Does Google use llms.txt?

Not at the moment. Google has said llms.txt is speculative and that its systems do not currently use it. Other major AI engines have not confirmed using it either. Some documentation platforms and AI tools do read it, so support exists but is partial and early.

How do I create an llms.txt file?

Create a plain markdown file named llms.txt at the root of your domain. Start with an H1 of your site or brand name, add a short blockquote summary, then list your most important pages as markdown links with a brief description of each, grouped under H2 sections. Keep it concise and current.

Is llms.txt the same as robots.txt?

No. robots.txt tells crawlers which URLs they may or may not access. llms.txt does the opposite in spirit: it points AI models toward your most useful content and summarizes it in a clean, readable format. One restricts, the other guides.

Does llms.txt improve AI visibility?

There is no confirmed ranking or citation benefit yet, because major engines have not committed to using it. The upside today is low-cost future-proofing and cleaner content for the tools that do read it. Real AI visibility still comes from quotable content, authority, and earned citations, which you should measure directly.

Where do I put the llms.txt file?

At the root of your domain, so it resolves at yourdomain.com/llms.txt, the same location pattern as robots.txt. Some sites also publish an llms-full.txt with the full text of key pages for models that want the complete content.

What is llms.txt? Definition, format and uses (2026)

llms.txt is a proposed standard file that gives large language models a clean, curated map of your website. Placed at the root of your domain, it lists your most important pages with short descriptions in plain markdown, so an AI model can find and understand your best content without wading through navigation, ads, and scripts. Think of it as a reading list you hand to AI, not a set of rules.

The idea was proposed in 2024 and has spread fast, partly because it is simple and partly because brands are anxious to be understood by AI engines. It is worth knowing what llms.txt does, how to make one, and, just as important, what it does not do yet.

What is llms.txt?

Structure of an llms.txt file: site name, summary blockquote, and sections of links

llms.txt is a single markdown file at yourdomain.com/llms.txt. Its job is to point AI models to your key content and summarize it in a format that is easy to parse. A typical file has a clear structure:

An H1 with your site or brand name.
A short blockquote summarizing what the site is about.
One or more H2 sections (for example Docs, Products, Guides) listing the relevant pages as markdown links, each with a one-line description.

Some sites also publish an llms-full.txt, which contains the full text of the most important pages in one file, for models that want the complete content rather than links to fetch.

The point is signal over noise. A normal web page wraps its content in menus, banners, and code. llms.txt strips that away and says, in effect, here is what matters and here is what it means.

llms.txt vs robots.txt and sitemaps

robots.txt vs sitemap.xml vs llms.txt: restrict crawlers, list all URLs, guide AI to key content

It is easy to lump these together, but they do different jobs.

robots.txt tells crawlers which URLs they are allowed to access. It restricts.
sitemap.xml lists every URL you want indexed, for search engine crawlers. It enumerates.
llms.txt curates and summarizes your best content for AI models. It guides.

A sitemap is a full directory. llms.txt is an edited recommendation list with context. The two complement each other rather than overlap.

How to create an llms.txt file

You can write one by hand in a few minutes.

Create a plain text file named llms.txt.
Add an H1 with your brand name, then a blockquote with a one or two sentence summary.
Add H2 sections for your main content areas.
Under each section, list the key pages as markdown links, each followed by a short description of what the page covers.
Upload it to the root of your domain so it resolves at yourdomain.com/llms.txt.
Keep it current. A stale map is worse than none, because it points models at outdated pages.

Several platforms now generate llms.txt automatically, including some documentation tools and SEO plugins, so check whether your stack already offers it before writing one manually.

Does llms.txt actually work?

This is where honesty matters. Adoption on the publishing side has been quick, but support on the engine side is partial and unconfirmed.

Google has said llms.txt is speculative and that its systems do not currently use it. Other major AI engines have not committed to reading it either. At the same time, some documentation platforms, developer tools, and AI products do consume llms.txt, so it is not useless, it is just early and inconsistent.

So treat llms.txt as low-cost future-proofing rather than a guaranteed visibility lever. It takes little effort, it cannot hurt, and it positions you well if support broadens. What it will not do today is reliably get you cited in ChatGPT or summarized in a Google AI Overview. Those outcomes still come from quotable content, brand authority, and earned citations.

Should you add one?

For most sites, yes, with realistic expectations. The cost is minutes, the downside is near zero, and a clean content map is good hygiene regardless of which engines adopt it. Documentation-heavy sites and software products get the most obvious value, since their content maps cleanly to a link list.

Just do not mistake publishing an llms.txt for an AI visibility strategy. The file is a small technical step. The work that actually moves the needle is making your content easy to quote and earning mentions on the sources AI engines trust. See generative engine optimization for the full picture, and our guide on how to rank on ChatGPT for the practical tactics.

How to measure what matters

Whether or not you publish llms.txt, the real question is whether AI engines mention and cite you. You measure that directly, not by assuming a file did its job. Track a fixed set of prompts across ChatGPT, Perplexity, Google AI Overview, and Google AI Mode, and watch your mention rate, share of voice, and citations over time. That is what Mencoro is built to do, so you can tell whether any change, llms.txt included, actually moved your visibility.

What is llms.txt? Definition, format, and whether it works