# Bayer Global robots.txt
# https://www.bayer.com/

# Default rules for all compliant crawlers
User-agent: *
Disallow: /search/
Disallow: /*?

# OpenAI: allow ChatGPT Search
User-agent: OAI-SearchBot
Allow: /
Disallow: /search/
Disallow: /*?

# OpenAI: allow user-requested retrieval
User-agent: ChatGPT-User
Allow: /
Disallow: /search/
Disallow: /*?

# OpenAI: block model-training crawler
User-agent: GPTBot
Disallow: /

# Anthropic: allow Claude Search
User-agent: Claude-SearchBot
Allow: /
Disallow: /search/
Disallow: /*?

# Anthropic: allow user-requested retrieval
User-agent: Claude-User
Allow: /
Disallow: /search/
Disallow: /*?

# Anthropic: block model-training crawler
User-agent: ClaudeBot
Disallow: /

# Perplexity: allow search indexing and citations
User-agent: PerplexityBot
Allow: /
Disallow: /search/
Disallow: /*?

# Perplexity: allow user-requested retrieval
User-agent: Perplexity-User
Allow: /
Disallow: /search/
Disallow: /*?

# Mistral: allow AI search indexing
User-agent: MistralAI-Index
Allow: /
Disallow: /search/
Disallow: /*?

# Mistral: allow user-requested retrieval
User-agent: MistralAI-User
Allow: /
Disallow: /search/
Disallow: /*?

# Google: opt out of Gemini model training and grounding
# Does not affect Google Search, AI Overviews or AI Mode
User-agent: Google-Extended
Disallow: /

# Apple: opt out of Apple generative-AI model training
# Does not block regular Applebot search crawling
User-agent: Applebot-Extended
Disallow: /

# Meta: block model-training crawler
User-agent: meta-externalagent
Disallow: /

# Common Crawl: block collection for public datasets
User-agent: CCBot
Disallow: /

# ByteDance: block AI-training crawler
User-agent: Bytespider
Disallow: /
Sitemap: https://www.bayer.com/sitemap.xml