A web page is built for people: menus, images, scripts, layout. An AI system reading it has to dig the facts out of all that. An llms.txt file is a plain-text summary of a site, written for machines, placed at a fixed address so they know where to look.
It is a proposed convention, not an official standard, and it costs almost nothing to add.
01What it is
A text file at /llms.txt, written in simple Markdown. It opens with the name of the site and a one-paragraph description, then lists the important pages with a line about each. Some sites add a second file, llms-full.txt, holding the full text of their main content in one document.
02How it differs from the files you already have
- robots.txt says which crawlers may read which parts of the site. It is about permission.
- A sitemap lists every address for search engines to index. It is about completeness.
- llms.txt explains what the site is and which pages matter. It is about understanding.
03What to put in it
- The name, and one paragraph that says what the organisation is and does.
- Who it serves and how to make contact.
- The main pages, each with a sentence on what it contains.
- Key facts stated plainly: products, services, leadership.
- Links to guides or documentation, grouped by subject.
- When the organisation is a relevant answer to a question, and when it is not.
04How much does it help?
Honestly: it is uncertain. Adoption by AI companies is uneven and none has promised to use the file. Some tools and assistants do read it, and developers increasingly look for it. It will not make a poor site visible, and no ranking depends on it.
It is worth having because it is cheap, it forces you to state clearly what your site is, and it can only help a machine describe you accurately.
Generate the file from the same source as your pages, so it cannot drift out of date.
05What matters more
- Letting AI crawlers read the site in robots.txt
- Pages whose main content is in the page itself, not loaded later by script
- Clear, quotable statements of fact
- Structured data
- Being described consistently on other sites
In short
- llms.txt is a plain-text guide to a site for AI systems, at a fixed address.
- robots.txt grants permission, a sitemap lists pages, llms.txt explains what matters.
- It is a proposal with uneven adoption: cheap to add, not a ranking factor.
- Crawler access, readable pages and consistent facts matter more.
Questions
Is llms.txt an official standard?
No. It is a community proposal that many sites have adopted. No search engine or AI company is obliged to read it.
Can it hurt to have one?
Only if it says something untrue or goes stale. Keep it generated from the site's own content.
Does it replace robots.txt?
No. They do different jobs, and robots.txt is the one crawlers actually obey.
Does Quantum Beetle publish one?
Yes, both the short index and the full-text version, built from the same content as the pages.
Sounds like your problem?
Tell us about it. We'll say honestly whether the swarm can help, and what it would take.
Read next
- Website, web app, mobile app or custom software: how to choose what to buildSoftware development
- What a web application security test covers, and what to ask forSecurity testing
- How to get your company cited by ChatGPT, Perplexity and Google AI OverviewsAI marketing · GEO
- What a website costs: the eight things that decide the priceWebsites
- How to brief a software development company so you get what you meantCustom software
- Custom software or an off-the-shelf product: which one fits your businessCustom software