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
Assurance SDK

Assurance SDK

The unifying runtime for execution, trace normalization, and assure calls.

The Assurance SDK is the connective runtime of Q: ingest suite metadata, drive the SUT (when configured), normalize traces, and call deterministic assurance.

Chapters

PageUse when
OverviewHow the SDK fits the loop today
QAVE Studio suite fetch APIProject SDK keys + /sdk list/fetch
Agent + JSONLAgent / JSONL execution paths
Langfuse bridgePulling traces from Langfuse

A single SDK call that both drives your bot and scores the run is listed under Coming soon.

Why an SDK (not only an API)

The same SDK contract works from Studio and from your own CI or in-VPC runtime against the Assurance Gateway.

Export formats (detail)

Export formats (detail)

SDK overview

Packages, responsibilities, and the honest boundary between eval-only and SUT drive.

On this page

ChaptersWhy an SDK (not only an API)