Settingsbeginner

Configuring "AI Picks the Team" for Voice Handover

The voice handover Team dropdown now offers "AI picks the team," letting the model choose both the team and queue for a call transfer from team descriptions instead of a fixed assignment. Covers enabling it, why descriptions are required, how it differs from a fixed team/queue, and its fallback behavior.

5 min read

Configuring “AI Picks the Team” for Voice Handover

Voice handover used to mean picking one team and, optionally, one queue in advance — every call that needed a human went to that same destination, no matter what the caller actually needed. AI picks the team replaces that fixed assignment with a model decision: when a voice call needs to hand over to a person, the model looks at every team’s description and picks the team and the queue in a single choice, instead of a person having pre-decided it for every call ahead of time.

This is a per-stack setting on the voice handover configuration, stored as voiceHandoverAiTeam on the agent stack. It sits alongside — and overrides, for voice — the existing handoverTeamId used by fixed team assignment.

Where to enable it

  1. Open the agent stack’s Voice settings and find the Handover card.
  2. Open the Team dropdown. Alongside your tenant’s actual teams, you’ll see an AI picks the team option.
  3. Select it and save.

Selecting AI picks the team doesn’t touch handoverTeamId — that field is shared with the text-handover configuration and is left exactly as it was. The AI-picks flag simply takes priority over it for voice calls; if you later switch the dropdown back to a specific team, that fixed choice is what applies again.

Why every team needs a description

The model isn’t guessing from team names alone. Each team is offered to the model as an option carrying two things: its name and its description. A team with no description is effectively invisible to this feature — the model has nothing to judge whether it’s the right destination, so it won’t be considered as a candidate.

That’s why saving the voice handover with AI picks the team selected checks that at least one team actually has a description, and warns you if none do. Before this reaches the model, team names and descriptions are run through the same sanitization used for text handover’s by-description routing, so a team description can’t be used to smuggle instructions into the routing prompt.

Practically, this means the quality of your team descriptions is the configuration. A one-line “Handles refund requests and chargebacks” gives the model something to route on; a blank field or a name alone does not.

How this differs from a fixed team or a fixed queue

  • Fixed team (a specific team selected in the dropdown) — Whoever configured the stack — Ahead of time, for every call
  • Fixed queue (a specific queue selected alongside the team) — Whoever configured the stack — Ahead of time, for every call
  • AI picks the team — The model, from each team’s name and description — At the moment of handover, per call

With a fixed team, every handover from this stack lands on that one team regardless of what the call was about. With AI picks the team, the model reads the caller’s situation and the available teams’ descriptions and picks both the team and its queue together, as a single decision — it isn’t choosing a team and then falling back to that team’s default queue separately.

Fallback behavior: a fixed queue still wins

If a fixed queue is also configured on the stack, that queue takes priority over the AI’s pick — a fixed queue still wins even when AI picks the team is selected for the team itself. Set a fixed queue only if you specifically want every AI-routed handover to land in that one queue regardless of which team the model chose; otherwise leave the queue unset so the model’s per-team queue choice is what’s actually used.

Handovers where nothing could be routed (for example, a no-input situation with no team decision available) go through without a queue id attached, and are picked up by whatever fallback behavior applies at the transfer bridge — they aren’t silently dropped, but they also aren’t guaranteed to land in a specific queue.

Relationship to text handover’s “by description” routing

If you’ve already configured text handover to route by description, this will feel familiar: it’s the same underlying idea — let the model choose a destination from team descriptions instead of a fixed assignment — applied to voice. The two settings are independent of each other and scoped to their own channel: turning on AI picks the team for voice does not change how text handover routes, and vice versa. What they share is the same team descriptions and the same sanitization step, so a description you write with text handover’s by-description routing in mind will also be usable, unchanged, by the voice version of this feature.

Tags

Ai FeaturesHow To