Dashboard API

Evidence grounding confidence audit — read-only dossier-safe evidence status

Read-only confidence audit for grounded Cernion answers. It keeps Capability Broker routing confidence separate from evidence confidence, exposes source classes, scope limitations, tool failures, missing evidence and positive follow-ups. It does not create HITL items, interface placeholders, RAG ingests, Personal-Agent sessions or external calls.

get/api/dashboard-api/evidence-grounding-confidence-audit

Request

  • Base URL: https://api.cernion.de
  • URL: https://api.cernion.de/api/dashboard-api/evidence-grounding-confidence-audit
  • Auth: none declared

Query parameters

requestIdstring
sessionIdstring
domainstring
capabilityIdstring
sourceActionstring
scopeIdstring
gridOperatorIdstring
datasourceIdstring
datapointIdstring
querystring
networkOperatorConfirmedboolean
includeFederatedKnowledgeboolean

Opt-in only (default false). When true, additionally probes knowledge-rag.federatedSearch health/availability alongside knowledge-rag.query.

tokenstring

Optional Cernion MCP token as URL query parameter. If provided, it overrides CERNION_TOKEN for this request. Prefer Authorization Bearer header in production to reduce token exposure in URLs/logs.

Response

Read-only evidence-grounding confidence audit

auditIdstring
requestContextobject
routingConfidenceobject
evidenceConfidenceobject
answerStatusstring
sourceClassBreakdownobject
requiresNetworkOperatorConfirmationboolean
sourceActionsobject
dossierEvidenceobject
timestampstring date-time
_errorsstring[]

Changes

No recorded changes to this operation across all 2 revisions of this API.