Skip to content

Interoperability

Agent Evidence is a bridge, not a replacement for existing standards.

Standard or systemRelationship
Agent RuntimeRuntime produces execution facts; evidence packages trust, review, replay, and audit facts.
Agent UIUI displays evidence; evidence owns portable review/read models.
Agent KnowledgeKnowledge provides source-grounded material; evidence records selected, omitted, stale, and contradicted source refs.
Agent ArtifactArtifact systems own bytes, versions, previews, and diffs; evidence links artifact refs and reviews.
A2APeer tasks, messages, and artifacts can be cited; evidence preserves native peer ids and remote refs.
MCPTool calls and resources can become source/provenance refs; evidence does not define tool schemas.
OpenTelemetryTraces, spans, logs, metrics, and GenAI operation names are referenced for correlation.
CloudEventsEvent envelopes can carry evidence events.
W3C PROVEntity/activity/agent pattern informs provenance chains.
W3C Web AnnotationSelectors and targets inform claim/source anchoring.
in-toto / SLSAAttestation and provenance patterns inform signed export and build-style evidence.
OpenLineageRun/job/dataset facets inform data lineage interoperability.
CycloneDXAttestations, claims, evidence, counter-evidence, declarations, and confidence inform audit packaging.

Interoperability means preserving native ids and semantics while adding evidence-specific relationships. Agent Evidence should not flatten every upstream concept into generic text.

Draft standard for portable agent evidence, provenance, review, and replay.