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 afterwards. When you are finished, resolve the conversation with the Resolve button in the thread header. The contact’s next message starts fresh and the AI answers it as normal.

​
Pause reasons

The AI also stops on its own in a few situations. Whatever the cause, the conversation shows a paused label with the reason: Where you see it:
  • A Paused chip next to the conversation’s status in the thread header, with the full reason on hover.
  • A row in the conversation timeline marking the moment the AI stopped.

​
Turning the AI back on

For any pause caused by the conversation itself — a teammate’s reply, a keyword, an escalation, a booking, a limit, profanity, a procedure — resolving the conversation is the way back, and deliberately the only one: a paused conversation is one a person is dealing with, so it stays with that person until they close it out. Resolving clears the pause, so the contact’s next message is answered by the AI as normal — whether that message reopens this conversation or starts a new one.
There is no Unpause AI action. A conversation handed to a human is not handed back mid-thread.
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, with no exceptions and no per-agent setting to turn that off. See Chat Agents for full configuration details.