ChatGPT, Claude and Perplexity increasingly read a site's /llms.txt to work out what it is and which pages matter. Fill this in, copy the file, drop it at your site root.
Fill in the form above and press Generate.
Upload it to https://yoursite.com/llms.txt — the root, same place as robots.txt. Serve it as text/plain.
llms.txt. The Pro Pack gets you a good one: four annotated real-world templates (SaaS, ecommerce, docs, local business), the llms-full.txt pattern, a 28-point audit checklist, and copy-paste robots.txt rules for every major AI crawler. See what's in it →
A plain-Markdown file at your site root that gives language models a curated, low-noise summary of your site: what it is, the facts you want stated correctly, and links to the pages worth reading. It is the AI-era sibling of robots.txt and sitemap.xml — where robots.txt says what crawlers may read and sitemap.xml lists everything, llms.txt says what's actually worth reading and what the facts are.
# H1 — the site name — then a > blockquote summary. That header shape is the convention parsers expect.## sections. Put anything non-essential under a section literally named ## Optional — it's the documented signal that a page can be skipped under a tight context budget.text/html, or putting it at /docs/llms.txt instead of the root.robots.txt and then wondering why nothing reads the file.For people doing this across several sites or for clients. You get: an annotated llms.txt template with worked examples for SaaS / ecommerce / docs / local business, a longer llms-full.txt pattern, a 28-point AI-search readiness audit checklist, and the robots.txt crawler-allowlist snippets for GPTBot, ClaudeBot, PerplexityBot and Google-Extended.
Delivery: emailed to your Stripe receipt address within 24 hours. The generator above stays free forever — you don't need this to use it.