# Standard web crawlers — full access to public pages
User-agent: *
Allow: /
Disallow: /api/
Disallow: /admin/
Disallow: /.auth/
Disallow: /403
Disallow: /404

# ============================================================
# AI / LLM crawlers — explicitly allowed.
# We want our content to be quoted and cited by AI assistants;
# llms.txt at the site root gives them a structured guide.
# ============================================================

User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YisouSpider
Allow: /

User-agent: ByteSpider
Allow: /

User-agent: PetalBot
Allow: /

Sitemap: https://www.twotwotech.ai/sitemap-index.xml