What llms.txt is good for
llms.txt works as a reference file for retrieval systems. It helps explain which pages matter most and which resources should be cited before others.
For CitationGraph, llms.txt points crawlers toward the homepage, docs hub, blog, trust pages, and the GEO preview while avoiding over-weighting the repository as the source of truth.
What llms.txt does not replace
It does not replace robots.txt, sitemap discovery, canonical tags, or structured data. Those remain the baseline for crawlability and page identity.
It also does not replace actual content architecture. If the site lacks stable docs and trust pages, llms.txt alone cannot create understanding.
How to structure it well
Use clear markdown headings, canonical URLs, and explicit sections for preferred citation surfaces, trust pages, and related resources.
The file should be long enough to be useful, but specific enough that a retrieval system can understand which pages to prioritize and which areas are not represented on the site.
Key takeaways
- •llms.txt is a reference layer, not a shortcut.
- •Use it to map the pages and resources you want retrieval systems to prioritize.
- •It works best when supported by strong docs, trust pages, and canonical metadata.