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
Concepts

Lifecycle

The assurance loop from simulation suite to scored history and golden data.

QAVE Studio connects one assurance loop. Most teams live in stages 1–7 every day:

#StageWhere in Studio
1Build a simulation suiteGenerate
2Exercise your AI systemExecute / SDK
3Capture tracesTracing
4Normalize traces for scoringFetch tracing
5Score with evidenceAssure
6Browse past runsHistory
7Capture SME judgmentWorkbench

Flow: Generate → Execute → Trace → Fetch → Assure → History → Workbench.

Alongside the loop, use Coverage to see whether your suite covers the test space, and Error analysis to turn failed conversations into reusable failure modes.

Items still in progress (for example a single SDK call that drives and scores in one step) are listed under Coming soon.

Concepts

Shared vocabulary and mental models for the QAVE Studio assurance lifecycle.

Glossary

Map friendly QAVE Studio terms to API and package names.