# llms.txt — Usage policy for Large Language Model crawlers
# Site: https://www.corvedental.com/
# Default policy: ALLOW retrieval for on-demand answers/previews; DISALLOW model training + bulk ingestion.
# Contact: webmaster@corvedental.com
# Updated: 2025-08-23

# OpenAI
User-agent: GPTBot
Disallow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Anthropic
User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Allow: /

# Perplexity
User-agent: PerplexityBot
Disallow: /

# Google (AI training control)
User-agent: Google-Extended
Disallow: /

# Common Crawl (feeds many AI training sets)
User-agent: CCBot
Disallow: /

# ByteDance / TikTok
User-agent: Bytespider
Disallow: /

# Meta / Facebook
User-agent: FacebookBot
Disallow: /

# Amazon
User-agent: Amazonbot
Disallow: /

# Microsoft (block AI preview/training crawler; search indexing by bingbot is governed in robots.txt)
User-agent: BingPreview
Disallow: /

# Fallback rule
User-agent: *
Crawl-Delay: 5

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