# SendThisFax — https://www.sendthisfax.com
#
# Policy: allow search indexing and AI citation (real-time retrieval
# by ChatGPT Search, Perplexity, Gemini, etc.). Reserve training rights
# under EU Directive 2019/790 Article 4.
#
# Expressed two ways: Content-Signal for crawlers that honor it, and
# explicit Disallow for training-only user-agents.

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

# Internal and operational endpoints
Disallow: /admin/
Disallow: /api/
Disallow: /webhooks/
Disallow: /up
Disallow: /health/

# Email Address Obfuscation rewrites mailto: links to
# /cdn-cgi/l/email-protection, which only resolves via JavaScript.
# Scope this to /l/ only: /cdn-cgi/scripts/ serves the decoder that restores
# the address before hydration, and blocking it makes crawlers hydrate against
# the undecoded placeholder (React #418).
Disallow: /cdn-cgi/l/

# Per-fax status pages contain unguessable public_ids; do not index.
Disallow: /en/fax/
Disallow: /de/fax/
Disallow: /fr/fax/
Disallow: /nl/fax/
Disallow: /es/fax/
Disallow: /it/fax/

# Training-only crawlers. Citation/search crawlers such as OAI-SearchBot,
# ChatGPT-User, PerplexityBot, Googlebot, and Applebot remain allowed
# via the default group above.

User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: cohere-training-data-crawler
Disallow: /

Sitemap: https://www.sendthisfax.com/sitemap.xml