# Clinovus AI — robots.txt
# Strategy: Open access for SEO + GEO (Generative Engine Optimization)
# Last updated: 2026-05-08

# ===== Default rules (all bots) =====
User-agent: *
Allow: /
Disallow: /signup
Disallow: /inscription
Disallow: /login
Disallow: /compte
Disallow: /account
Disallow: /confirm
Disallow: /confirmation
Disallow: /reset-password
Disallow: /logout
Disallow: /error
Disallow: /mailer-templates/
Disallow: /assets/

# ===== AI / GEO crawlers (explicit allow for clarity) =====
# OpenAI (ChatGPT real-time browsing + training)
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Anthropic (Claude real-time browsing + training)
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

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

# Perplexity (real-time RAG search)
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Google AI (Gemini, AI Overviews)
User-agent: Google-Extended
Allow: /

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

# Bytedance (Doubao)
User-agent: Bytespider
Allow: /

# Meta AI
User-agent: FacebookBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

# DuckDuckGo Assist
User-agent: DuckAssistBot
Allow: /

# Mistral (used by your own stack)
User-agent: MistralAI-User
Allow: /

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

# You.com
User-agent: YouBot
Allow: /

# Diffbot
User-agent: Diffbot
Allow: /

# ===== Sitemap =====
Sitemap: https://clinovusai.com/sitemap.xml

# Block Internet Archive crawls (post-pivot)
User-agent: ia_archiver
Disallow: /

User-agent: archive.org_bot
Disallow: /

# Block Internet Archive crawls (post-pivot)
User-agent: ia_archiver
Disallow: /

User-agent: archive.org_bot
Disallow: /

# Block Internet Archive crawls (post-pivot)
User-agent: ia_archiver
Disallow: /

User-agent: archive.org_bot
Disallow: /