From the source
AI SRE assists engineering teams across Databricks operate 100s of microservices deployed across 1,500 Kubernetes clusters, spanning 70+ regions and three clouds The platform enables teams to build and maintain their own composable agentic runbooks, allowing the system to successfully scale across 150+ teams and 2,000+ daily investigations.
To ensure reliability, the system prioritizes transparency over black-box reasoning by linking every diagnostic recommendation directly to verifiable raw evidence, forcing a "context-first" development approach.
In our previous blog post , we shared how Databricks uses AI to debug thousands of databases.
Here, we continue that story by exploring how our engineers use AI to operate 100s of microservices across 1500+ Kubernetes clusters, spanning 70+ regions and three clouds.
When something breaks at 2 AM, the on-call engineer needs to answer one question quickly: What changed?
AI SRE is an AI-powered debugging agent that begins investigating as soon as an incident fires.
It correlates signals from across our stack and guides engineers through root cause analysis.
…
