#llmsmap.me

AI publishing conventions and standards: llms.txt, ai.txt, and robots.txt

llms.txt and ai.txt are emerging conventions rather than formal web standards. These files solve different problems: robots.txt for access, llms.txt for context, llms-full.txt for depth, and ai.txt for usage policy. Publishing them can reduce discovery friction for compatible tools, but it does not guarantee crawling, indexing, ranking, or citation.

Four machine-readable website files provide access, structure, deep context, and usage policy to an AI agent
robots.txtcrawler access
llms.txtcurated context
llms-full.txtdeeper material
ai.txtusage policy

llms.txt

Purpose
A compact, curated overview of a website for language models and AI agents.
Location
/llms.txt
Audience
LLMs, AI assistants, RAG systems, agentic crawlers.

llms-full.txt

Purpose
An expanded text context file for deeper analysis of large documentation or content sites.
Location
/llms-full.txt
Audience
LLMs, RAG pipelines, documentation processors.

ai.txt

Purpose
A policy-style file that explains how AI systems may use, summarize, or train on content.
Location
/ai.txt
Audience
AI crawlers, aggregators, AI product teams.

robots.txt

Purpose
The classic crawler access-control file for search and automated fetchers.
Location
/robots.txt
Audience
Search bots, web crawlers, AI crawlers that respect robots.txt.

Recommended publishing order

  1. Make sure robots.txt allows the crawlers you want to support.
  2. Publish llms.txt as the short canonical guide to the site.
  3. Add llms-full.txt when the site has dense documentation or long-form content.
  4. Use ai.txt if you need to state usage, attribution, or training rules.

Frequently asked questions

Do I need all four files?+

No. Start with a valid robots.txt and a concise llms.txt. Add llms-full.txt for documentation-heavy sites and ai.txt when you need an explicit AI usage policy.

Does llms.txt replace sitemap.xml or Schema.org?+

No. llms.txt provides curated context, sitemap.xml helps discover URLs, and Schema.org describes entities on individual pages. They work best together.

Does publishing llms.txt guarantee AI search visibility?+

No. It removes friction, but visibility still depends on crawl access, original content, citations, technical markup, and each AI product’s retrieval rules.

Where should the files be published?+

Publish them at the host root: /llms.txt, /llms-full.txt, /ai.txt, and /robots.txt. Configure each subdomain separately when it serves distinct content.

AI publishing conventions and standards: llms.txt, ai.txt, and robots.txt — llmsmap.me