# --- OpenAI ---
    User-agent: GPTBot
    Disallow: /
    User-agent: ChatGPT-User
    Allow: /
    
    # --- Google AI training ---
    User-agent: Google-Extended
    Disallow: /
    
    # --- Anthropic / Claude ---
    User-agent: anthropic-ai
    User-agent: ClaudeBot
    User-agent: Claude-Web
    Disallow: /
    
    # --- Perplexity ---
    User-agent: PerplexityBot
    Disallow: /
    
    # --- ByteDance / TikTok ---
    User-agent: Bytespider
    Disallow: /
    
    # --- Amazon ---
    User-agent: Amazonbot
    Disallow: /
    
    # --- Facebook / Meta ---
    User-agent: FacebookBot
    Disallow: /
    
    # --- Apple ---
    User-agent: Applebot-Extended
    Disallow: /
    
    # --- Other AI dataset crawlers ---
    User-agent: Diffbot
    User-agent: ImagesiftBot
    User-agent: Omgilibot
    User-agent: Omgili
    User-agent: YouBot
    Disallow: /
    
    # --- SEO crawlers often used for AI datasets ---
    User-agent: AhrefsBot
    User-agent: SemrushBot
    User-agent: MJ12bot
    User-agent: DotBot
    User-agent: CCBot
    Disallow: /
    
    # --- Default rules for normal crawlers ---
    User-agent: *
    Crawl-delay: 10
    Disallow: /admin/
    Disallow: /error/
    
    Sitemap: https://www.insurancewebsitessocialmedia.com/sitemap.xml