GeoAeoAleGeoAeoAle · Platforms
What official sources say about search and citation in Google, ChatGPT, Perplexity, and other systems.
Published items: 13 · growing collection
Microsoft Learn describes generated answers over public websites in Copilot Studio. This is useful evidence about public-web settings and their limits, but it does not prove that a page will be shown or cited in consumer Bing or Copilot. Measure page access, selection, displayed links, and visits separately.
Read articleBrave Search is a search service with its own independent index. Its AI Answers produce a short summary from search results and show source links, while Ask Brave is designed for longer dialogue and follow-up prompts. The documentation confirms these modes and their source display, but does not reveal why one URL is selected over another.
Read articleChatGPT Search is a web-connected answer mode in ChatGPT. OpenAI distinguishes OAI-SearchBot for search, GPTBot for training, and ChatGPT-User for user-triggered requesting pages. Allowing a crawler enables access, but does not guarantee source selection, inclusion, ranking, or a source link.
Read articleAnthropic’s official documentation confirms Claude web search and the sources shown in responses. It does not disclose one universal ordering rule, the complete page-selection process, or a rule that every accessible page will be selected and cited. Evaluate Claude using saved answers and links, while measuring site access separately.
Read articleDuckDuckGo Search Assist is an optional feature in search results: it scans the web, generates a brief answer, and always links it to one or two sources. Duck.ai is a separate anonymized chat experience using models from multiple providers. Search Assist and Duck.ai should not be measured as one system.
Read articleGemini may show a Sources panel with links, but that panel proves only which sources were displayed for one answer. It does not reveal the internal crawler, ordering, or whether all relevant pages were considered. Measure page access, displayed links, support for the specific claim, and visits as separate events.
Read articleGoogle AI Search is a set of generative features inside Google Search. A site should be crawlable and indexable through normal Search systems, but Google does not promise a separate path into an AI answer. Search Console and server logs expose parts of the process, not a complete source-link records.
Read articleX Help describes Grok as a product that may decide to search public X posts and conduct a real-time web search. That confirms two observable search routes—X posts and the wider web—but not the private index, ranking weights, candidate list, or reason for a particular source link.
Read articleKagi combines its Teclis and TinyGem indexes with external and specialist sources, user controls, and AI features. Assistant can use the web through Kagi Search, but the web setting, selected filter, and answer link are conditions we can observe for one prompt—not a promise that a page will be cited.
Read articlePerplexity documents a crawler called PerplexityBot, but a request from that bot proves only that a page was delivered. It does not prove that the page entered an index, was selected for a particular prompt, appeared in an answer, or brought a visitor. Measure technical access, page selection, displayed source links, and visits separately.
Read articleYandex describes Neuro/Yandex AI as a mode that breaks down complex questions, finds relevant web materials, synthesizes an answer, and adds source links. Official documentation confirms source-linked web discovery, but not internal ranking or source link of any particular page.
Read articleYandex documentation helps verify whether its search crawler can open a page, what server response it receives, and whether the page appears in the index. It does not reveal how Alice selects sources. A crawler visit proves only that the page was requested, not that Alice used or cited it in an answer.
Read articleYou.com publishes several distinct interfaces and modes: consumer agents, Research/ARI, and web/news search APIs. They share web data and source links, but their capabilities must not be conflated: API annotations, a highlighted Research source link, and a consumer answer are different audit artifacts.
Read article