Publish llms.txt for agent retrieval
Add a root /llms.txt file that tells AI agents what the site is, which URLs matter, and how to interpret the content.
Why this can grow a startup
AI agents often need compact context before deciding which pages to fetch. A concise Markdown index reduces ambiguity, points models to authoritative URLs, and makes the catalogue easier to cite or summarize without forcing the model to infer the whole product from JavaScript-rendered pages.
Company example
The llms.txt proposal standardizes a root Markdown file with a short project summary and curated file lists for model and agent consumption.
Source and metric
Source: llmstxt.org
Source discovered: May 19, 2026
When to use it
Use this when SEO, AI Search, Content is relevant to pre-launch, 0-100, 100-1K and you can run a bounded test with a free budget.
When not to use it
Do not use it as a substitute for customer evidence, a clear owner, or a measurable stop condition. Local platform rules and market behavior still need checking.
Founder checklist
- Read llmstxt.org and identify what is directly supported.
- Choose one channel context: SEO, AI Search, Content.
- Define the test around one observable customer behavior.
- Set an owner, evidence window, and stop condition before launch.
Explore the context
Apply this with an operator
Turn isolated search tactics into a crawlable visibility system tied to demand and proof.