What is llms.txt?
llms.txt is a proposed standard for a plain markdown file at yoursite.com/llms.txt that tells large language models what a website is about and where its most useful pages are. Think of it as a curated reading list for AI systems, not a set of access rules.
The format was proposed in 2024 by Jeremy Howard of Answer.AI. A typical file opens with the site name as an H1 heading and a short summary in a blockquote, followed by sections of links with one line of context per page. Some sites also publish an llms-full.txt that contains the full text of their key pages.
It is easy to confuse with robots.txt, but the two do different jobs. robots.txt tells crawlers what they may fetch. llms.txt only suggests what is worth reading and blocks nothing.
How much llms.txt matters for AI visibility
The idea makes sense. AI systems work with limited context, and a clean summary with direct links is easier to process than menus, cookie banners and scripts. Writing a good llms.txt also forces you to state plainly what your company does, which helps every reader, human or machine.
Be realistic about the effect, though. Support from AI companies is limited and uncertain, and Google has said it does not use the file for Search. It is not a ranking factor and no substitute for crawlable pages, access for AI crawlers or content worth citing. Treat it as a cheap, optional extra.
How to create an llms.txt file
Write a two or three sentence summary of who you are, what you offer and for whom.
List your most important pages, such as products, pricing, documentation and key guides, with one factual line each.
Use absolute URLs and plain markdown, and publish the file at the root of your domain.
Keep it up to date and make sure its facts match your structured data and About page.
Check your server logs to see whether AI crawlers request it. If none do, keep the effort small.
Trackbase publishes its own file at trackbase.ai/llms.txt, covering the English and Dutch site in one document. To see which AI crawlers visit your site and what they read, use Crawler Analytics.
Examples of llms.txt
A B2B payroll software vendor lists its product overview, pricing page, security page and API documentation, each with one descriptive line.
A Dutch bicycle webshop links to its main category pages, its delivery and returns policy and its frame size guide, and leaves out filter and cart URLs.
A developer tool publishes an llms-full.txt with its complete documentation, so a coding assistant can load everything in one go.
A marketing agency keeps a short file with its services, case studies and contact page, and reviews it every quarter.
Frequently asked questions
Does llms.txt improve my visibility in ChatGPT or Google?
Do not expect it to. Google has said it does not use llms.txt for Search, and other AI companies have not confirmed that they rely on it. Your AI visibility still depends on crawlable pages, clear content and mentions on sources that AI models trust. Treat llms.txt as a low-cost extra that documents your site well, not as a strategy.
What is the difference between llms.txt and robots.txt?
robots.txt is an access file: it tells crawlers which parts of a site they may or may not fetch, and well-behaved bots follow it. llms.txt is a content guide: it summarizes the site and points language models to its most useful pages, but it cannot block or allow anything. Never list pages in llms.txt that robots.txt blocks.
What should an llms.txt file contain?
Start with your company or site name as a heading and a short, factual summary of what you do. Then add sections with links to your most important pages, such as products, pricing, documentation and key guides, each with one line of context. Leave out login pages, filters and thin content, and update the file whenever your offer changes.