Cost & ops
Output Drift
Also known as model drift, quality drift
Output drift is a gradual change in a live system's output, with no release behind it.
Causes include a provider adjusting a model, a retrieval corpus shifting, or edge cases the eval set never covered.
It is slower and less visible than a hard regression.
It needs its own threshold and a named owner, not the alerts that only catch a crash.
← Back to the full glossaryRelated terms
More in Cost & ops
Inference Cost Inference cost is what it costs to run a trained model on a request. Notebook-to-Production Notebook-to-production is the gap between a working prototype and a system that runs reliably. Model Deprecation Model deprecation is a provider retiring a model version on its own schedule. Acceptance Rate Acceptance rate is the share of an agent's proposed changes a human reviewer approves.