# Policy: search engines and agents that fetch a page when a person asks
# may read this site. Crawlers that only collect AI training data may not.
#
# Content-Signal (https://contentsignals.org) has three keys: search,
# ai-input and ai-train. A crawler obeys only the most specific group that
# names it, so each Allow group repeats the signal.
#
# Edge cases:
# - Google-Extended and Applebot-Extended are not crawlers. Googlebot and
#   Applebot fetch the pages; these tokens only control use for AI training.
#   Blocking Google-Extended also stops Gemini Apps and Vertex AI grounding.
#   It does not change Google Search or AI Overviews, which use Googlebot.
# - GoogleOther, Google-CloudVertexBot, Baiduspider and Amazonbot are not
#   training-only, so they follow the * group.
# - Agents that fetch for a person (ChatGPT-User, Claude-User,
#   Perplexity-User...) may not read robots.txt at all. They are named
#   here so the policy for them is explicit.

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

# Crawlers that only collect AI training data. This group comes first:
# parsers that take the first substring match would otherwise read
# Applebot-Extended as Applebot.
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: CCBot
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: Bytespider
User-agent: meta-externalagent
User-agent: FacebookBot
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: MistralAI-Training
User-agent: Diffbot
User-agent: ImagesiftBot
User-agent: omgili
User-agent: omgilibot
User-agent: Timpibot
User-agent: AI2Bot
User-agent: Webzio-Extended
User-agent: Cotoyogi
User-agent: ICC-Crawler
Disallow: /

# Search indexes and agents that fetch when a person asks.
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: DuckAssistBot
User-agent: MistralAI-User
User-agent: meta-externalfetcher
User-agent: Applebot
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

Sitemap: https://piyushc.com/sitemap-index.xml