Skip to main content

​
Live conversation monitor

The Live tab is the dashboard surface for supervising AI-agent conversations while they are still running. Instead of polling the API, you open one page and see every conversation the agent is holding right now — voice calls and chat threads (web chat, SMS, WhatsApp, and the other messaging channels) — and can click into any of them to watch the transcript and send the agent a note. Access is limited to the owner, admin, and supervisor roles, because the surface shows live customer conversation content.

​
Open the Live tab

  1. Open Agents in the dashboard.
  2. Select the Live tab.
The page polls every 5 seconds and shows each live conversation as a row: the agent, the channel, the contact, the last message, the turn count, and how long it has been active. Conversations appear here while they have activity in the last few minutes; once one goes quiet it drops off the list, and the list starts page-sized with a Load more control when the contact center is busy. A direct visit to /agents/live redirects to Agents → Live — the tab is the canonical surface.

​
Work a single conversation

Select any row (or its View button) to open the per-conversation detail at /agents/live/[conversationId]. The detail page polls every 2 seconds and auto-scrolls to the newest message. The header shows the agent name, the channel, a status badge, and the conversation id; a Pending approvals strip appears above the transcript whenever the agent has paused on a sensitive tool call and is waiting for a human decision — resolve those from the same page.

​
Reading the transcript

Every message carries a role badge so you can tell speakers apart at a glance:
  • Agent — a reply the AI generated.
  • User — what the customer said.
  • Tool — an action the agent executed (the tool name is shown with it), rendered in a monospace block so call details are easy to scan.
  • System — internal context messages, shown dimmed.

​
Send a note to the agent from the page

The panel under the transcript is a whisper: a one-way note from you to the agent, applied on its next turn. The customer never sees it.
  1. Type the note (1–1000 characters; the counter shows your position).
  2. Send it with the button or Ctrl+Enter — set the shortcut in muscle memory and you can steer mid-turn.
Below the input, the last five notes are listed with a pending or read badge — a note is pending until the agent picks it up on a later turn, then read. If the conversation ends before the agent takes another turn, a pending note is never applied, so whisper while the conversation is still running.

​
Which conversations count as live — and where 404s come from

The list treats a conversation as live when its status is active or open (a voice call in progress counts too) and it saw activity within the last few minutes. The note endpoint is broader — it accepts active, open, and escalated, so you can still whisper to an agent on a conversation that has been handed to a human. What the statuses mean in practice:
  • active / open — the agent is answering.
  • escalated — a human has the conversation; the agent stops replying until control is handed back.
Once a conversation closes, its id stops resolving on the write path: sending a note to it returns 404, exactly as the API does. The detail page renders that as a “Conversation not found — it may have ended” state instead of a retry loop, so a supervisor watching a conversation as it ends gets a clean explanation rather than an error flash.

​
How this page complements the API guide

The Human-in-the-loop oversight page documents the same actions from the API side — supervisor notes, tool approvals, hand-off — with request/response examples you can script. The Live tab is the day-to-day workstation for the same operations: open it during staffed hours, and fall back to the API only when you are wiring oversight into your own tooling.

​
See also