Skip to main content
When a chat agent is handling a conversation, the AI can stop responding — either because a teammate stepped in, or because something about the conversation calls for a person.

​
When a teammate replies, the AI stops

The moment anyone on your team sends a message in a conversation from Unibox, the AI goes quiet on that conversation. This is automatic on every channel and there is nothing to configure — a human reply means a human owns the conversation. The AI does not come back on that conversation by itself, and it stays out of it however long the conversation runs — closing the conversation does not change that, and neither does the contact writing in again days later. A human reply means a human owns the conversation until someone says otherwise. When you want the AI to take over again, open the ⋯ menu in the thread header and choose Let the AI reply again. The AI answers the contact’s next message as normal. It applies from that moment on, not retroactively, so nothing you or the AI has already sent changes. If a teammate replies again afterwards, the AI goes quiet again — you do not have to undo anything first, and handing a conversation back once does not opt it out of this permanently.

​
Pause reasons

The AI also stops on its own in a few situations. Whatever the cause, the conversation shows a paused band with the reason: Where you see it:
  • A band at the top of the conversation, just under the header, reading AI paused and the reason. It is shown on open and snoozed conversations; a resolved conversation does not show it.
  • A row in the conversation timeline marking the moment the AI stopped — and, if someone has handed the conversation back, a row for that too.

​
Turning the AI back on

It depends on who stopped it, and the difference matters: When the AI stopped itself — a keyword, an escalation, a booking, a message limit, profanity, a procedure — resolving the conversation is the way back. Resolve it with the Resolve button in the thread header, and the contact’s next message is answered by the AI as normal. When a teammate replied, resolving is not enough, because the AI is staying out of a conversation a colleague is handling rather than reacting to something the contact did. Use Let the AI reply again in the ⋯ menu. That option shows on an open conversation that is currently showing the teammate-reply pause. On a conversation you have already resolved it is not there — nothing is waiting to be answered yet — and it comes back as soon as the contact writes in again. Resolving is never the way back from a teammate’s reply, so if the conversation is resolved and you want the AI to handle the contact’s next message, wait for that message and then use the menu option.
There is no Unpause AI switch, and Let the AI reply again is not one. It is a one-off instruction for a single conversation, not a setting, and there is nothing to switch back — the next teammate reply silences the AI again on its own.
Two exceptions clear themselves. A Low balance pause lifts as soon as the wallet is topped up, and a Usage limit pause lifts when the limit resets or is raised. Both are workspace-wide billing states rather than a decision about that conversation, so no one has to reopen anything. Escalations are final. When a conversation escalates, the AI leaves it and does not come back on its own — not after a follow-up message, and not if the escalation would otherwise trigger again. The contact can keep writing; the AI stays silent and the thread waits for a person. Resolving the conversation is what hands it back. If the same conversation escalates a second time later, the AI stops again, but your team is only notified once, so a reopened thread cannot spam anyone. Contact opted out is different. Resolving the conversation does not lift an opt-out. SMS opt-outs block every outbound path to that contact — including the AI — until the contact replies START, UNSTOP, or YES, or someone manually re-opts them in from the contact panel. Resolving just closes this conversation; the AI still won’t message that contact again until the opt-out itself clears.

​
Configuring pause behavior

Some pause reasons are configured per agent, in the agent’s Settings tab:
  • Protection keywords that trigger a pause
  • Profanity detection
  • Message limits
  • Whether to pause after a completed booking
Two pauses are not configurable. Pausing after a teammate’s reply always happens, on every channel. Pausing after an escalation always happens too: once a conversation has been escalated, the AI is out of it until the conversation is resolved, with no per-agent setting to turn that off. See Chat Agents for full configuration details.