# All crawlers welcome — including AI search, answer engines, and training bots.
User-agent: *
Allow: /
Disallow: /whitepapers/dl/

# Explicit allowlist for major AI crawlers (search, answer engines, training).
# Listed so intent is unambiguous to bots that look for their own user-agent first.

# OpenAI
User-agent: GPTBot
Allow: /
Disallow: /whitepapers/dl/

User-agent: OAI-SearchBot
Allow: /
Disallow: /whitepapers/dl/

User-agent: ChatGPT-User
Allow: /
Disallow: /whitepapers/dl/

# Anthropic
User-agent: ClaudeBot
Allow: /
Disallow: /whitepapers/dl/

User-agent: Claude-SearchBot
Allow: /
Disallow: /whitepapers/dl/

User-agent: Claude-User
Allow: /
Disallow: /whitepapers/dl/

User-agent: anthropic-ai
Allow: /
Disallow: /whitepapers/dl/

# Google AI (separate from Googlebot, controls Gemini / AI Overviews training)
User-agent: Google-Extended
Allow: /
Disallow: /whitepapers/dl/

# Apple Intelligence
User-agent: Applebot-Extended
Allow: /
Disallow: /whitepapers/dl/

# Perplexity
User-agent: PerplexityBot
Allow: /
Disallow: /whitepapers/dl/

User-agent: Perplexity-User
Allow: /
Disallow: /whitepapers/dl/

# DuckDuckGo AI
User-agent: DuckAssistBot
Allow: /
Disallow: /whitepapers/dl/

# Meta AI
User-agent: Meta-ExternalAgent
Allow: /
Disallow: /whitepapers/dl/

User-agent: Meta-ExternalFetcher
Allow: /
Disallow: /whitepapers/dl/

# Amazon
User-agent: Amazonbot
Allow: /
Disallow: /whitepapers/dl/

# ByteDance
User-agent: Bytespider
Allow: /
Disallow: /whitepapers/dl/

# Cohere
User-agent: cohere-ai
Allow: /
Disallow: /whitepapers/dl/

User-agent: cohere-training-data-crawler
Allow: /
Disallow: /whitepapers/dl/

# Common Crawl (used as a training data source by many AI systems)
User-agent: CCBot
Allow: /
Disallow: /whitepapers/dl/

# Diffbot
User-agent: Diffbot
Allow: /
Disallow: /whitepapers/dl/

# You.com
User-agent: YouBot
Allow: /
Disallow: /whitepapers/dl/

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