llms.txt and ai.txt: machine-readable files for AI crawlers on Wix

Just as robots.txt tells search engine crawlers what they can and cannot access, new file standards are emerging to communicate directly with AI systems. llms.txt provides a structured summary of your site for large language models. ai.txt provides guidance for AI agents. These are early-stage standards, but implementing them now gives your Wix site a significant advantage as adoption grows.

What is llms.txt?

llms.txt is a proposed standard (llmstxt.org) that provides a structured, markdown-formatted summary of your website specifically designed for AI systems. It lives at yourdomain.com/llms.txt and gives large language models a concise overview of who you are, what you do, what topics you cover, and where to find your most important content. Think of it as a cheat sheet for AI engines.

The format is simple: a markdown file with your site name, a brief description, and categorised links to your most important content. The goal is to reduce the need for AI engines to crawl and interpret your entire site, instead giving them a curated, authoritative summary they can reference instantly.

Writing an Effective llms.txt File

# Your Business Name

> Brief 1-2 sentence description of your business and expertise.

## About

- [About Us](https://yourdomain.com/about): Full background, credentials and history
- [Our Services](https://yourdomain.com/services): Complete list of services offered

## Key Topics

- [Wix SEO Guide](https://yourdomain.com/wix-seo): Comprehensive guide to Wix SEO
- [Local SEO](https://yourdomain.com/local-seo): Local search optimisation services

## Resources

- [Blog](https://yourdomain.com/blog): Regular articles on SEO and Wix
- [Case Studies](https://yourdomain.com/case-studies): Documented client results

## Contact

- [Contact Page](https://yourdomain.com/contact): Get in touch

What is ai.txt?

ai.txt is a complementary file that provides instructions and preferences for AI agents interacting with your site. While llms.txt summarises your content, ai.txt communicates policies: what AI agents should know about your business, how they should represent your information, and any specific instructions about attribution or usage.

Hosting Static Files on Wix

Wix does not natively support hosting arbitrary text files at custom URLs. However, there are workarounds that achieve the same result. The most reliable approach is to add the content via Wix Custom Code in the site-wide head section as a meta tag alternative, or use the Wix Velo router to serve text content at the correct URL path.

How to add llms.txt functionality to your Wix site

• Create the content of your llms.txt file following the markdown format above
• If using Wix Velo: create an HTTP function that serves the text file at /llms.txt
• If not using Velo: add the key information as structured data in your homepage schema
• Include a link to your llms.txt equivalent in your robots.txt or homepage meta tags
• Validate by visiting the URL and confirming the content renders as plain text

robots.txt and AI Crawlers

Your existing robots.txt file also matters for GEO. AI crawlers like GPTBot (OpenAI), PerplexityBot, ClaudeBot (Anthropic) and Google-Extended respect robots.txt directives. If you want to be cited by AI engines, you must ensure your robots.txt is not blocking these crawlers. Check your Wix robots.txt and remove any blanket blocks on AI user agents.

Complete How-To Guide: Setting Up llms.txt, ai.txt and AI Crawler Access on Wix

This guide covers creating machine-readable files for AI systems, configuring your Wix robots.txt for AI crawler access, and verifying that AI engines can discover and read your content.

How to configure your Wix site for AI crawler access and machine-readable files

• Step 1: Check your current robots.txt by visiting yourdomain.com/robots.txt. Copy the contents and review for any Disallow rules that might block AI crawlers.
• Step 2: In your Wix Dashboard, go to Settings then SEO then robots.txt. Ensure there are no rules blocking User-agent: GPTBot, User-agent: PerplexityBot, User-agent: ClaudeBot, or User-agent: Google-Extended.
• Step 3: If any AI crawlers are blocked, remove the Disallow rules for them. Save and verify by checking your robots.txt URL again. Changes may take a few minutes to propagate.
• Step 4: Create your llms.txt content in markdown format. Start with your business name as an H1, add a brief 1-2 sentence description, then list your most important pages organised by category (About, Services, Key Topics, Resources, Contact).
• Step 5: Select 10-20 of your highest-quality, most authoritative pages for inclusion in llms.txt. Do not include every page. This is a curated summary of your best content.
• Step 6: Host your llms.txt file. If using Wix Velo, create an HTTP function that serves the markdown content at /llms.txt. If not using Velo, add the structured summary as meta information in your homepage schema or as a downloadable text file.
• Step 7: Create your ai.txt content. Include your business name, a description of what you do, your preferred attribution format, and any specific instructions for how AI engines should represent your information.
• Step 8: Add your ai.txt content to your site using the same hosting method as llms.txt. Place it at yourdomain.com/ai.txt if possible.
• Step 9: Reference your llms.txt in your robots.txt by adding a comment or custom directive pointing to its location. While not yet a standard directive, it aids discovery.
• Step 10: Submit your sitemap to both Google Search Console and Bing Webmaster Tools. Verify that your most important pages (the ones listed in llms.txt) are all indexed in both search engines.
• Step 11: Test AI crawler access by using the Google Rich Results Test to confirm your pages render correctly for crawlers. Check that important content is not hidden behind JavaScript that crawlers cannot execute.
• Step 12: Verify your setup quarterly. Check that robots.txt is still allowing AI crawlers, your llms.txt content is current with your latest pages, and your sitemap includes all important URLs.