# Google (Search + AI Overviews use Googlebot)
User-agent: Googlebot
Allow: /

# Google-Extended (Gemini / Vertex grounding + training)
User-agent: Google-Extended
Allow: /

# Bing (powers Copilot, ChatGPT web search, DuckDuckGo)
User-agent: Bingbot
Allow: /

# OpenAI / ChatGPT
User-agent: OAI-SearchBot
Allow: /
User-agent: ChatGPT-User
Allow: /
User-agent: GPTBot
Allow: /

# Anthropic / Claude
User-agent: ClaudeBot
Allow: /
User-agent: Claude-SearchBot
Allow: /
User-agent: Claude-User
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /
User-agent: Perplexity-User
Allow: /

# Apple Intelligence / Siri
User-agent: Applebot
Allow: /
User-agent: Applebot-Extended
Allow: /

# DuckDuckGo
User-agent: DuckDuckBot
Allow: /

# Common Crawl (pretraining corpus for most LLMs — C4/FineWeb/Dolma derive from it)
User-agent: CCBot
Allow: /

# Meta AI (training + live fetch) and Facebook/Instagram link previews
User-agent: meta-externalagent
Allow: /
User-agent: meta-externalfetcher
Allow: /
User-agent: facebookexternalhit
Allow: /

# Link-preview bots (shared event links must render rich cards)
User-agent: Twitterbot
Allow: /
User-agent: Discordbot
Allow: /
User-agent: WhatsApp
Allow: /
User-agent: TelegramBot
Allow: /
User-agent: LinkedInBot
Allow: /
User-agent: Slackbot
Allow: /
User-agent: Snapchat
Allow: /

# Amazon (Alexa + Rufus answers)
User-agent: Amazonbot
Allow: /

# TikTok search
User-agent: Bytespider
Allow: /

# Block every other crawler (generic scrapers)
User-agent: *
Disallow: /

# Sitemap location
Sitemap: https://www.crowdvolt.com/sitemap.xml