep it accurate?
Generate it from the same source as your website, so it updates automatically when pages are added, renamed or removed. A hand-written file that goes out of date can point AI tools at pages that no longer exist. This website builds its llms.txt from the same content as its pages at every deploy.
What are the common mistakes?
- Treating it as a replacement for good pages and a clear entity across the web.
- Listing every page instead of the ones that matter.
- Letting it go out of date.
- Writing it as marketing copy instead of plain facts.