DoorDash, Instacart, Uber Eats pick three distinct LLM search strategies
They integrate LLMs differently: DoorDash enriches a knowledge graph offline, Instacart applies LLMs at the query‑understanding layer, and Uber Eats fine‑tunes a model into the embedding backbone of a two‑tower retrieval system. The contrast shows that integration depth is dictated by existing infrastructure, giving teams a framework for choosing how deeply to embed AI in production search.