Skip to content

When the agent hands over to a human

Escalating a conversation to your team.

A conversation always carries one of three states: "Unresolved", "Needs human", "Resolved". The AI agent only answers in the first. Moving to the second is what escalating means: the conversation is waiting for a person, and the agent falls silent.

The four ways a conversation gets escalated

  • The agent decides. It has a tool for it, and uses it when it cannot help or when the visitor asks for a person. It first writes the visitor a message explaining the handover, then changes the state.
  • You decide. The state button at the top of the conversation cycles through the three states on each click: "Unresolved" → "Needs human" → "Resolved" → "Unresolved".
  • You answer. Your first message in an "Unresolved" conversation moves it to "Needs human", and assigns it to you if nobody had taken it yet. So there is nothing to click in order to take over: writing is enough.
  • The conversation runs too long. Past 40 visitor messages in one conversation it is escalated automatically — an exchange that long is no longer going anywhere on its own.

What the agent’s escalation sets off

  • A message to the visitor, written for their case, before the state changes.
  • An internal note explaining the reason, if "Internal notes writing" is on in the AI configuration. Only your team sees it.
  • The tags it suggests, if they already exist among yours: the ones it invents are ignored, never created.
  • An email to every team member who asked for one.

That email goes to nobody by default. Each member turns it on for themselves under Configuration → Notifications: "Email Notifications" first, then "Conversation Escalation". Without that, the escalation still happens, but it waits for someone to open the inbox.

Why the agent did not answer

Four conditions have to hold for it to answer. The first one missing explains the silence:

  • The conversation is "Unresolved". Escalated or resolved, the agent writes no more — and that is deliberate: it does not talk over the person who took the conversation back.
  • The plan includes the AI agent. The free plan has none: every conversation there waits for a person. An unpaid invoice past its grace period returns the organization to the free plan, so the agent goes quiet then too.
  • The "Enable AI" switch is on, under AI Configuration.
  • The monthly quota of agent messages is not spent. Once it is, the visitor’s message is still recorded — it is never lost — but no automatic reply goes out until the next month.

What bounds the agent

  • It re-reads the last 12 messages of the conversation, not the whole of it.
  • It chains at most 5 actions per message received — a search, a tag, an escalation each count as one.
  • Its answer is capped at 800 tokens: it answers short, and hands over rather than holding forth.