Logs, traces, metrics, sampled inputs, outputs, costs, latency, and evaluation results are linked across the request path. Privacy controls and retention policies limit what production data is captured.
Model observability collects signals needed to understand the behavior and health of an AI system in operation.
Logs, traces, metrics, sampled inputs, outputs, costs, latency, and evaluation results are linked across the request path. Privacy controls and retention policies limit what production data is captured.