conversation_id or session_id.
Agnost AI groups those events into one timeline so you can review the user’s goal,
the agent’s responses, tool activity, and outcome together.
Open a conversation
- Open Users in the Agnost AI sidebar.
- Apply the workspace, time-range, and metadata filters you need.
- Select a row to inspect its messages, spans, errors, and available audio.
Users groups stable user identities and their conversations. “Conversation”
remains the canonical data term for one related interaction timeline.
Conversation identity
Reuse one stable conversation identifier across every turn that belongs together. The integration path determines the field name:
Starting a new identifier on every turn fragments the timeline. Reusing one
identifier across unrelated users combines data that should remain separate.
What to inspect
- Whether the user’s goal was resolved.
- Repeated questions, corrections, and abandoned flows.
- Failed or unexpectedly slow tool calls.
- The intent and violation evidence attached to the conversation.
- Agent-version, plan, surface, or cohort metadata that explains the outcome.
Next steps
- Events: inspect the records behind a conversation.
- Intents: group conversations by what users wanted.
- Violations: find where expected behavior was not followed.