User-agent: *
Allow: /

Sitemap: https://invorec.com/sitemap-index.xml

# ─────────────────────────────────────────────────────────────────────
# AI crawler policy: allow crawlers that make citation in AI answers
# possible; block crawlers that only collect training data.
# Note: robots.txt compliance is voluntary — some crawlers ignore it.
# ─────────────────────────────────────────────────────────────────────

# --- AI search and retrieval: allowed ---
# These make citation in AI answers possible.
User-agent: OAI-SearchBot
Allow: /
User-agent: Claude-SearchBot
Allow: /
User-agent: PerplexityBot
Allow: /
User-agent: DuckAssistBot
Allow: /
User-agent: Amazonbot
Allow: /

# --- User-triggered fetches: allowed ---
# Fired when a person explicitly asks an assistant to read a page.
# Blocking these only breaks a request the user made themselves.
User-agent: ChatGPT-User
Allow: /
User-agent: Claude-User
Allow: /
User-agent: Perplexity-User
Allow: /
User-agent: MistralAI-User
Allow: /
User-agent: Meta-ExternalFetcher
Allow: /

# --- Training-only collectors: blocked ---
User-agent: GPTBot
Disallow: /
User-agent: ClaudeBot
Disallow: /
User-agent: CCBot
Disallow: /
User-agent: meta-externalagent
Disallow: /
User-agent: cohere-ai
Disallow: /
User-agent: AI2Bot
Disallow: /
User-agent: Bytespider
Disallow: /

# --- Google and Apple control tokens ---
# Google-Extended is not a crawler; it governs Gemini training AND
# grounding, and cannot be split. Allowed deliberately so the site stays
# eligible for citation in Gemini answers. It does not affect Googlebot
# indexing or ranking either way.
User-agent: Google-Extended
Allow: /
# Applebot-Extended governs Apple Intelligence training only.
User-agent: Applebot-Extended
Disallow: /