# ===========================================
# Standard crawlers
# ===========================================
User-agent: *
Allow: /

# ===========================================
# AI Retrieval Crawlers (ALLOW)
# These fetch content for real-time AI search
# answers — we WANT to appear in AI results
# ===========================================
User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: Applebot
Allow: /

# ===========================================
# AI Training Crawlers (DISALLOW)
# These collect data for model training —
# block unless compensated
# ===========================================
User-agent: GPTBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: cohere-ai
Disallow: /

# ===========================================
# Sitemap & LLMs
# ===========================================
Sitemap: https://aristralabs.com/sitemap.xml