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

Assure

Deterministic, evidence-backed scoring against built-in or custom rubrics.

Assurance scores a normalized trace against a Criterion (rubric). The reasoning model produces critical analysis; a separate reward head emits a deterministic 0.00–1.00 score with evidence. The reasoning LLM does not emit the score itself.

Guides

  • Evaluate API
  • Rubrics and evidence
  • Reading scores

Fetch tracing

Pull traces from observability backends and normalize them for assure.

Evaluate API

Call the Gateway assure endpoints and QAVE Studio eval-only workflows.

On this page

Guides