At 7-Eleven, operational resilience at scale depends on how quickly data can be converted into action. With thousands of stores generating structured sensor telemetry, equipment failures can directly impact revenue, yet traditional development approaches were too slow to scale predictive maintenance solutions efficiently. This session explores how 7-Eleven accelerated ML delivery using Databricks and an agentic AI–driven workflow. Built on Delta tables and a medallion architecture, the solution enabled scalable ingestion, governed access, and ML-based failure detection. Using Windsurf, GitLab, and Databricks Asset Bundles, the team significantly accelerated code generation, integration, and deployment. The end-to-end solution was delivered in under two weeks versus an estimated six weeks, reducing development effort, accelerating time-to-market, and helping protect millions in revenue.
