How AI Search Works
Also: grounding AI, grounded generation
Grounding is the practice of tying an AI model's answer to verifiable external sources retrieved at query time, rather than relying on the model's internal memory alone. Grounded answers cite where each claim came from, which reduces hallucination and makes your content quotable.
Updated
When an engine grounds an answer, it is pulling specific, citable statements from real pages. Content with clear, sourced, self-contained claims is the easiest to ground, which is exactly what gets cited.
Grounding is the mechanism that connects retrieval to trust: the model shows its work by naming the sources behind the answer.
Go deeper
How Does AI Search Work?