Does llms.txt help a business show up in AI answers?
Short answer
Not on current evidence. The guidance Google, OpenAI, Anthropic, Perplexity and Microsoft give site owners does not say llms.txt helps a site appear in their AI answers, and Google says you don't need new machine readable files or AI text files for its AI features. llms.txt is an optional proposal whose author says it is used most for software documentation that coding agents read. A local business should start by letting crawlers in and keeping its facts in plain page text.
The site-owner guidance from Google, OpenAI, Anthropic, Perplexity and Microsoft does not say llms.txt helps a site appear in AI answers. Google says its AI features need no special files. The file is easy to publish, but a local business should see to crawler access and clear pages first.
What is llms.txt?
llms.txt is a proposal for a Markdown file at the root of a website, at /llms.txt, that gives AI agents a short summary of the site and links to its key pages. The proposal was first published in September 2024, and a second version followed in August 2026. Chrome’s documentation calls it “an emerging convention,” and the proposal says it “is open for community input.”
The format is simple. The file opens with the site’s name as a heading. A short summary and lists of links under section headings can follow. The proposal also suggests a clean Markdown copy of the pages agents might need.
It does not replace the files search engines already read. robots.txt tells crawlers what access is acceptable, and a sitemap lists the indexable pages. The proposal describes llms.txt as a curated overview that is “used on demand, when an agent needs information about a topic while assisting a user.”
What do Google, ChatGPT, Claude, Perplexity and Copilot say about it?
| Company | What its guidance for site owners says |
|---|---|
| Google (AI Overviews and AI Mode) | “You don’t need to create new machine readable files, AI text files, or markup to appear in these features.” |
| OpenAI (ChatGPT search) | Its crawler page covers robots.txt rules for OAI-SearchBot, GPTBot and ChatGPT-User. It says nothing about reading llms.txt on other sites. |
| Anthropic (Claude) | Its crawler article covers robots.txt rules for ClaudeBot, Claude-User and Claude-SearchBot. It does not mention llms.txt. |
| Perplexity | Its crawler page covers PerplexityBot and Perplexity-User. It says nothing about reading llms.txt on other sites. |
| Microsoft (Bing and Copilot) | Bing and Copilot search experiences rely on “the same core crawling, indexing, and ranking foundation as traditional search.” The guidelines do not mention llms.txt. |
OpenAI, Anthropic, Perplexity and Google, for its Gemini API, do publish llms.txt files for their own developer documentation. Nothing in the guidance above says their search answers read the file on your site.
Who uses llms.txt today?
Mostly coding agents, according to the proposal. It says the files “are used most heavily for software documentation, where coding agents follow them to find API references and tutorials.” Agents are expected to read the file, then follow its links to the detail they need.
Chrome’s Lighthouse audit tool now checks for the file as part of its agentic browsing audits. A missing file is marked Not Applicable, “as providing the file is optional at the moment.” Lighthouse flags the page when the server returns an error for the file. Its documentation says that without the file, agents “may spend more time crawling the site” to understand its structure.
Should a local business publish one?
It is optional, and the guidance points to other work instead. Google lists these among the SEO fundamentals that still count for its AI features, and Bing says SEO best practices “also support eligibility for AI-generated experiences, grounding results, and citations”:
- Let the crawlers in. Google lists “ensuring that crawling is allowed in robots.txt, and by any CDN or hosting infrastructure.” Which AI crawlers to allow names the ones that matter.
- Keep the facts in page text. Google asks that “important content is available in textual form,” with structured data that matches the visible text.
- Keep your Business Profile current. Google lists checking that your Business Profile information is up to date.
If your website platform already makes an llms.txt, read it. The proposal lists Wix and the Yoast SEO plugin for WordPress among the tools that generate one automatically. The services, area and contact details in it should match your site.
If you write one yourself, use only facts that already appear on your site, and leave out anything addressed to AI models. Bing warns that attempts to add “content designed to manipulate or interfere with language models used by Bing or Copilot may result in reduced visibility or removal from search experiences.” Check that the address returns the file or a 404 (not found), since Lighthouse flags a server error.
What does a small one look like?
Only the heading is required. A short file for a local business might read:
# Example Roofing
> Example Roofing repairs and replaces roofs for homes in Springfield and nearby towns.
## Key pages
- [Roof repair](https://www.example.com/roof-repair): Leaks, storm damage and inspections
- [Service area](https://www.example.com/service-area): The towns we cover
- [Contact](https://www.example.com/contact): Phone, hours and how to book
Why does ultruxy.ai have one?
Because it takes no upkeep. Ours is built from the same page data as our sitemap, so it updates whenever the site does. We don’t count it as a reason any assistant will name us, and we don’t sell it as one. You can read it at ultruxy.ai/llms.txt.
The AI visibility checklist covers the checks that come first, and What is AEO? explains the wider work. To have your own site checked, Ultruxy offers a free visibility report. How we approach the work is on the AEO service page.
Sources
- 01 The /llms.txt file, v2 llmstxt.org
- 02 Changes llmstxt.org
- 03 AI features and your website Google Search Central
- 04 llms.txt Chrome for Developers
- 05 Overview of OpenAI Crawlers OpenAI
- 06 Does Anthropic crawl data from the web, and how can site owners block the crawler? Anthropic
- 07 Perplexity Crawlers Perplexity
- 08 Webmaster Guidelines Microsoft Bing Webmaster Tools
- 09 OpenAI Developers llms.txt OpenAI
- 10 Anthropic Developer Documentation llms.txt Anthropic
- 11 Gemini API llms.txt Google AI for Developers
- 12 Perplexity llms.txt Perplexity