--- title: llms.txt sidebarTitle: llms.txt description: Every Jamdesk site generates llms.txt and llms-full.txt automatically. AI tools use these files to understand your documentation. --- If you want AI tools like ChatGPT, Claude, or Copilot to give accurate answers about your product, they need structured access to your docs, not just whatever made it into their training data. Every Jamdesk site generates `llms.txt` and `llms-full.txt` following the [llmstxt.org](https://llmstxt.org) spec. AI tools read these files instead of crawling individual pages. ## What Jamdesk Generates | File | Content | |------|---------| | `llms.txt` | Page titles, descriptions, and URLs (a structured table of contents) | | `llms-full.txt` | Complete documentation content in a single file | Jamdesk generates both at build time and serves them from the same CDN as your docs. ## Verify Your Files Check that your files exist after your first build: If your docs are at the root of your domain (e.g., `docs.acme.com` or `acme.jamdesk.app`): ```bash curl https://docs.acme.com/llms.txt curl https://docs.acme.com/llms-full.txt ``` If your docs are under `/docs` on your main site (like this site at `jamdesk.com/docs`): ```bash curl https://jamdesk.com/docs/llms.txt curl https://jamdesk.com/docs/llms-full.txt ``` ## File Format The `llms.txt` file lists every page with its title, description, and URL: ```text # Your Project Documentation > Documentation for Your Project ## Pages - [Getting Started](https://your-project.jamdesk.app/getting-started): Set up your first project in 5 minutes - [Authentication](https://your-project.jamdesk.app/authentication): How to authenticate API requests - [Configuration](https://your-project.jamdesk.app/configuration): Configure your project settings ``` The `llms-full.txt` file contains the complete Markdown content of every page, concatenated with page boundaries marked by headings. ## How It's Built - Generated at build time alongside your HTML - Served from CDN with the same cache policy as your docs - Updates automatically on every build - No configuration needed; all pages are included by default ## AI Crawlers Jamdesk's default `robots.txt` allows all major AI crawlers (Claude, ChatGPT, Copilot, Gemini). Your documentation is accessible to AI tools out of the box. `sitemap.xml` lists URLs for search engines to crawl and index. It doesn't include any content, just links and metadata like last-modified dates. `llms.txt` is designed for AI models. It includes page titles, descriptions, and (in `llms-full.txt`) the actual content. AI tools can read the full file to understand your documentation without making multiple HTTP requests. ## What's Next? Built-in chat assistant for visitor questions Let AI tools search and query your docs interactively Fetch raw Markdown for individual pages