Full Answer

The llms.txt file sits alongside robots.txt and sitemap.xml as part of a site's machine-readable discovery layer. While robots.txt tells crawlers what they may access and sitemaps tell them what pages exist, llms.txt tells AI systems what the site is about and how to interact with it meaningfully.

The file uses a simple structured format to declare: the site's purpose and primary offerings, the content taxonomy (product categories, blog pillars, resource types), API endpoints or feeds available for programmatic access, preferred citation format, and any usage guidelines for AI systems consuming the content. For a WooCommerce store, this might include product category structure, the WooCommerce REST API endpoint, structured data formats in use, and content licensing terms.

The practical benefit is discoverability speed. When an AI shopping agent evaluates whether to include a store in product recommendations, it can read the llms.txt file in a single request and understand the store's inventory scope, data accessibility, and content organisation. Without the file, the agent must crawl multiple pages, parse HTML, and infer the store's structure — a process that is slower, more error-prone, and often abandoned in favour of stores that provide the information upfront.

For WordPress and WooCommerce sites, creating an llms.txt file is a low-effort task with outsized potential impact. The file can be generated from existing site data — product categories from WooCommerce, content pillars from the blog taxonomy, and API documentation from WooCommerce's built-in REST API. Combined with complete product schema markup and a clean sitemap, the llms.txt file completes the three-layer AI discoverability stack that positions a store for visibility in the emerging agent-driven commerce landscape.