Yelp's engineering team details how they evolved 'Biz Ask Anything' (Yelp Assistant on business pages) from a two-week prototype to a production system over nine months. Key challenges covered include: building near-real-time data pipelines (NRT indices, Cassandra EAV store) with sub-100ms reads; a multi-stage question analysis
Table of contents
Finding an Answer in an Ocean of ContentThe Life of a QuestionThe Data Problem — Scalable, Fresh, SearchableDeconstructing the Question — Intent, Safety, and RetrievalAnswer Quality — Accuracy, Helpfulness and VoicePerformance — Time-to-First-Token is CrucialCost - Every token countsUser Education — “What Can I Even Ask?”AcknowledgementsSort: