Robin Ooi — AI SEO Malaysia
AI Search & GEO

What Is an llms.txt File, and Does It Do Anything?

By Robin Ooi4 min read

The short answer

An llms.txt file is a markdown document at your site root that tells AI systems what your business does and which pages matter, in plain language. It is cheap to add and no major AI provider has committed to reading it, so treat it as low-cost housekeeping rather than a visibility strategy.

Illustration of a plain-text llms.txt file acting as a structured summary of a website for AI systems

What an llms.txt file is

An llms.txt file is a markdown document that lives at the root of your domain, at yoursite.com/llms.txt. It describes what your business does and lists your most important pages with a short explanation of each, written for a machine that has never heard of you.

The idea, proposed by Jeremy Howard of Answer.AI in 2024, is straightforward. HTML pages are full of navigation, cookie banners, scripts and layout markup. A language model working with a limited context window has to wade through all of it. An llms.txt gives it the summary instead, in a format it parses natively.

It is a convention, not a standard. Nobody is obliged to read it. That distinction matters, and I will come back to it.

How it differs from robots.txt and sitemap.xml

These three files get confused constantly. They do completely different jobs.

Three root files, three purposes
FileFormatAnswers the question
robots.txtPlain text directivesWhat are you allowed to crawl?
sitemap.xmlXMLWhat URLs exist and when did they change?
llms.txtMarkdownWhat is this business, and what should you read first?

robots.txt controls access. sitemap.xml handles discovery. llms.txt is about comprehension. It is the only one of the three that tries to explain rather than list.

What goes in one

The structure is loose but the convention is consistent: an H1 with your name, a blockquote summarising what you do, then H2 sections grouping links with descriptions.

  1. H1 with the entity name. Your business or brand, exactly as you want it referred to.
  2. A blockquote summary. Two or three sentences. What you do, who for, where. This is the line most likely to be reused verbatim, so write it properly.
  3. Grouped link sections. Services, locations, tools, about. Each link gets a one-line description of what is on that page and why someone would want it.
  4. Optional detail. Pricing ranges, founding date, credentials, service areas. Facts that answer the questions a buyer asks before they trust you.

Keep it factual and keep it short. Marketing copy performs badly here. The file exists to be parsed, not to persuade. Anything you would not want quoted back at you out of context should not be in it.

Ours sits at robinooi.com.my/llms.txt if you want a working example to copy the shape from.

The honest answer on whether it works

No major AI provider has publicly committed to reading llms.txt as a ranking or retrieval input. OpenAI, Anthropic and Google have not announced support for it as a signal. Anyone telling you it guarantees AI citations is selling something.

What the evidence actually supports is different. Citation depends overwhelmingly on retrieval position, which depends on domain trust and search visibility. That is the finding from the AirOps and Kevin Indig study across 16,851 ChatGPT queries, and I went through the implications in how ChatGPT decides which sources to cite. A text file at your root does not change your trust profile.

So why add one? Because the cost is close to zero and there are two plausible small upsides. If adoption grows, you are already there. And more usefully, writing one forces you to state clearly what your business does and which pages matter, which is an exercise that improves the rest of your site whether or not any machine ever reads the file.

Where to put your effort
ActionEffortRealistic impact on AI visibility
Publish llms.txt30 minutesLow. Cheap insurance, not a lever
Unblock AI crawlers in robots.txt15 minutesHigh if you were blocking them
Add Article and FAQPage schemaA few hoursModerate, once you are already retrievable
Restructure pages to answer firstDaysModerate to high on pages already ranking
Earn editorial mentions on trusted sitesOngoingHighest, and the slowest

Do the top two this week because they take under an hour combined. Do not confuse them with the bottom one, which is the work that actually moves citation share, and which is what an AI SEO engagement is mostly spent on.

Adding one to your site

  1. Write the file in markdown. Aim for under 400 lines, and prioritise ruthlessly. This is a curated index, not a full sitemap.
  2. Save it as llms.txt and place it in your public root, so it resolves at yoursite.com/llms.txt.
  3. Confirm it serves as text/plain or text/markdown. Some hosts will try to download it instead of displaying it.
  4. Use absolute URLs throughout. A relative link in a plain-text file has no reliable base to resolve against.
  5. Update it whenever your services, pricing bands or main pages change. A stale file is worse than none, because it confidently states things that are no longer true.

Frequently asked questions

What is llms.txt used for?

It gives AI systems a plain-markdown summary of what a website is about and which pages matter most, without the navigation, scripts and layout markup that fill a normal HTML page. It is intended to make a site easier for a language model to understand within a limited context window.

Is llms.txt an official standard?

No. It is a community convention proposed by Jeremy Howard of Answer.AI in 2024. No major AI provider has publicly committed to reading it as a retrieval or ranking input, so adoption remains voluntary on both sides. Treat it as optional housekeeping rather than a requirement.

Does llms.txt replace robots.txt or sitemap.xml?

No, they solve different problems. robots.txt controls what crawlers may access, sitemap.xml lists which URLs exist and when they changed, and llms.txt explains what the business is and which pages matter. You should have all three, and none substitutes for another.

Will adding llms.txt get me cited by ChatGPT?

Very unlikely on its own. Research shows citation is driven mainly by retrieval position, which follows from domain trust and search visibility. A text file at your root does not change either. Add it because it costs almost nothing, not because you expect it to move citation share.

Where should the llms.txt file be located?

At the root of your domain, so it resolves at yoursite.com/llms.txt. On most platforms that means placing it in your public or static directory. Check that it serves with a text content type rather than triggering a file download in the browser.

Robin Ooi, AI SEO and online reputation management specialist based in Penang, Malaysia

Written by Robin Ooi

Robin is a Malaysian AI SEO and reputation specialist with more than fifteen years in search. He is the Amazon bestselling author of Your SEO Sucks! and works with MNC and listed company clients across Kuala Lumpur, Penang, Johor and Singapore. Read more about Robin Ooi.

See exactly where you're losing traffic — in 60 seconds

Run the free AI SEO scan on your website. You'll get your visibility score across Google and AI search, plus the top issues costing you leads right now. No sign-up call, no obligation.

Trusted by MNCs and listed companies across Malaysia & Singapore

WhatsApp Robin