Generative Engine Optimization Updated 2026-07-04

LLMs.txt

LLMs.txt is a proposed convention: a plain markdown file served at the root of a website that gives large language models a curated summary of the site's most important content. It helps AI systems find, understand, and use the right pages at answer time instead of parsing cluttered HTML.

Definition

The file lives at /llms.txt and is written in markdown: a short description of the site followed by organized links to key pages, often with one-line summaries. Where robots.txt tells crawlers what they may not access, LLMs.txt does the opposite job: it hands AI systems a prioritized reading list. The format was proposed in 2024 by Jeremy Howard of Answer.AI and has since been adopted by many documentation-heavy sites.

Adoption is voluntary on both sides. Publishing the file costs little, but no major AI provider has committed to reading it systematically, so treat it as a low-cost hedge rather than a guaranteed channel. It pairs naturally with clean information architecture: if a site cannot produce a sensible LLMs.txt, its content hierarchy probably confuses machine readers too.

Why it matters for AI visibility

LLMs.txt is part of a broader shift toward publishing for machine readers as well as human visitors. Sites that maintain one signal which pages carry their canonical answers, which is exactly what an AI assistant needs when deciding what to cite. Even while provider support remains inconsistent, the exercise forces clarity about which pages should represent the brand in AI answers.

Related terms