Human-in-the-Loop¶
Configure human agent handoff to seamlessly transfer conversations from AI to human agents and back.
Overview¶
The Human-in-the-Loop workflow allows AI agents to escalate conversations to human agents when needed. This is powered by the Human Agent tool, which handles queue management, agent assignment, timeout behavior, and end-of-session feedback.
Refreshed Human Agent UI (1.0.34)
The Human Agent screen inherits the refreshed chat UI — sleeker layout, language-model picker and attach-file inline in the message input, and prompt shortcuts in a more compact arrangement.
Human Agent console showing the refreshed conversation layout — My Active / Queued for Human / AI Active panels with the streamlined message input
Quick Setup¶
- Create a Human Agent tool under Settings > Processors > Tools (see Tools > Human Agent)
- Assign the tool to your agent under Agent Settings > Tools
- Set the tool description to instruct the LLM when to trigger handoff
Key Features¶
Transfer and Queue Management¶
| Setting | Description |
|---|---|
| Maximum Queue Time | Max duration a transfer request stays in the queue before returning to AI |
| Agent Console Notification Idle Timeout | Max idle time after a human agent receives a notification. Set to 0 to disable |
| Mid-Conversation Agent Idle Timeout | Max inactivity during active conversation before returning to AI |
| Agent No Response Message | Message shown when idle timeout is exceeded |
Human Agent Identity¶
End users see the name of the human agent who joins. Admins can configure a custom transfer message with {{human_agent_name}} placeholder.
Chat Rating¶
After a human-agent session ends, users can rate their experience on a 5-star scale with optional feedback. Ratings and feedback are available in Conversation Monitoring and agent reports.
Notification Sound¶
Select from multiple notification sound options to alert human agents of incoming transfers.
Monitoring¶
- Conversation Monitoring — view human agent ratings, feedback, and session details
- Agent Reports — metrics for Unpicked Conversations, Picked Conversations, and Requests for Human Agents
- Email Notifications — configure alerts for flagged conversations and message dislikes in Agent Behavior settings
Related Topics¶
- Tools > Human Agent — Full tool configuration reference
- Agent Builder — Advanced — Behavior and notification settings
- Templates — Customize notification email templates
- Back to All Guides