# Emporiqa — robots.txt
# Per-bot Allow/Block is managed at the edge via Cloudflare AI Crawl Control.
# This file is the durable published policy. Both layers are aligned: AI
# crawlers (ClaudeBot, GPTBot, Google-Extended, CCBot, Applebot-Extended,
# Amazonbot, Bytespider, meta-externalagent, PerplexityBot, OAI-SearchBot,
# Claude-SearchBot, etc.) fall under `User-agent: *` below and may crawl.

# Content-Signal expresses our explicit stance under the IETF "AI Preferences"
# draft and EU Directive 2019/790 Article 4. Search and real-time AI grounding
# (citations in Claude / ChatGPT / Perplexity / Gemini) are permitted; AI
# training corpus inclusion is reserved.
Content-Signal: search=yes, ai-input=yes, ai-train=no

Sitemap: https://emporiqa.com/sitemap.xml

# LLM-facing reference files (plain text, not HTML pages)
# https://emporiqa.com/llms.txt
# https://emporiqa.com/llms-full.txt

User-agent: *
Allow: /
Disallow: /admin/
Disallow: /chat/
Allow: /platform/create-store/
Disallow: /platform/
Disallow: /webhooks/
# Personalized cold-outreach demo landing pages. RETIRED 2026-08-27: the route
# now 302s to the homepage because ~1,222 sent emails still carry these links.
# Keep this Disallow until the route itself goes (see website/demo_urls.py,
# suggested 2027-03): without it a crawler spends budget on 675 URLs that all
# redirect to the same page. Remove both together.
Disallow: /d/
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?mc_cid=
Disallow: /*?mc_eid=