File Generation

How llms.txt and site-data.json help AI crawlers understand your site.

Last updated Feb 3, 2025

Why AI Crawlers Need Special Files

Traditional search engines crawl HTML and follow links. AI search engines like ChatGPT, Perplexity, and Claude work differently — they need structured, machine-readable data to understand and recommend your business accurately.

CitedPro generates two files specifically designed for AI crawlers:

  • llms.txt — A markdown file that explains your business in plain language
  • site-data.json — Structured JSON data for programmatic access

llms.txt

The llms.txt file is a markdown document that provides AI language models with a clear, structured overview of your business.

What It Contains

  • Business name and description
  • Contact information
  • Services and products with descriptions
  • Frequently asked questions
  • Social media links
  • Team information (if provided)

Example Structure

# Business Name

> Brief description of your business.

## Contact
- Phone: (555) 123-4567
- Email: hello@example.com
- Address: 123 Main St, City, State

## Services

### Service Name
Description of the service and what it includes.
Price: $99

## FAQs

### What are your hours?
We're open Monday-Friday, 9am-5pm.

## Social
- Twitter: @example
- LinkedIn: /company/example

File Location

By default, llms.txt is placed in your site root:

https://yoursite.com/llms.txt

If your server doesn't allow writing to the root, it falls back to:

https://yoursite.com/wp-content/uploads/srsk/llms.txt

site-data.json

The site-data.json file provides the same information in a structured JSON format that AI systems can parse programmatically.

What It Contains

{
  "name": "Business Name",
  "description": "What your business does",
  "url": "https://yoursite.com",
  "contact": {
    "phone": "(555) 123-4567",
    "email": "hello@example.com"
  },
  "services": [...],
  "products": [...],
  "faqs": [...],
  "social": {...}
}

Use Cases

  • AI agents fetching business data
  • Automated systems building knowledge bases
  • Search engines indexing structured content
  • Third-party integrations

Generating Files

  1. Complete your business information in CitedPro → Setup
  2. Go to CitedPro → Files
  3. Click Generate Files
  4. Verify the files show green "Active" status

Tip

Files are automatically regenerated when you update your business information in Setup. You can also manually regenerate anytime from the Files tab.

Verifying Your Files

After generation, verify your files are accessible:

  1. Visit yoursite.com/llms.txt — should display markdown content
  2. Visit yoursite.com/site-data.json — should return JSON
  3. Check the Files tab for any error messages

Common Issues

  • 404 Not Found: Files may be in the uploads folder if root writing failed
  • Empty Content: Complete the Setup wizard with business information first
  • Caching: Clear your cache after regenerating files

Best Practices

  • Keep information current: Regenerate files when business details change
  • Be specific: Detailed service descriptions help AI recommend you accurately
  • Add FAQs: Common questions help AI answer queries about your business
  • Include pricing: If public, include pricing to appear in comparison queries