# Default: allow all well-behaved crawlers
User-agent: *
Allow: /
Disallow: /app/
Disallow: /admin/
Disallow: /api/
Disallow: /confirm

# Explicit allow list for AI crawlers (same rules as default)
# OpenAI
User-agent: GPTBot
Allow: /
Disallow: /app/
Disallow: /admin/
Disallow: /api/
Disallow: /confirm

User-agent: OAI-SearchBot
Allow: /
Disallow: /app/
Disallow: /admin/
Disallow: /api/
Disallow: /confirm

User-agent: ChatGPT-User
Allow: /
Disallow: /app/
Disallow: /admin/
Disallow: /api/
Disallow: /confirm

# Anthropic
User-agent: ClaudeBot
Allow: /
Disallow: /app/
Disallow: /admin/
Disallow: /api/
Disallow: /confirm

User-agent: Claude-Web
Allow: /
Disallow: /app/
Disallow: /admin/
Disallow: /api/
Disallow: /confirm

User-agent: anthropic-ai
Allow: /
Disallow: /app/
Disallow: /admin/
Disallow: /api/
Disallow: /confirm

# Perplexity
User-agent: PerplexityBot
Allow: /
Disallow: /app/
Disallow: /admin/
Disallow: /api/
Disallow: /confirm

User-agent: Perplexity-User
Allow: /
Disallow: /app/
Disallow: /admin/
Disallow: /api/
Disallow: /confirm

# Google Gemini training (separate from Googlebot for Search)
User-agent: Google-Extended
Allow: /
Disallow: /app/
Disallow: /admin/
Disallow: /api/
Disallow: /confirm

# Apple Intelligence
User-agent: Applebot-Extended
Allow: /
Disallow: /app/
Disallow: /admin/
Disallow: /api/
Disallow: /confirm

# Cohere
User-agent: cohere-ai
Allow: /
Disallow: /app/
Disallow: /admin/
Disallow: /api/
Disallow: /confirm

# Common Crawl (feeds many LLM datasets)
User-agent: CCBot
Allow: /
Disallow: /app/
Disallow: /admin/
Disallow: /api/
Disallow: /confirm

# Block aggressive/low-value crawlers (optional — uncomment if load becomes an issue)
# User-agent: Bytespider
# Disallow: /
# User-agent: Amazonbot
# Disallow: /

Sitemap: https://grantsby.eu/sitemap.xml