Glossary · Grounding
Giving an AI model content from the Google Search index at prompt time, so that its answer rests on that content.
Google’s documentation 2
Documented in
Google's crawler documentation defines grounding in Gemini Apps and in Grounding with Google Search on Vertex AI as providing content from the Google Search index to the model at prompt time, and sites manage whether their content is used for it with the Google-Extended robots.txt token.
Google · Day 2 · Lightning session D: Rendering and JavaScript
Google's Gemini API documentation on grounding with Google Search says the model automatically generates and runs one or more search queries when needed, and the response lists the search queries it executed.
Google AI for Developers (Gemini API docs) · Day 3 · Making sense of users' queries
Said at the event 6
Slide and stage claims that name it, the ones Google’s documentation does not cover first.
Consistent with docs 2
AI Mode and AI Overviews use the same crawling and the same index as Search. At serving they add grounding on the Search index and query fan-out.
Day 1 · How Search works and where's AI?
Google's slide on how LLM features with grounding generally work showed a query going to both the search engine and an LLM, the search engine's results going to the LLM, the LLM generating fan-out queries that go back to the search engine, and the LLM returning answers with links.
John Mueller · Day 3 · Making sense of users' queries
Nothing to verify 1
A community speaker described the retrieval stage as whether an AI requests a site's pages when grounding its answer; if it does not, the cause may be a crawling or an indexing issue.
Day 1 · Lightning session A: Automation and AI
Press and analysis 3
The panel spoke of blocking Google's 'AI crawling or training' with Google-Extended, but Google documents Google-Extended as a usage token, not a crawler: disallowing it does not stop Googlebot fetching pages and only controls use for Gemini training and grounding.
Ibrahim Anjro · Day 1 · Q&A
nofollow is a link-graph hint for search engines, not an access control: to keep AI crawlers away from content, use robots.txt rules for the specific crawlers; at Google, Google-Extended covers Gemini training and grounding, and the Search generative AI control covers AI Overviews and AI Mode.
Ibrahim Anjro · Day 2 · Controlling indexing
Google documents Gemini grounding only as content from the Search index at prompt time; the live read of a specific page at a user's request, described on stage, is not documented, so it is unclear whether it works like a user-triggered fetcher, which generally ignores robots.txt, or follows Google-Extended.
Ibrahim Anjro · Day 2 · Lightning session D: Rendering and JavaScript
Built on these claims 6
Kit items about Grounding: their own words name it, or several of the claims they rest on do.
Developer requirements 2
Also instory angle A-001glossary terms Grounding, AI Mode, Hallucination
Connected things 13
Relations
Most often named with it
Things named in the same claim, with the number of claims they share.
Topics that feature it