{
 "slug": "google-extended",
 "name": "Google-Extended",
 "operator": "Google",
 "operator_slug": "google",
 "category": "ai-training",
 "category_label": "AI training crawlers",
 "robots_token": "Google-Extended",
 "user_agent_substring": "(control token only — no crawler)",
 "user_agent_example": "(none: Google-Extended never appears as a user-agent)",
 "respects_robots_txt": "n-a",
 "respects_robots_txt_label": "control token only — no crawler",
 "verification_method": "none",
 "verification_label": "no published verification method",
 "published_ip_ranges_url": null,
 "ip_ranges_endpoint": null,
 "ipv4_prefix_count": 0,
 "ipv6_prefix_count": 0,
 "what_it_is": "Not a crawler. A robots.txt token that tells Google whether pages Googlebot already fetched may be used to train and ground Gemini. You will never see it in an access log; disallowing it changes what Google does with content it fetched under a different name.",
 "cost_of_blocking": "You are excluded from Gemini grounding and Gemini training. Google Search ranking and indexing are explicitly unaffected. This is the cleanest 'no training, keep my search traffic' lever that exists.",
 "operator_docs": "https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers",
 "html_url": "https://www.pathwren.workers.dev/crawler/google-extended.html",
 "json_url": "https://www.pathwren.workers.dev/crawler/google-extended.json",
 "last_reviewed": "2026-09-03",
 "links": [
  {
   "rel": "self",
   "href": "https://www.pathwren.workers.dev/crawler/google-extended.json",
   "type": "application/json"
  },
  {
   "rel": "changes",
   "href": "https://www.pathwren.workers.dev/changes.json?since=111",
   "type": "application/json",
   "title": "What changed since your cursor — poll this instead of re-downloading this document",
   "cursor_param": "since",
   "head_cursor": 111,
   "min_poll_seconds": 21600,
   "how": "Read `cursor` from the response and send it back as `since`. It advances only when something really changed, so an unchanged answer is proof rather than luck — about 2.5 KB, or a 304 with no body if you send back the ETag."
  },
  {
   "rel": "related",
   "href": "https://www.pathwren.workers.dev/data/agents.json",
   "type": "application/json",
   "title": "Every crawler record in one file"
  },
  {
   "rel": "related",
   "href": "https://www.pathwren.workers.dev/crawler/google-extended.md",
   "type": "text/markdown"
  },
  {
   "rel": "service-desc",
   "href": "https://www.pathwren.workers.dev/openapi.json",
   "type": "application/json",
   "title": "Every read endpoint, described formally"
  }
 ]
}