# VoxPrep.ai — robots.txt
# Public marketing & content pages are open to all search engines and AI assistants.
# We explicitly allow major AI crawlers because some only honor named user-agent rules.

# Search engines
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Slurp
Allow: /

User-agent: YandexBot
Allow: /

User-agent: Baiduspider
Allow: /

# Social previews
User-agent: Twitterbot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: LinkedInBot
Allow: /

# AI assistants — OpenAI / ChatGPT
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# AI assistants — Anthropic / Claude
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# AI assistants — Google / Gemini (training opt-in)
User-agent: Google-Extended
Allow: /

# AI assistants — Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# AI assistants — Apple Intelligence
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# AI assistants — Meta AI
User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: FacebookBot
Allow: /

# AI assistants — DuckDuckGo
User-agent: DuckAssistBot
Allow: /

# AI assistants — xAI / Grok
User-agent: xAI-Bot
Allow: /

# AI assistants — Mistral
User-agent: MistralAI-User
Allow: /

# AI assistants — You.com
User-agent: YouBot
Allow: /

# AI assistants — Cohere
User-agent: cohere-ai
Allow: /

# Common Crawl (feeds many open-source models)
User-agent: CCBot
Allow: /

# Bytedance (used by various AI products)
User-agent: Bytespider
Allow: /

# Catch-all
User-agent: *
Allow: /

Sitemap: https://voxprep.ai/sitemap.xml
Sitemap: https://rskxneruiyxzlizwrkhz.supabase.co/functions/v1/blog-sitemap