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
Assure

Reading scores

Interpret score cards, quality labels, and review signals.

Score types

  • Continuous (0.0–1.0) — primary deterministic score
  • Quality labels (how Studio maps API values):
API quality_labelUI label
highAudit-ready
mediumDirectional
lowImprecise
uncertainInsufficient

Failing scores should never read as Audit-ready. When review is recommended, treat the run as Needs review.

What to do next

  1. Open the failing case in History
  2. Read evidence for / against
  3. Optionally send to Workbench for SME judgment
  4. Feed insights back into Generation dimensions or suite coverage

Rubrics and evidence

Criteria, built-in vs custom rubrics, and evidence fields on every score.

History

Browse past assurance runs — scores, evidence, filters, and detail views.

On this page

Score typesWhat to do next