example.com

Upload to the site root so it is served at https://example.com/llms.txt. It is plain text: no build step and no server change are required.

# example.com

> Public site summary for example.com, generated from an independent snapshot on 2026-11-15.

This file lists the pages an AI agent can read and states how the content may be used. Every link below points at the live site; nothing here replaces the site.

## Key pages
- [Home page](https://example.com/)

## Use of this content by AI systems

AI systems may read these pages and cite example.com with attribution. Model-training use is governed by the site's robots.txt, which states the policy per crawler category (model training / AI search and citation / user-triggered fetches).

## Notes

- Generated by Global Fact Hub (https://globalfacthub.com) on 2026-11-15.
- Keep this file in the site root so it is served at https://example.com/llms.txt.

Download llms.txt

Upload to https://example.com/.well-known/ai-catalog.json and reference it from a <link rel="ai-catalog" href="/.well-known/ai-catalog.json"> tag or an Agentmap line in robots.txt. The entry's url stays the canonical customer address https://example.com/llms.txt even though we only host a sample copy under https://globalfacthub.com/domain/example.com/. ARD is designed for agent resources (MCP servers, A2A agents); replace this site-summary entry when you publish one.

{
  "specVersion": "1.0",
  "entries": [
    {
      "identifier": "urn:air:example.com:llms-txt",
      "displayName": "example.com site summary",
      "title": "example.com site summary (llms.txt)",
      "description": "Public site summary for example.com: key pages, an AI usage statement and the crawler policy that applies to them. Generated from an independent snapshot on 2026-11-15.",
      "type": "text/markdown",
      "url": "https://example.com/llms.txt",
      "representativeQueries": [
        "example",
        "explam",
        "can you show me an example"
      ]
    }
  ]
}

Download ai-catalog.json

Append these lines to the existing robots.txt and keep every existing line. Do not replace the file: the block only adds rules and states a default policy you can edit per category.

# ---- AI agent policy (appended by Global Fact Hub on 2026-11-15) ----
# Append this block to the end of the robots.txt of example.com.
# No existing rule is removed or rewritten: this block only adds rules below yours.
# RFC 9309: a crawler that matches a named group reads only that group, so each
# category below repeats its own policy.

# 1) Model-training crawlers. Change 'Allow: /' to 'Disallow: /' to opt out of training.
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: Google-Extended
User-agent: Applebot-Extended
Allow: /

# 2) AI search and citation crawlers. Keep these allowed so AI answers can cite the site.
User-agent: OAI-SearchBot
User-agent: Claude-SearchBot
User-agent: PerplexityBot
Allow: /

# 3) User-triggered fetches: a person asked an assistant to open a page.
User-agent: ChatGPT-User
User-agent: Claude-User
User-agent: Perplexity-User
Allow: /

# ---- end of appended AI agent policy ----

Download robots-ai-block.txt