Is the llms.txt file really useful for getting cited by AI?
Is the llms.txt file useful for getting cited by AI?
Not much, for now. llms.txt is a 2024 proposal that summarizes a website for AI agents, but Google says it does not need it and, according to Ahrefs, 97% of these files received no requests in May 2026. It costs almost nothing to publish; indexing, content and third-party sources matter far more.
What is the llms.txt file?
llms.txt is a text file placed at the root of a website (/llms.txt), written in Markdown. It was proposed in September 2024 by Jeremy Howard, on llmstxt.org, as a way “to provide information to help agents use a website”: a short introduction, guidance and links to the important pages.
The idea is appealing: give AI assistants a clean summary of the site, instead of letting them work out the essentials from HTML pages full of menus and scripts.
Do AI assistants read llms.txt?
The available data says no, or very little:
- Google does not use it. In its documentation on AI features, Google writes that you don’t need to create new machine-readable files, AI text files or special markup to appear in AI Overviews and AI Mode.
- Crawlers almost never request it. According to an Ahrefs study of server logs from 137,000 domains, reported by PPC Land, 97% of llms.txt files received zero requests in May 2026, and AI retrieval bots accounted for only 1.1% of requests to these files.
Adoption is growing anyway: Originality.ai counted 36,120 llms.txt files in May 2026 on the sites it tracks, up from 4,088 a year earlier. Many websites are publishing a file that crawlers ignore.
Should you publish an llms.txt anyway?
Yes, if it costs you almost nothing, for example if it is generated automatically from your website, like the one on houdour.ma. It can help the AI agents that do read it, and it forces you to state clearly who you are and which pages matter.
No, if you are counting on it to get cited. llms.txt replaces none of the steps that matter.
What actually matters for getting cited?
- A robots.txt that lets AI search crawlers in: OAI-SearchBot for ChatGPT, PerplexityBot for Perplexity, Claude-SearchBot for Claude.
- Indexed pages in Google and Bing, added to their webmaster tools.
- Pages that answer your customers’ questions directly, with sourced facts.
- Structured data that matches the visible text of your pages.
- Mentions on other websites: directories, comparisons, press.
See the detailed guide: How to appear in ChatGPT answers in Morocco
Frequently asked questions
Should I delete my llms.txt?
No. It does no harm and costs almost nothing to maintain if it is generated automatically. Just don't expect results from it, and don't spend on it the time the essentials need: indexing, content and mentions on other websites.
Does llms.txt replace robots.txt?
No. robots.txt tells crawlers what they may crawl, and AI search crawlers respect it. llms.txt is only an optional summary of the site. A robots.txt that blocks OAI-SearchBot, PerplexityBot or Claude-SearchBot makes you invisible, whatever your llms.txt says.