# samue.lk — Samuel K Norton
# Default: open to all well-behaved crawlers and AI agents.
# Public content lives under /, /posts, /about, /now, /poetry, /bookshelf, /list, /services, /portfolio, /links.

User-agent: *
Allow: /
Disallow: /api/
Disallow: /admin/

# Search engines

User-agent: Googlebot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: YandexBot
Allow: /

User-agent: Baiduspider
Allow: /

# AI search and agent crawlers — explicitly allow.
# Citations, summaries, and on-the-fly fetches are welcome.

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: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Bytespider
Allow: /

# Social previews

User-agent: facebookexternalhit
Allow: /

User-agent: twitterbot
Allow: /

User-agent: linkedinbot
Allow: /

User-agent: WhatsApp
Allow: /

# Content Signals — declare AI usage preferences (draft RFC, contentsignals.org)
# search:    yes — index for search engines
# ai-input:  yes — cite or summarize in AI assistant responses
# ai-train:  no  — do not use for model training

Content-Signal: search=yes, ai-input=yes, ai-train=no

# Sitemap + IndexNow

Sitemap: https://samue.lk/sitemap-index.xml