See full implementation open source here → https://github.com/mongodb-industry-solutions/smf-yield-defect-detection When a critical excursion hits a semiconductor fab, engineers often have to investigate across multiple disconnected systems — costing time and money. Traditionally, investigating a "critical excursion" requires engineers to manually stitch together context from five or more disparate systems—ranging from SQL records and time series telemetry to wafer image storage. In this video, we show how MongoDB Atlas enables real-time detection and AI-powered root cause analysis by unifying telemetry, vector search, and operational data into a single platform. Watch a live demo of an AI agent that investigates issues autonomously and delivers evidence-based insights in seconds. Key features covered: Converging time series, vector search, and document data. Triggering AI agents via real-time change streams. Multimodal vector search for wafer defect identification. Autonomous correlation of sensor data and historical RCA reports. Explore more hands-on tutorials on the MongoDB Developer YouTube Channel! 00:00:00 The Crisis of Manual Data Stitching 00:01:02 Converging Time Series and Vector Search 00:01:37 Building the Autonomous AI Agent 00:02:31 Demo: Real-Time Root Cause Analysis 00:03:51 Impact: From Post-Mortems to Real-Time Action Subscribe to the MongoDB for Developers YouTube Channel: https://www.youtube.com/@MongoDBDevelopers?sub_confirmation=1 Sign-up for a free cluster → https://www.mongodb.com/cloud/atlas/register Subscribe to MongoDB YouTube→ https://mdb.link/subscribe Visit Mongodb.com → https://mdb.link/MongoDB Read the MongoDB Blog → https://mdb.link/Blog Read the Developer Blog → https://mdb.link/developerblog MongoDB for Developers YouTube Channel → https://www.youtube.com/@MongoDBDevelopers

 297      15