Starter · Part of Quality Assurance
Bulk evaluation submission
CSV and JSON bulk imports for high-volume evaluation pipelines — auto-coaching tools, third-party speech-analytics platforms, and historical backfills land directly in the evaluation queue without manual entry. Async job processing per spec 30 §5.3.
For the operator
Use this when you're standing up a new QA program with historical data, integrating an AI-scoring vendor whose output needs to flow into your scorecard structure, or migrating from a legacy QA tool. Submit a CSV or JSON file via the bulk-import API; the worker validates each row against the target scorecard, assigns scores, and writes evaluations into the same queue manual evaluators use. Rejected rows surface in the job status response with row-level error context. Idempotency keys mean re-submitting a partially-failed batch is safe.
Business impact
Lets you scale QA volume without scaling QA headcount linearly. A BPO running 10,000 evaluations a month — half via AI scoring, half via human review — keeps both streams in one auditable queue, one calibration session, one report. The same API powers a backfill of two years of historical evaluations for a regulated client's compliance audit; without bulk import that's a year of manual data entry.