AI Reliability Console
Monitor behavior, manage risk, and ship confidently
Evaluation Studio / Run
Support Assistant - Emergency Replay
Support Assistant · gpt-4.1 · run_220
Decision
No Ship
Confidence
91%
Overall Score
68
Release Gate
5.4%
Critical Failure Rate
Release GateRegressionDisagreement 19.9%
Regression exceeded safety and latency guardrails; immediate rollback recommended.
Derived metrics
Helpfulness: 66Information Density: 61Format Adherence: 88Coherence: 63
Decision metrics by intent
Release Gate
Decision: No Ship
Critical Failure Rate: 5.4%
Pass Rate: 81.5%
Regression
Regression %: 5.8%
Result Variance %: 8.4%
Pass Rate: 81.5%
Policy pack: Regulated Support v4Evaluator versions lockedResidency: US-EastAudit evidence chain: active
Run Metric Timeline
Quality and risk evolution during execution.
Judge Score Breakdown
Per-metric score spread across evaluators.