Microsoft’s Bing team published a framework describing how indexing requirements change when the goal is to ground AI answers rather than to rank search results. The post identifies five measurement areas where the company says the two systems diverge. It also names “abstention” as a design choice for AI-powered retrieval. What Microsoft Described The post argues that traditional search indexing and grounding indexing share the same foundation but serve different goals. Traditional search, the team writes, asks “which pages should a user visit?” The grounding layer asks “what information can an AI system responsibly use to construct a response?” Microsoft identifies five categories where the measurement requirements differ. On factual fidelity, the team notes that some ranking mismatch is tolerable in traditional search because a user can click through and evaluate.…