Glossary
What is llms.txt?
llms.txt is a plain Markdown file placed at the root of a website (yoursite.com/llms.txt) that gives large language models a short summary of the site and a curated list of links to its most useful pages.
Where it comes from
The format was proposed in September 2024 by Jeremy Howard of Answer.AI. The idea is simple: web pages are full of menus, scripts and layout that make them slow for an AI model to read, so a site can offer one clean file that says what the company is and where the important information lives.
A typical llms.txt has an H1 with the site name, a short summary in a blockquote, and sections of links, each with a one-line note. Some sites also publish llms-full.txt, which holds the full text of key pages in one file.
What it does not do
llms.txt is a proposal, not an official web standard. It does not control access the way robots.txt does, and major search engines have not said they use it for ranking. Some AI tools and developer products read it, especially for documentation, and support is uneven.
That makes it cheap insurance rather than a growth lever: it takes an hour to write well and does no harm, but it will not fix a site that crawlers cannot read.
Why it matters for B2B websites
B2B companies are often described wrongly by AI assistants: an old product name, a category they left, a missing service. A well-written llms.txt states the current facts in your own words, in one place, with links to the pages that prove them.
Example
- # Company name
- > One-paragraph summary: what you sell, who it is for, where you work
- ## Services, with a link and one line for each
- ## Proof, with links to case studies
- ## Company, with links to pricing, about and contact
How we handle it
We write llms.txt from the same approved copy as the site, so it never contradicts the pages, and update it when services or pages change. pentaclay.com publishes one at /llms.txt. It sits alongside the work that matters more: HTML pages, open robots.txt rules and clear content, which our AI search optimization service covers.
Last updated 15 November 2026
