Browse this section
Enterprise Agents

Run traces

Every step, source, tool call and decision — recorded and searchable.

Every run produces a trace: an ordered record of everything the agent did.

What's in a trace

Step typeRecorded
triggerTrigger type and input
retrievalQuery, knowledge bases, passages retrieved with scores and permissions applied
reasoningThe agent's intermediate plan and conclusions (summarised)
tool_callTool, parameters, scope, response, duration; simulated flag in test mode
approvalPolicy triggered, approvers notified, decision, decider, timestamp
handoffRecipient and case summary
resultFinal status and output

Viewing

Agents → (agent) → Runs → (run) or GET /runs/{id} and GET /runs/{id}/trace. Traces are searchable by input fields, tool, status and time.

Retention

Default 90 days; configurable from 30 days to 7 years per workspace. Traces can be exported continuously to S3-compatible storage or your SIEM.

Privacy

Traces contain the data the agent processed. Access to traces follows workspace roles; admins can restrict trace access per agent to a group (for example, finance traces to finance).