# CrunchJunkie — https://crunchjunkie.io
# Public marketing pages are open to all crawlers (search engines AND AI answer
# engines — GPTBot, ClaudeBot, PerplexityBot, Google-Extended, OAI-SearchBot, etc.
# are covered by the wildcard rule below; we want our content cited by AI). The
# authenticated app, API and account flows are kept out of the index.

User-agent: *
Allow: /
Disallow: /api/
Disallow: /admin
Disallow: /auth
Disallow: /gate
Disallow: /invite
Disallow: /oauth
Disallow: /onboarding
Disallow: /welcome
# /share/ is deliberately NOT disallowed. Shared reports carry noindex via
# X-Robots-Tag and a robots meta tag; blocking the crawl here would stop a
# crawler ever reading those directives, leaving a leaked share URL eligible
# for URL-only indexing. Allow the fetch so the noindex is honoured.
Disallow: /builder
Disallow: /clients
Disallow: /dashboard
Disallow: /data
Disallow: /monitoring
Disallow: /partner
Disallow: /reports
Disallow: /search
Disallow: /settings
Disallow: /templates
Disallow: /visibility

# LLM-friendly content maps (emerging llms.txt convention):
#   Curated index: https://crunchjunkie.io/llms.txt
#   Full corpus:   https://crunchjunkie.io/llms-full.txt
Sitemap: https://crunchjunkie.io/sitemap.xml