Paste your website. We crawl up to twenty pages, then write an llms.txt in the standard layout from what is actually there. Every link is checked against the crawl, so nothing is invented. Review it, edit it, download it and upload it to the root of your site.
llms.txt is a plain Markdown file served at the root of a website (yoursite.com/llms.txt) that gives AI assistants a curated summary of the site: what the company does, which pages matter, where the product, contact and policy pages are. It was proposed in 2024 as the AI-era counterpart to robots.txt and sitemap.xml, and a growing number of AI crawlers fetch it before they read anything else.
The format is deliberately simple: an H1 with the site name, a blockquote with a one-paragraph summary, then H2 sections each holding a bullet list of links with a one-line description. Because it is Markdown, an assistant can read it in a single request and understand the site the way a well-briefed human would, instead of reconstructing it from dozens of pages of navigation, scripts and footers.
This generator builds the file from your real pages. We crawl the homepage, your sitemap sample and the pages linked from them, collect each page's title, description and heading, and ask our writing model to sort them into About, Key pages, Products / Services, Contact and Policies. The model only sees that inventory, and every link in its output is checked against the URLs the crawl saw, so pages it never visited cannot appear.
Treat the result as a first draft: tighten the summary, remove pages you do not want highlighted, add any that the crawl missed. Then upload the file to your web root so it answers at /llms.txt with a text/plain or text/markdown content type. Results are cached for 24 hours per domain. If you would rather we maintain it, together with the structured data and the pages that get you cited, that is part of every Redlift plan.
At the root of your domain, next to robots.txt, so it answers at https://yoursite.com/llms.txt. On WordPress, upload it to the public_html folder or use a plugin that serves root files; on Shopify or Webflow, add it as a static file or a redirect to a hosted copy; on a custom site, add it to the public directory.
Do ChatGPT and Claude recommend you? Run five buyer prompts across the AI engines and see who gets named instead.
OpenCrawl your site and score it for answer-engine optimization: AI crawler access, llms.txt, structured data and indexability.
OpenBuild valid JSON-LD for Organization, LocalBusiness, Product, FAQPage and Article, with validation before you paste it.
Openllms.txt, structured data, crawler access and the content AI engines cite are part of every Redlift plan.