Why it matters
Live trace improves diagnosis, governance and user confidence.
Architecture position
Expose stage, evidence source, tool call, policy decision, latency and failure state without leaking secrets.
Under research
Agent execution traceability
Users cannot trust an agent when they cannot see what it is doing, waiting for or failing on.
Evidence or hypothesis
Recurring need observed in agent workflow and telemetry design.
Related publication
Governed AI operating layer
Related product
CapAI Agent Hub
Next intended output
Define a vendor-neutral trace schema.