Clusters left running, warehouses nobody's querying, apps nobody's using. Kostavo scans for resources that are active outside their expected operating window and stops them automatically.
A developer starts a cluster on Friday afternoon and forgets to stop it. It runs all weekend. Databricks won't stop it for you.
Databricks Apps keep running after work hours even when no one is connected. Dev apps don't need to be available at 3am.
Without continuous scanning, nobody knows what's running over the weekend, and forgotten resources quietly run for days.
Kostavo can automatically stop Databricks Apps after operating hours and start them again before your team arrives. The only resource type with full start/stop scheduling.
Kostavo scans for clusters and warehouses that are currently running. On finding them active, it can notify the resource owner or stop them automatically.
Beyond scheduling, Kostavo also verifies that Databricks Apps aren't running on compute that's larger than allowed: flags oversized app compute and notifies the owner.
Kostavo flags compute that is still running, like a GPU cluster idle since Friday evening.
Full start/stop scheduling: stop after hours, start before work
Running cluster detection: notify or stop automatically
Running warehouse detection: notify or stop automatically
Provisioned throughput and scale-to-zero disabled detection
Running Vector Search endpoints: notify or flag for removal
Continuously-running jobs and declarative pipelines in continuous mode: notify or stop
SQL Alerts scheduled to run too frequently against a warehouse
Connect a workspace and see what is still running this weekend.