Kill the database, save the platform: Chaos engineering for a resilient data layer

Reliability is a core promise of every Internal Developer Platform, yet many platform teams still depend on databases that can become critical points of failure. In this interactive workshop, participants will deploy CockroachDB within a platform environment, deliberately introduce failures, and observe how a distributed SQL database maintains availability without downtime. Through live demos and guided exercises, we'll explore node failures, multi-region deployment strategies, data residency requirements, and self-service data provisioning. Attendees will leave with practical patterns for building resilient platform architectures and applying chaos engineering techniques to uncover weaknesses before they impact users.