Warehouses left running, oversized for the workload, with auto-stop disabled. Kostavo scans for all of it and notifies your team or stops them automatically.
A warehouse with no auto-stop keeps consuming compute even when no one is querying. Databricks doesn't enforce this for you.
Analysts spin up 2XL warehouses for exploratory queries. Without size policies, overprovisioning goes unnoticed.
Warehouses on the preview channel, with open permissions, missing cost tags, or excessive multi-cluster scaling create hidden risk.
Flags warehouses that are currently running and verifies whether auto-stop is disabled or set above your configured threshold. Can stop them automatically.
Scans warehouse size against your configured maximum and flags warehouses where the multi-cluster max exceeds a reasonable threshold.
Detects warehouses on the preview channel, with overly permissive access, missing cost tags, or not using serverless compute.
Warehouse findings alongside the rest of your estate: running warehouses, sizing, and serverless candidates.
Currently running: notify or stop
Disabled or above max threshold: fix or notify
Exceeds maximum: downscale or notify
Max clusters too high: fix or notify
Open access or preview channel: notify
Missing cost tags or not using serverless: notify
SQL Alerts (v2) running on warehouses larger than needed: can move to a smaller warehouse automatically
SQL Alerts (v2) scheduled to run too frequently (wasteful polling against a warehouse): fix or notify
SQL Alerts (v2) with no notification destination configured: silently running but alerting no one
Alerts using the deprecated legacy SQL alert format: flag for migration or removal
Connect a workspace and see which warehouses are sitting idle right now.