Skip to main content

What Is a Trace?

A trace is a single AI interaction captured within a session. Every request sent to an AI service, every response received, and every related event creates a trace. Traces are the raw material agents review. Each one records what happened, where it came from, and what the outcome was.

Trace Directions

Every trace has a direction that describes the type of interaction.

Viewing a Trace

Within a session, select any trace to see its full details.
  • Direction and source show the type of interaction and which service was involved.
  • Assessments show what each agent found and the verdict it reached.
  • Outcome shows whether the trace was allowed, flagged, or blocked.
  • Escalations show which channels were notified, when applicable.

What Happens After Capture

Agents review it

Your active agents review the trace, each recording its own assessment.

The outcome is resolved

Based on the security agents’ findings and their roles, the trace is allowed, flagged, or blocked. The most restrictive outcome wins. High-criticality findings also notify your channels.

It is logged

The trace reaches its final state and is recorded. Escalations are sent to your connected channels.
For the full picture, see Trace lifecycle.

Sessions

How traces are grouped into sessions.

Trace lifecycle

Follow a trace from capture to final state.