# Commonplace (c.austinpranger.com) - robots.txt
# This content may not be used to train AI models. Reasoning: https://c.austinpranger.com/ai-crawlers/
# Robots exclusion protocol: RFC 9309. Known AI training crawlers are also refused by the server.

# AI training crawlers and opt-out tokens: no access.
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: CCBot
User-agent: Bytespider
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: Diffbot
User-agent: Amazonbot
User-agent: Omgilibot
User-agent: omgili
User-agent: ImagesiftBot
User-agent: Timpibot
User-agent: AI2Bot
User-agent: Ai2Bot-Dolma
User-agent: PanguBot
User-agent: YouBot
User-agent: img2dataset
User-agent: Kangaroo Bot
User-agent: GoogleOther
User-agent: meta-externalagent
User-agent: meta-externalfetcher
User-agent: FacebookBot
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: Webzio-Extended
Disallow: /

# AI search indexers (OAI-SearchBot, Claude-SearchBot, PerplexityBot, DuckAssistBot) and assistants fetching a page for a person
# (ChatGPT-User, Claude-User, Perplexity-User, MistralAI-User) fall under the default group below: allowed.

User-agent: *
Allow: /
# Content Signals (a proposed convention): search yes, use as a live answer source yes, training no.
Content-Signal: search=yes, ai-input=yes, ai-train=no

Sitemap: https://c.austinpranger.com/sitemap-index.xml