Robots.txt tells crawlers what they can access. LLMS.txt tells them what they can do with what they find. This distinction — between access control and usage control — is the fundamental innovation of llms.txt.
The LLMS.txt File Format
LLMS.txt is a Markdown file at yourdomain.com/llms.txt. It gives AI language models a machine-readable summary of your site purpose and content permissions.
Minimal Valid Example
# My Tech Blog > A blog covering software engineering and AI tools > for professional developers. ## Permissions Training Allowed: No Commercial Use: No Citation Required: Yes ## Contact licensing@mytechblog.com
Full Enterprise Example
# The Financial Times (Example) > Premium financial journalism. 500+ staff journalists. > Target: Finance professionals, investors. ## Permissions Training Allowed: No Commercial Use: No Citation Required: Yes Attribution Format: "Source: [Title], FT, [Date]" ## LLM Rules - GPTBot: Blocked - PerplexityBot: Allowed with citation ## Content Sections - /news/ — Breaking financial news - /analysis/ — Market analysis - /data/ — Market data (no redistribution) ## Links - [Sitemap](https://ft.com/sitemap.xml) --- Last Updated: 2025-01-15
SEO Benefits of LLMS.txt
LLMS.txt can actively improve your SEO. The site description helps AI retrieval systems identify you as an authoritative source. Content category links add an internal linking signal. The update-frequency field helps crawlers understand how often to revisit.
Implementation Across CMS Platforms
WordPress: Create the file at your root using cPanel File Manager or FTP.
Shopify: Online Store > Themes > Edit code > Add new root file.
Next.js/Gatsby: Place in the public folder — served automatically.
