# robots.txt — Alexander van der Pol (Senior Engineering Manager — Data Center & Cloud Infrastructure)
#
# Generated from content/crawler-policy.json by scripts/build_site.py.
# Policy of record with full rationale: /ai-crawler-policy/
#
#   ALLOWED  classic search crawlers + AI *search/retrieval* + user-initiated fetchers
#   BLOCKED  AI *training* crawlers (no attribution benefit for a personal profile)
#
# Classic search
User-agent: *
Allow: /
Disallow: /cache/
Disallow: /scripts/

# --- AI search / retrieval (these produce referrals and citations) ---
User-agent: OAI-SearchBot
Allow: /
User-agent: ChatGPT-User
Allow: /
User-agent: Claude-User
Allow: /
User-agent: Claude-SearchBot
Allow: /
User-agent: PerplexityBot
Allow: /
User-agent: Perplexity-User
Allow: /
User-agent: Google-CloudVertexBot
Allow: /
User-agent: Google-Extended
Allow: /
User-agent: Applebot
Allow: /
User-agent: OAI-AdsBot
Allow: /

# --- AI training crawlers: disallowed (see /ai-crawler-policy/) ---
User-agent: GPTBot
Disallow: /
User-agent: ClaudeBot
Disallow: /
User-agent: Applebot-Extended
Disallow: /
User-agent: CCBot
Disallow: /
User-agent: anthropic-ai
Disallow: /
User-agent: Bytespider
Disallow: /
User-agent: meta-externalagent
Disallow: /
User-agent: Amazonbot
Disallow: /
User-agent: Diffbot
Disallow: /

Sitemap: https://alexander-van-der-pol.pages.dev/sitemap.xml