ai-visibility-audit

Build a valid llms.txt in a minute

Fill in your site name, a one-line summary and the pages that matter, and this page writes the file in the shape the llms.txt proposal asks for. Everything runs in your browser; nothing is sent anywhere.

Generator

The form is pre-filled with a worked example for a fictional company so you can see the shape before you type. Replace the values with your own; the output updates as you go.

Your site

The site name becomes the H1 and the summary becomes the blockquote. Keep the summary to one sentence.

Pages

One row per page. Rows with the same section name are grouped under one heading, in the order you first use each name. Tick a row as optional to move it into the final Optional section.

0 characters, 0 lines

    How to publish it

    The file only counts if it sits at the site root and is served as plain text. Four steps, then verify with the audit tool.

    1. Upload to the rootSave the output as llms.txt and put it next to robots.txt and sitemap.xml, so it is reachable at /llms.txt. On GitHub Pages that means the folder the site is published from.
    2. Serve it as textThe content type should be text/plain or text/markdown, UTF-8, with an HTTP 200. Most servers do this for a .txt file with no extra configuration.
    3. Check the headersRun curl -I https://your-site/llms.txt and confirm a 200 status and a text content type. A redirect to the home page, a 404 or an HTML content type all mean it is not published yet.
    4. Verify with the auditRun python ai_visibility_audit.py https://your-site and look for the llms_txt check under GEO. It confirms the file exists, starts with an H1, has a summary line and that the links resolve.

    The audit tool itself is at servia-tech.github.io/ai-visibility-audit and the source, including this page, is on GitHub. If you want the full text of your key pages available too, publish an llms-full.txt beside it.

    Frequently asked questions

    Short, honest answers. The same questions are marked up as FAQPage structured data on this page.

    What is llms.txt?

    llms.txt is a plain Markdown file at the root of a website, proposed by Jeremy Howard in September 2024, that gives AI assistants a short summary of the site and a curated list of its most useful pages. It starts with an H1 naming the site, then a blockquote summary, then H2 sections that each list links with a one-line description.

    Do I need an llms.txt?

    Not strictly. No major AI company has confirmed that its crawlers or assistants read llms.txt, so it is not a ranking lever. It costs a few minutes, some documentation tools and agents do read it, and writing one forces you to decide which pages matter. Treat it as a cheap courtesy to machines, and fix robots.txt, firewall blocks and structured data first.

    Where does the file go?

    At the root of the site, so it is reachable at https://your-site/llms.txt, served with a text/plain or text/markdown content type and an HTTP 200. Keep it in the same place as robots.txt and sitemap.xml. You can also publish llms-full.txt beside it with the full text of your key pages.

    Does Google use llms.txt?

    No. Google's search advocates have said that Google Search does not use llms.txt, and AI Overviews rely on the ordinary Googlebot crawl, robots.txt and structured data. Publish it for the assistants and tools that may read it, but do not expect it to change your Google results.