# Sandooq — https://sandooq.app
#
# Content-Signal below states how this content may be USED once fetched
# (https://contentsignals.org/). search / ai-input / ai-train are all
# granted: being quoted in an AI answer is the point.
#
# NOTE: a crawler obeys exactly ONE group — its most specific user-agent
# match — and ignores `*` entirely. So the AI group below repeats every
# rule from `*`. Dropping a repeat would silently UN-disallow that path
# for those crawlers, which is the classic way this file goes wrong.

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Allow: /api/mcp
Disallow: /api/*
Disallow: /healthz

# AI crawlers: identical rules, plus the image optimizer (see AI_EXTRA_DISALLOW).
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Google-Extended
User-agent: Bytespider
User-agent: Amazonbot
User-agent: meta-externalagent
User-agent: DuckAssistBot
User-agent: CCBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Allow: /api/mcp
Disallow: /api/*
Disallow: /healthz
Disallow: /_next/image

Sitemap: https://sandooq.app/sitemap.xml
Agentmap: https://sandooq.app/.well-known/ai-catalog.json