# getautorx.ca - robots policy
# Public-by-default site. AI crawlers are welcomed explicitly so we can be cited
# correctly in ChatGPT, Claude, Perplexity, Google AI Overviews, etc.

User-agent: *
Allow: /

# Internal / scratch
Disallow: /sample/

# Trust Center policy PDFs, passcode-gated on-page (2026-07-07), not meant to be
# crawled or indexed directly. This only matches the .pdf files served from
# public/compliance/, it does not block /compliance/phipa/ or /compliance/pipeda/,
# which are separate marketing pages under the same path.
Disallow: /compliance/*.pdf$

# Use page-level noindex for /docs/*, /customers/*, /status/, /contact/thank-you
# (not blocked here so well-behaved crawlers can follow internal links into them).

# ── Explicit allow for AI / LLM crawlers ────────────────────────────────────
# OpenAI
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Anthropic
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# Google AI training / AI Overviews surface
User-agent: Google-Extended
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Meta AI
User-agent: meta-externalagent
Allow: /

User-agent: FacebookBot
Allow: /

# Apple Intelligence
User-agent: Applebot-Extended
Allow: /

# Common Crawl (used as training data by many models)
User-agent: CCBot
Allow: /

# Cohere
User-agent: cohere-ai
Allow: /

# Bytespider / TikTok
User-agent: Bytespider
Allow: /

# Amazon
User-agent: Amazonbot
Allow: /

# Diffbot (knowledge graph)
User-agent: Diffbot
Allow: /

Sitemap: https://getautorx.ca/sitemap-index.xml