# COLA Cloud robots.txt
# https://colacloud.us

User-agent: *
Allow: /

# Search and user-requested AI agents
User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: MistralAI-User
Allow: /

User-agent: MistralAI-Index
Allow: /

User-agent: Amzn-SearchBot
Allow: /

User-agent: Amzn-User
Allow: /

User-agent: DuckAssistBot
Allow: /

# Google-Extended couples Gemini grounding and training; reviewed URLs only.
User-agent: Google-Extended
Disallow: /
Allow: /$
Allow: /pricing$
Allow: /bulk-data$
Allow: /api$
Allow: /mcp$
Allow: /product-enrichment$
Allow: /data/beer$
Allow: /data/california-wine$
Allow: /blog/iowa-liquor-product-list-benchmark$

# YouBot: reviewed buyer pages only.
User-agent: YouBot
Disallow: /
Allow: /product-enrichment$
Allow: /data/beer$
Allow: /data/california-wine$
Allow: /data-packs/whiskey$
Allow: /blog/whiskey-dataset-evaluation$

# Other model-training, low-value AI, and commercial SEO crawlers
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: anthropic-ai
User-agent: Bytespider
User-agent: CCBot
User-agent: meta-externalagent
User-agent: Meta-ExternalAgent
User-agent: Amazonbot
User-agent: MistralAI-Training
User-agent: SemrushBot
User-agent: AhrefsBot
User-agent: DataForSeoBot
User-agent: PetalBot
Disallow: /

# Provide llms.txt for AI agents
# See: https://llmstxt.org/

Sitemap: https://colacloud.us/sitemap.xml