Yu Chen

Enterprise execution relies on trusted data, yet enrichment vendors often conflict and hierarchies drift. Manual validation is slow, and blind automation poses risks. This session details a production-grade validation system built on Databricks to transform CRM chaos into governed data layer. Using Delta Sharing feeds from various providers, we built a triangulation framework to reconcile signals across parent hierarchies, Salesforce structures, and revenue estimates. Rather than accepting data blindly, we implemented an AI governance layer that: 1. Reasons across enrichment signals to propose re-parenting. 2. Validates outputs via secondary agents to eliminate hallucinations. 3. Automates approvals based on confidence thresholds or escalates for human review. Attendees will learn to design multi-agent architectures and AI guardrails that preserve trust while accelerating planning cycles—enabling autonomous, governed workflows that improve revenue visibility at scale.

Due to the increasing value of GPU resources, we have restructured Xiaohongshu's image search system to create a near-line/offline inference pipeline, ultimately developing a high-quality cost-saving and efficiency-improving solution that utilizes idle computing resources to handle billions of data-scale model inference tasks: In the transient and easily evictable resource pool with tidal characte