AI Reliability Console
Monitor behavior, manage risk, and ship confidently
Evaluation Studio / Run
Voice QA - Escalation Sweep
Voice QA Agent · gpt-4o-mini · run_222
Decision
Pending
Confidence
52%
Overall Score
75
Release Gate
3.4%
Critical Failure Rate
Release GateQuality DiagnosisDisagreement 17.1%
Compliance language edge-cases are still unstable; escalation queue is growing.
Derived metrics
Helpfulness: 73Information Density: 70Format Adherence: 91Coherence: 71
Decision metrics by intent
Release Gate
Decision: Pending
Critical Failure Rate: 3.4%
Pass Rate: 86.9%
Quality Diagnosis
Overall Score: 75
Pass Rate: 86.9%
Judge Agreement: 74%
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.