Problem
So far, once x10 was paused for a conversation, either by an agent stepping in or by x10 pausing itself, it almost never comes back on. Someone would have to manually re-enable it, and in practice that rarely happens. So conversations that x10 could be handling just sit paused.
What it does now
- An agent reply is the trigger.When an agent sends a message into a conversation where x10 is paused, that message kicks off a check to see whether x10 can safely come back on. There's no background scanning; the agent's reply is what starts it.
- Works no matter where the agent replies from.The trigger fires whether the message is sent directly through Tailwind or from an external platform (e.g. Hostaway); either way, x10 sees it and runs the check.
- Only resumes when the conversation is genuinely clear.After that trigger, x10 turns back on only if all of these hold:
◦ Automation is enabled at the property and company level.
◦ There's no pending escalation.
◦ There's no open task tied to the conversation.
- Stays out of the way on active work.If there's a live escalation or a pending task, x10 leaves it alone and won't try to answer follow-ups related to that thread. Humans keep the lead where it matters.
Why it matters
Paused conversations were quietly dragging down our automation rate, not because x10 couldn't help, but because nobody flipped it back on. Now x10 self-corrects: it picks conversations back up the moment it's safe to, so guests get answered faster and the onus is no longer on the agents to turn x10 on/off on a conversation. We expect this will result in a higher automation rate, more automated responses and decrease the load on agents