3
AC
Quality/Human Review

Human Quality Review

Review queues, sampling, assignment, scorecards, disputes, secondary/consensus review and calibration — compare human vs AI evaluators.

Agreement rate

81.4%

Evaluator FP

6.2%

Evaluator FN

4.8%

Bias index

0.07

Review queuesRandom samplingRisk-based samplingAssignmentReviewer capacityReview formsScorecardsTimestamp commentsTranscript correctionAudio clippingEscalationDispute workflowSecondary reviewConsensus reviewCalibration sessionsReviewer quality analytics

Review queue

Review call_8f2a91

Tool failure + low containment

Queue

risk

Assignee

Ava Chen

Language

en-US

AI score

42

Human score

—

Duration

312s

Review form / scorecard

Completed reviews become labelled datasets for evaluator improvement. Timestamp comments and clips attach to the call record.

Calibration trend

Disagreement reasons

Reviewer capacity

ReviewerLoadTodayQA
Ava Chen28/401194
Marcus L.22/35991
Jordan P.18/30796
Priya N.14/25593