Agent Stacksadvanced

Orchestrator States Reference

The state machine the orchestrator runs over every conversation in a stack — the states, the transitions, and what triggers each one.

May 10, 2026

Orchestrator States Reference

Every conversation handled by an Agent Stack moves through a state machine controlled by the orchestrator. The state determines what happens next — whether the specialist replies, whether re-routing kicks in, whether handover triggers.

You can’t directly edit these states. They’re driven by what’s happening in the conversation. Knowing them helps you understand what the orchestrator is doing and why.

The states

  • triaged — A new message arrived. The router is about to pick a specialist
  • active_specialist — A specialist has been assigned and is handling the conversation
  • stalled — The conversation has stopped progressing — repeated turns without resolution
  • re_triage — The orchestrator decided the wrong specialist was picked; routing again
  • risk — Sentiment-and-risk infrastructure agent flagged the conversation as risky
  • handover_pending — Handover has been triggered; prerequisites are being collected
  • human_active — A human has picked up; AI is no longer replying
  • resolved — The conversation is done — by the AI or by a human

Transitions

  • (start)triaged — New customer message arrives
  • triagedactive_specialist — Router picks a specialist successfully
  • active_specialiststalled — Stall threshold hit — too many turns without progress
  • active_specialistresolved — Specialist marks the issue resolved
  • active_specialistrisk — Sentiment / risk detection fires
  • stalledre_triage — Orchestrator decides a different specialist would help
  • stalledrisk — Stall persists past the escalation threshold
  • re_triageactive_specialist — New specialist assigned
  • riskhandover_pending — Handover triggered; collecting prerequisites
  • handover_pendinghuman_active — Prerequisites complete, conversation queued to a human
  • human_activeresolved — Human resolves and marks Done

What you can tune

  • Stall threshold — how many unprogressed turns before active_specialist becomes stalled. Lower = more aggressive intervention. Higher = the AI gets more chances.
  • Risk auto-escalation — when the sentiment-and-risk agent flags a conversation as risky, transition to risk automatically. Default on.
  • Check interval — how often the orchestrator evaluates state. Shorter = faster intervention, more compute. Longer = cheaper, slower to react.

These settings live on the orchestrator config and inherit from tenant or global defaults if you haven’t customized per stack.

What’s the same as conversation status

Don’t conflate orchestrator state with the conversation status. The conversation status is the inbox lifecycle (Active / Snoozed / Done / Archived) — visible to your team in the conversation list. The orchestrator state is the AI-internal state of an in-progress conversation. A conversation with orchestrator state human_active will typically have a conversation status of Active in the inbox.

See also

Tags

ReferenceAi Features

See Atender in action

Book a personalized demo and see how AI-powered customer service with expert humans can transform your support operation.