# PartSpec.AI robots policy
# Principle: BLOCK bots that ingest content to TRAIN models (no traffic back).
#           ALLOW bots that fetch a page to CITE it in an answer (traffic + attribution).
# robots.txt is honor-system; well-behaved bots obey it.

# --- BLOCK: pure training crawlers ---------------------------------------
User-agent: GPTBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: YouBot
Disallow: /

# --- ALLOW (by omission): answer/retrieval engines that cite us -----------
# Googlebot, Bingbot, Google-Extended (kept on purpose: AI Overviews reach),
# OAI-SearchBot, ChatGPT-User, PerplexityBot, Perplexity-User,
# Claude-User, Claude-SearchBot, Applebot (search). These fall through to *.

# --- Everyone else --------------------------------------------------------
# Content Signals (contentsignals.org / IETF draft): machine-readable usage
# preferences. ai-train=no (don't train on us), search=yes (do index/cite us),
# ai-input=yes (ok to use as live grounding in generated answers).
User-agent: *
Content-Signal: ai-train=no, search=yes, ai-input=yes
Allow: /

Sitemap: https://partspec.ai/sitemap.xml