How to use the llms.txt generator
- Enter your site name and a one-sentence summary. Write it as a plain statement of what the site is and who it is for.
- Add sections such as Docs, Products or Guides, and list your most useful pages as Title | URL | description.
- Use an Optional section for secondary pages. Keep the file short and curated, not a copy of your sitemap.
- Download the file and upload it to your site root as /llms.txt.
What llms.txt is
llms.txt is a proposed convention, published at llmstxt.org, for a Markdown file at the root of a site that gives large language models a concise overview and links to the pages worth reading. It starts with an H1 title, an optional summary in a blockquote, then H2 sections containing bullet lists of links, each optionally followed by a short description.
Does llms.txt help rankings or AI citations?
There is no evidence that it does. llms.txt is not a Google ranking factor, and Google has said that no special files or markup are needed to appear in its AI features. No major search engine or AI assistant has confirmed that it reads llms.txt when choosing what to cite. Some developer tools and coding assistants do consume it, which is where it is most useful today, particularly for documentation sites.
So treat it as a low-cost courtesy, not a growth tactic. What reliably helps visibility in AI answers is the same as for search: clear, accurate, well-structured pages that are crawlable and worth citing.
What to put in the file
- A clear summary that states what you do without marketing language.
- Your best pages, such as key guides, product docs, pricing and policies, rather than every URL.
- Short descriptions that tell a model what each link contains.
- An Optional section for pages that can be skipped when context is limited.
llms.txt vs robots.txt vs sitemap.xml
robots.txt controls which crawlers may fetch what. A sitemap lists every URL you want indexed. llms.txt is a short, human-curated reading list. They do different jobs and do not replace each other.
An example llms.txt file explained
A small example shows how the format fits together. The file starts with a single H1 line holding the site name. A blockquote under it gives a one or two sentence summary. Then come H2 sections such as Guides or Products, each followed by a bulleted list of links in the form: hyphen, link in square brackets with the page title, the address in parentheses, a colon and a short description.
The summary and the descriptions do most of the work. They tell a language model what each page contains, so it can choose which to read first when its context window is limited. Write them as plain statements of fact, not slogans. "Step by step guide to setting up redirects in Nginx" is more useful than "The ultimate redirect resource".
Which sites benefit most
The convention was designed with documentation and developer tools in mind. If people use AI coding assistants to work with your product, a clean index of your docs can help those tools find the right page quickly. Technical documentation, API references, open source projects and software help centers are the clearest fit.
For a small business site, a shop or a personal blog, the benefit is uncertain. It costs little to publish, so it is harmless, but do not expect it to change how often you are mentioned in AI answers. Spend the same hour improving your most important pages and making sure they can be crawled.
How to keep the file useful over time
An outdated index is worse than none. Add a reminder to review the file whenever you publish or retire an important page. Remove links that redirect or return errors, and update descriptions when a page changes purpose.
Keep the list short. Ten to thirty carefully chosen links beat a dump of every URL, because the point is curation. If you want a complete list of pages for search engines, that is the job of your XML sitemap, not of llms.txt.
What actually helps visibility in AI answers
AI search products and assistants pull from pages they can crawl, understand and trust. The practical steps are the same ones that help in classic search: allow reputable crawlers in your robots.txt, publish clear and accurate pages, use descriptive headings, cite sources, keep facts consistent across the site and mark up your content with sensible structured data.
Original information is the strongest lever. Data, examples and experience that other pages do not have give an assistant a reason to quote you. Run the free SEO audit to check the technical foundations, then put your effort into content worth citing.
A short checklist for your llms.txt
- Start with the site or project name as a single H1 heading.
- Add a one or two sentence summary as a blockquote.
- Group links into clear H2 sections with meaningful names.
- Give every link a short factual description.
- Keep the list curated: fewer than about thirty links for most sites.
- Check that every link returns a normal page and not a redirect or error.
- Upload it to the root of your domain and open it in a browser to confirm.
Revisit the file whenever your site structure changes, and treat it as a small piece of documentation that you maintain, not as a ranking tactic.
Frequently asked questions
Is llms.txt required?
No. It is an optional, unofficial convention. Sites without it are not penalised.
Does Google use llms.txt?
Google has said it does not use it for rankings and that AI features need no special markup. Do not expect an SEO benefit.
Where do I put the file?
At the root of your domain, so it loads at https://example.com/llms.txt.
How is it different from a sitemap?
A sitemap is an exhaustive list for crawlers. llms.txt is a short curated guide in Markdown aimed at language models.
Is my content uploaded?
No. The file is generated in your browser.