AIBullisharXiv – CS AI · Mar 36/1010
🧠
Agentic Multi-Source Grounding for Enhanced Query Intent Understanding: A DoorDash Case Study
DoorDash developed an AI system that uses multiple data sources to better understand ambiguous search queries by combining catalog data with web search results. The system achieved significant accuracy improvements over traditional methods and is now deployed across 95% of DoorDash's daily search traffic.