# --- Allow Google Search Indexing ---
User-agent: Googlebot
Allow: /

# --- Block Google AI (Gemini/Vertex AI training) ---
User-agent: Google-Extended
Disallow: /

# --- Block OpenAI (GPT/ChatGPT) ---
User-agent: GPTBot
Disallow: /
User-agent: ChatGPT-User
Disallow: /

# --- Block Anthropic (Claude) ---
User-agent: anthropic-ai
Disallow: /
User-agent: Claude-Web
Disallow: /

# --- Block Common Crawl (Primary dataset for many LLMs) ---
User-agent: CCBot
Disallow: /

# --- Block Cohere ---
User-agent: cohere-ai
Disallow: /

# --- Block Meta (Llama/Facebook) ---
User-agent: FacebookBot
Disallow: /

# --- Block Perplexity ---
User-agent: PerplexityBot
Disallow: /

# --- Fallback for other compliant crawlers ---
User-agent: *
Allow: /