# Allow all search engines and AI crawlers
User-agent: *
Allow: /
Allow: /routes/*
Disallow: /api/*
Disallow: /dashboard/*
Disallow: /admin/*
Disallow: /embed/*

# AI crawlers.
#
# Each named block below repeats the Disallow list on purpose. robots.txt has
# no inheritance: a crawler obeys the ONE group that matches it best, so a bare
# "User-agent: GPTBot / Allow: /" block does not pick up the rules from the "*"
# group. Before this, every named AI bot was free to crawl /admin/* and /api/*
# while ordinary crawlers were kept out.
#
# /embed/* stays disallowed here too. Those URLs are one bare widget per public
# route, thousands of near-identical thin pages. The white-label story is told
# by /p, which is prerendered and carries Service + FAQPage markup. pointing AI
# crawlers at the widgets instead would trade one good citation target for a
# few thousand bad ones.

User-agent: GPTBot
Allow: /
Disallow: /api/*
Disallow: /dashboard/*
Disallow: /admin/*
Disallow: /embed/*

User-agent: ChatGPT-User
Allow: /
Disallow: /api/*
Disallow: /dashboard/*
Disallow: /admin/*
Disallow: /embed/*

User-agent: Claude-Web
Allow: /
Disallow: /api/*
Disallow: /dashboard/*
Disallow: /admin/*
Disallow: /embed/*

User-agent: PerplexityBot
Allow: /
Disallow: /api/*
Disallow: /dashboard/*
Disallow: /admin/*
Disallow: /embed/*

User-agent: Anthropic-AI
Allow: /
Disallow: /api/*
Disallow: /dashboard/*
Disallow: /admin/*
Disallow: /embed/*

User-agent: ClaudeBot
Allow: /
Disallow: /api/*
Disallow: /dashboard/*
Disallow: /admin/*
Disallow: /embed/*

User-agent: Google-Extended
Allow: /
Disallow: /api/*
Disallow: /dashboard/*
Disallow: /admin/*
Disallow: /embed/*

# Sitemap location
Sitemap: https://cityheart.run/sitemap.xml