User-agent: *
Allow: /
Disallow: /games/
Disallow: /patterns
Disallow: /lessons
Disallow: /exercises
Disallow: /training
Disallow: /timemachine
Disallow: /compare
Disallow: /settings
Disallow: /skill
Disallow: /affiliate
Disallow: /prompts
Disallow: /feedbacks
Disallow: /analytics
Disallow: /nav
Disallow: /graph
Disallow: /data-access-request

# Welcome AI crawlers — Chess DNA is meant to be cited.
# Full allowlist mirrors what citation-leader competitors (chesssolve.com) ship.
# Each bot maps to a different AI engine / training pipeline:
#   GPTBot              → ChatGPT training data
#   OAI-SearchBot       → ChatGPT browse-mode citations
#   ChatGPT-User        → live ChatGPT browsing requests
#   anthropic-ai        → Claude training data
#   ClaudeBot           → Claude browse-mode citations
#   Claude-Web          → live Claude browsing requests
#   PerplexityBot       → Perplexity citations
#   YouBot              → You.com citations
#   cohere-ai           → Cohere training
#   Google-Extended     → Gemini / Google AI Overviews training
#   Amazonbot           → Alexa / Amazon AI citations
#   Bytespider          → Doubao / TikTok AI
#   Applebot-Extended   → Apple Intelligence training
#   FacebookBot         → Meta AI citations
#   CCBot               → Common Crawl (general LLM training corpus)
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: anthropic-ai
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: PerplexityBot
User-agent: YouBot
User-agent: cohere-ai
User-agent: Google-Extended
User-agent: Amazonbot
User-agent: Bytespider
User-agent: Applebot-Extended
User-agent: FacebookBot
User-agent: CCBot
Allow: /

Sitemap: https://chessdna.app/sitemap.xml