DataRobot incident

Serverless Prediction Servers are impacted when an a new deployment is created or an existing deployment is modified.

DataRobot experienced a major incident on September 2, 2025 affecting Prediction and MLOps, lasting 2h 30m. The incident has been resolved; the full update timeline is below.

Started: Sep 02, 2025, 03:37 PM UTC
Resolved: Sep 02, 2025, 06:07 PM UTC
Duration: 2h 30m
Detected by Pingoru: Sep 02, 2025, 03:37 PM UTC

Affected components

PredictionMLOps

Update timeline

investigating Sep 02, 2025, 03:37 PM UTC

We've identified an issue impacting serverless deployments when a new deployment is created or an existing deployment is modified, in Japan cluster. Prediction against existing deployments deployed to serveless prediction server that are not modified are not impacted. Engineering currently working on a fix to address the issue.
resolved Sep 02, 2025, 06:07 PM UTC

Engineering has applied the fix to mitigate the issue impacting serverless deployments when a new deployment is created or an existing deployment is modified. The problem has now been contained.