QAVE Studio Docs
QAVE Studio Docs
Sign inGet started — the Studio loop
Getting StartedFirst assurance runQuick assure
ConceptsLifecycleGlossaryHow QAVE Studio worksComing soon
Account & workspaceSignup and loginPeopleDemo creditsRolesSettings
Generate simulation suitesContext templatePII and field enhanceDimensionsAgents and plannerDraft review and Save
ExportExport formatsExport formats (detail)
Assurance SDKSDK overviewQAVE Studio suite fetch APIAgent and JSONL queueLangfuse bridge
Execute and tracesRecipe chatbot (reference SUT)TracingFetch tracing
AssureEvaluate APIRubrics and evidenceReading scores
History
WorkbenchGolden data
CoverageCoverage dashboardCoverage strategiesCoverage advisorTest case quality
RAG AssuranceRAG runsRAG datasetsRAG analytics
Project evalsError analysisUnderstanding scores
Studio guidesDimensionsTuplesConversation modesMulti-lingual testingWorkflowsHuman reviewBest practices
ReferenceAPI and packagesTroubleshooting
Workbench

Golden data

How SME annotations become calibration and preference pairs.

Golden data is the flywheel fuel:

  1. Assurance produces a score + evidence
  2. SMEs confirm, correct, or preference-rank outcomes
  3. Labels land in the calibration store
  4. Future runs and (eventually) customer SLMs improve against your bar

Keep PII redacted in review UIs. Prefer structured feedback over free-text-only notes when exporting for training.

Workbench

SME review queue for turning assurance results into golden judgment.

Coverage

Measure release readiness from dimensions, tuples, and approved suites.