# Allow mainstream search engines
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Applebot
Allow: /

# Block AI/training and bulk data crawlers
User-agent: GPTBot                 # OpenAI
Disallow: /

User-agent: ChatGPT-User           # ChatGPT browsing
Disallow: /

User-agent: CCBot                  # Common Crawl
Disallow: /

User-agent: ClaudeBot              # Anthropic
Disallow: /
User-agent: Claude-Web             # Anthropic
Disallow: /

User-agent: PerplexityBot          # Perplexity.ai
Disallow: /

User-agent: Google-Extended        # Google AI data use
Disallow: /

User-agent: Applebot-Extended      # Apple AI data use
Disallow: /

User-agent: Amazonbot              # Amazon crawler
Disallow: /

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

User-agent: Meta-ExternalAgent     # Meta AI data fetcher
Disallow: /
User-agent: Meta-ExternalFetcher
Disallow: /

# Default: allow others (optional). To block everything else, change to Disallow: /
User-agent: *
Disallow: /

# Optional: your sitemap
# Sitemap: https://your-domain.com/sitemap.xml