# Does llms.txt actually work? What the server logs say in 2026 > Google says no AI system uses llms.txt. A 137,210-domain log study found 97% of the files got zero requests. Who does read them, and whether to ship one. - URL: https://www.agentskillpacks.com/blog/does-llms-txt-actually-work - Author: İsmail Günaydın - Published: 2026-09-19 - Updated: 2026-09-19 ## Quick answer Not for AI search visibility, going by the public evidence in 2026. Google's AI features guide says you need no AI text files to appear in AI Overviews, and an Ahrefs log study of 137,210 domains found 97% of llms.txt files got zero requests in May 2026. Coding agents like Claude Code do read the file, and it takes minutes to write, so ship it as a courtesy, not as a tactic. I serve an llms.txt on this site. It is about 14 KB and lists all 19 products with their prices. I also built a free [llms.txt generator](/llms-txt-generator). So I have every reason to want the answer to this question to be yes. The evidence says mostly no. ## Does llms.txt help you show up in ChatGPT, Perplexity, or AI Overviews? Not in any way anyone has measured. The biggest dataset so far is an [Ahrefs study of 137,210 domains](https://ahrefs.com/blog/llmstxt-study/), published on June 15, 2026. In May 2026, 97% of the llms.txt files it tracked received zero requests of any kind. Of the requests that did arrive, only 19.5% came from AI bots. The search engines say the same thing. Google's [AI features guide](https://developers.google.com/search/docs/appearance/ai-features) states that you do not need new machine-readable files, AI text files, or markup to appear in its AI features. In June 2025, Google's John Mueller [wrote on Bluesky](https://www.seroundtable.com/google-ai-llms-txt-39607.html) that "no AI system currently uses llms.txt", and added that your server logs make it obvious. ## What is llms.txt, and who proposed it? llms.txt is a Markdown file at the root of a site that gives language models a short, curated map: what the site is, which pages matter, and where the plain-text versions live. Jeremy Howard published the [proposal at llmstxt.org](https://llmstxt.org) on September 3, 2024. It is a proposal, not a standard. No standards body has adopted it, and no search engine has promised to read it. The idea is sound. HTML is noisy, context windows are finite, and a site owner knows better than a crawler which ten pages matter. The problem is not the idea. The systems people want citations from have simply not opted in. ## Who actually reads llms.txt? Mostly bots that are not AI tools. In the Ahrefs data, 77% of the bots fetching llms.txt were SEO audit tools, tech profilers, and other crawlers. Among AI tools, agents lead: aside from GPTBot, at 4.51% of requests, and one agent-infrastructure bot, Claude Code out-fetched every AI retrieval bot, every AI assistant, and every AI training crawler. That pattern fits how people use these tools. A developer tells Claude Code or Cursor to read a library's docs, and the agent looks for the curated version first. Anthropic serves one for [its own developer docs](https://platform.claude.com/docs/llms.txt) for exactly this reason. If your buyers are developers working inside an AI coding tool, llms.txt reaches them. If your buyers ask ChatGPT for a recommendation, it probably does not. ## So is llms.txt worth shipping? Yes as a courtesy, no as a visibility tactic. Here is how I weigh it: | Question | Answer | | -------------------------------------- | ---------------------------------------------- | | Cost to write | Minutes with a generator | | Cost to serve | None, it is a static text file | | Measured effect on AI search citations | None found in public data so far | | Who benefits today | Developers pointing coding agents at your site | | Risk | Near zero, if it matches your real pages | The one real risk is drift. An llms.txt that lists old prices or a dead refund policy hands every agent that does read it the wrong facts. If you ship one, keep it next to the pages it describes and update both in the same change. The [line-by-line walkthrough of ours](/blog/toolgenx-robots-and-llms-txt-explained) shows what goes in it. ## What moves AI citations instead? The things AI engines demonstrably fetch: your actual pages. That means a robots.txt that lets the search bots in (OAI-SearchBot, PerplexityBot, Googlebot), content that renders without JavaScript, and passages that answer one question cleanly. The [AI crawler checker](/ai-crawler-checker) tests the first part in a few seconds. The [GEO guide for small shops](/blog/geo-seo-for-small-shops-what-moves-the-needle) covers the rest. I am keeping my llms.txt. It is cheap, it helps developers who point agents at this site, and it will be ready if a search engine ever opts in. I just do not count it as a reason anyone finds us. ## FAQ ### Does Google use llms.txt for AI Overviews? No. Google's AI features guide says you do not need to create new machine-readable files, AI text files, or markup to appear in its AI features. Being crawled and indexed by Googlebot like any other page is the requirement. ### Which AI tools actually read llms.txt? Mostly not AI tools at all: in Ahrefs' May 2026 data, 77% of the bots fetching llms.txt were SEO auditors, profilers, and other crawlers. Among AI tools, coding agents stand out. Claude Code out-fetched every AI retrieval bot, assistant, and training crawler except GPTBot and one agent-infrastructure bot. ### Is llms.txt an official standard? No. It is a proposal Jeremy Howard published at llmstxt.org on September 3, 2024. No standards body has adopted it, and no major search engine has committed to reading it. ### Should I delete my llms.txt? No need. It costs nothing to serve and helps developers who point a coding agent at your site. Just stop counting it as an AI visibility tactic, and put the hours into crawlable pages and quotable passages.