{
  "entity_a": {
    "slug": "claude-searchbot",
    "name": "Claude-SearchBot"
  },
  "entity_b": {
    "slug": "google-extended",
    "name": "Google-Extended"
  },
  "fields_documented": 11,
  "claims": 17,
  "last_verified": "2026-09-13",
  "fields": [
    {
      "field": "cites_sources",
      "value_a": "not_documented",
      "value_b": null,
      "claim_id_a": 34,
      "claim_id_b": null,
      "same": false
    },
    {
      "field": "honours_crawl_delay",
      "value_a": "yes",
      "value_b": "n/a",
      "claim_id_a": 29,
      "claim_id_b": 56,
      "same": false
    },
    {
      "field": "publishes_ip_list",
      "value_a": "yes",
      "value_b": "no",
      "claim_id_a": 30,
      "claim_id_b": 57,
      "same": false
    },
    {
      "field": "purpose_documented",
      "value_a": "search",
      "value_b": "policy_only",
      "claim_id_a": 32,
      "claim_id_b": 59,
      "same": false
    },
    {
      "field": "reads_llms_txt",
      "value_a": "not_documented",
      "value_b": null,
      "claim_id_a": 35,
      "claim_id_b": null,
      "same": false
    },
    {
      "field": "respects_robots_txt",
      "value_a": "yes",
      "value_b": "n/a",
      "claim_id_a": 28,
      "claim_id_b": 55,
      "same": false
    },
    {
      "field": "robots_token_differs_from_ua",
      "value_a": null,
      "value_b": "yes",
      "claim_id_a": null,
      "claim_id_b": 62,
      "same": false
    },
    {
      "field": "separate_search_and_training_tokens",
      "value_a": "yes",
      "value_b": "yes",
      "claim_id_a": 33,
      "claim_id_b": 60,
      "same": true
    },
    {
      "field": "user_agent_string_full",
      "value_a": "not_documented",
      "value_b": null,
      "claim_id_a": 36,
      "claim_id_b": null,
      "same": false
    },
    {
      "field": "verifiable_by_rdns",
      "value_a": "not_documented",
      "value_b": "n/a",
      "claim_id_a": 31,
      "claim_id_b": 58,
      "same": false
    },
    {
      "field": "what_it_controls",
      "value_a": null,
      "value_b": "Gemini model training and grounding, not Search inclusion",
      "claim_id_a": null,
      "claim_id_b": 61,
      "same": false
    }
  ],
  "differences": [
    {
      "field": "cites_sources",
      "statement_a": "Anthropic does not publish whether Claude search responses cite pages crawled by Claude-SearchBot.",
      "statement_b": null,
      "claim_id_a": 34,
      "claim_id_b": null
    },
    {
      "field": "honours_crawl_delay",
      "statement_a": "Claude-SearchBot respects the Crawl-delay directive in robots.txt when crawling domains.",
      "statement_b": "Google does not publish any Crawl-delay behaviour for the Google-Extended token.",
      "claim_id_a": 29,
      "claim_id_b": 56
    },
    {
      "field": "publishes_ip_list",
      "statement_a": "Anthropic publishes the IP address ranges used by Claude-SearchBot as a JSON file at https://claude.com/crawling/bots.json.",
      "statement_b": "Google publishes no IP list for Google-Extended because Google-Extended has no separate HTTP request user agent string.",
      "claim_id_a": 30,
      "claim_id_b": 57
    },
    {
      "field": "purpose_documented",
      "statement_a": "Claude-SearchBot analyses online content to improve the relevance and accuracy of Claude search responses.",
      "statement_b": "Google-Extended is a standalone product token that controls whether Google uses crawled content to train Gemini models.",
      "claim_id_a": 32,
      "claim_id_b": 59
    },
    {
      "field": "reads_llms_txt",
      "statement_a": "Anthropic does not publish whether Claude-SearchBot reads llms.txt files.",
      "statement_b": null,
      "claim_id_a": 35,
      "claim_id_b": null
    },
    {
      "field": "respects_robots_txt",
      "statement_a": "Claude-SearchBot honours industry standard robots.txt directives that signal do not crawl.",
      "statement_b": "Google-Extended is a robots.txt token that publishers set to control use of crawled content for Gemini training.",
      "claim_id_a": 28,
      "claim_id_b": 55
    },
    {
      "field": "robots_token_differs_from_ua",
      "statement_a": null,
      "statement_b": "Google-Extended is a robots.txt control token and does not correspond to a crawler user agent string.",
      "claim_id_a": null,
      "claim_id_b": 62
    },
    {
      "field": "user_agent_string_full",
      "statement_a": "Anthropic does not publish a full user agent string for Claude-SearchBot.",
      "statement_b": null,
      "claim_id_a": 36,
      "claim_id_b": null
    },
    {
      "field": "verifiable_by_rdns",
      "statement_a": "Anthropic does not publish a reverse-DNS verification method for Claude-SearchBot.",
      "statement_b": "Google does not publish a reverse-DNS verification method for Google-Extended.",
      "claim_id_a": 31,
      "claim_id_b": 58
    },
    {
      "field": "what_it_controls",
      "statement_a": null,
      "statement_b": "Google-Extended controls AI training and grounding in Google systems and does not control Google Search inclusion.",
      "claim_id_a": null,
      "claim_id_b": 61
    }
  ],
  "sources": [
    "https://claude.com/crawling/bots.json",
    "https://developers.google.com/search/docs/appearance/ai-features",
    "https://developers.google.com/search/docs/crawling-indexing/google-common-crawlers",
    "https://support.claude.com/en/articles/8896518-does-anthropic-crawl-content-from-the-web-and-how-can-site-owners-block-the-crawler"
  ]
}