{
  "entity_a": {
    "slug": "google-extended",
    "name": "Google-Extended"
  },
  "entity_b": {
    "slug": "perplexitybot",
    "name": "PerplexityBot"
  },
  "fields_documented": 11,
  "claims": 17,
  "last_verified": "2026-09-13",
  "fields": [
    {
      "field": "cites_sources",
      "value_a": null,
      "value_b": "yes",
      "claim_id_a": null,
      "claim_id_b": 118,
      "same": false
    },
    {
      "field": "honours_crawl_delay",
      "value_a": "n/a",
      "value_b": "not_documented",
      "claim_id_a": 56,
      "claim_id_b": 113,
      "same": false
    },
    {
      "field": "publishes_ip_list",
      "value_a": "no",
      "value_b": "yes",
      "claim_id_a": 57,
      "claim_id_b": 114,
      "same": false
    },
    {
      "field": "purpose_documented",
      "value_a": "policy_only",
      "value_b": "search",
      "claim_id_a": 59,
      "claim_id_b": 116,
      "same": false
    },
    {
      "field": "reads_llms_txt",
      "value_a": null,
      "value_b": "not_documented",
      "claim_id_a": null,
      "claim_id_b": 119,
      "same": false
    },
    {
      "field": "respects_robots_txt",
      "value_a": "n/a",
      "value_b": "yes",
      "claim_id_a": 55,
      "claim_id_b": 112,
      "same": false
    },
    {
      "field": "robots_token_differs_from_ua",
      "value_a": "yes",
      "value_b": null,
      "claim_id_a": 62,
      "claim_id_b": null,
      "same": false
    },
    {
      "field": "separate_search_and_training_tokens",
      "value_a": "yes",
      "value_b": "not_documented",
      "claim_id_a": 60,
      "claim_id_b": 117,
      "same": false
    },
    {
      "field": "user_agent_string_full",
      "value_a": null,
      "value_b": "Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; PerplexityBot/1.0; +https://perplexity.ai/perplexitybot)",
      "claim_id_a": null,
      "claim_id_b": 120,
      "same": false
    },
    {
      "field": "verifiable_by_rdns",
      "value_a": "n/a",
      "value_b": "not_documented",
      "claim_id_a": 58,
      "claim_id_b": 115,
      "same": false
    },
    {
      "field": "what_it_controls",
      "value_a": "Gemini model training and grounding, not Search inclusion",
      "value_b": null,
      "claim_id_a": 61,
      "claim_id_b": null,
      "same": false
    }
  ],
  "differences": [
    {
      "field": "cites_sources",
      "statement_a": null,
      "statement_b": "Perplexity links to the websites that PerplexityBot surfaces in Perplexity search results.",
      "claim_id_a": null,
      "claim_id_b": 118
    },
    {
      "field": "honours_crawl_delay",
      "statement_a": "Google does not publish any Crawl-delay behaviour for the Google-Extended token.",
      "statement_b": "Perplexity does not publish whether PerplexityBot honours the robots.txt Crawl-delay directive.",
      "claim_id_a": 56,
      "claim_id_b": 113
    },
    {
      "field": "publishes_ip_list",
      "statement_a": "Google publishes no IP list for Google-Extended because Google-Extended has no separate HTTP request user agent string.",
      "statement_b": "Perplexity publishes the IP address ranges used by PerplexityBot as a JSON file at https://www.perplexity.ai/perplexitybot.json.",
      "claim_id_a": 57,
      "claim_id_b": 114
    },
    {
      "field": "purpose_documented",
      "statement_a": "Google-Extended is a standalone product token that controls whether Google uses crawled content to train Gemini models.",
      "statement_b": "PerplexityBot surfaces and links websites in Perplexity search results.",
      "claim_id_a": 59,
      "claim_id_b": 116
    },
    {
      "field": "reads_llms_txt",
      "statement_a": null,
      "statement_b": "Perplexity does not publish whether PerplexityBot reads llms.txt files.",
      "claim_id_a": null,
      "claim_id_b": 119
    },
    {
      "field": "respects_robots_txt",
      "statement_a": "Google-Extended is a robots.txt token that publishers set to control use of crawled content for Gemini training.",
      "statement_b": "PerplexityBot honours robots.txt rules that webmasters set for the PerplexityBot token.",
      "claim_id_a": 55,
      "claim_id_b": 112
    },
    {
      "field": "robots_token_differs_from_ua",
      "statement_a": "Google-Extended is a robots.txt control token and does not correspond to a crawler user agent string.",
      "statement_b": null,
      "claim_id_a": 62,
      "claim_id_b": null
    },
    {
      "field": "separate_search_and_training_tokens",
      "statement_a": "Google-Extended controls Gemini training use only and does not affect inclusion in Google Search.",
      "statement_b": "Perplexity does not document a separate training crawler token alongside PerplexityBot.",
      "claim_id_a": 60,
      "claim_id_b": 117
    },
    {
      "field": "user_agent_string_full",
      "statement_a": null,
      "statement_b": "PerplexityBot sends the user agent string Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; PerplexityBot/1.0; +https://perplexity.ai/perplexitybot).",
      "claim_id_a": null,
      "claim_id_b": 120
    },
    {
      "field": "verifiable_by_rdns",
      "statement_a": "Google does not publish a reverse-DNS verification method for Google-Extended.",
      "statement_b": "Perplexity does not publish a reverse-DNS verification method for PerplexityBot.",
      "claim_id_a": 58,
      "claim_id_b": 115
    },
    {
      "field": "what_it_controls",
      "statement_a": "Google-Extended controls AI training and grounding in Google systems and does not control Google Search inclusion.",
      "statement_b": null,
      "claim_id_a": 61,
      "claim_id_b": null
    }
  ],
  "sources": [
    "https://developers.google.com/search/docs/appearance/ai-features",
    "https://developers.google.com/search/docs/crawling-indexing/google-common-crawlers",
    "https://docs.perplexity.ai/docs/resources/perplexity-crawlers",
    "https://www.perplexity.ai/perplexitybot.json"
  ]
}