Skip to Content
AI AgentsReliability & Failover

Reliability & Failover

Production agents fail in interesting ways: a model provider has an incident, a tool times out, a voice provider cuts out. Reliability settings let you stay graceful when that happens instead of dropping the customer.

The failure modes Omniflow handles

FailureWhat Omniflow does by default
Primary model returns 5xxRetries with exponential backoff (3 attempts, capped at 4s total).
Primary model times outFalls back to the configured fallback model.
Tool call returns 5xxRetries once, then surfaces the error to the model.
Tool call times outReturns a structured timeout error to the model.
Voice provider drops audioReconnects or transfers to a fallback provider mid-call.
All providers failTriggers transfer_to_human and plays the configured failure greeting.

Configure failover

Open Agents → [your agent] → Reliability.

Model fallback chain

SlotExample
PrimaryGPT-4o Realtime
Fallback 1Gemini Live
Fallback 2Cascaded (GPT-4o + Azure TTS)

Omniflow walks the chain top-down on each failure. If the conversation has already produced 3+ turns, it sticks with the current model where possible — switching mid-call hurts coherence.

Retry policy

SettingDefaultNotes
Model retries3Exponential backoff up to 4s total.
Tool retries1Most tools should idempotent retry; mutating tools should not.
Voice reconnects2Beyond this, transfer or end the call.

Failure greeting

A short message played if everything fails. Keep it human:

“I’m having trouble on my end — let me transfer you to a teammate who can help.”

Don’t make the failure greeting say “the system is down”. Customers don’t care about your stack — they want a path forward. Always pair the message with an actual transfer or callback.

Health monitoring

The Health tab shows real-time status for every provider:

  • Provider uptime over the last 24 hours.
  • Mean time to first token.
  • Tool error rate.
  • Failover trigger count.

Subscribe to a Slack channel for sustained-failure alerts via notifications.

Test failover

You can simulate failures from the test sandbox: pick a fault to inject (primary_model_503, tool_timeout, voice_disconnect) and watch the agent behave. This is the only safe way to validate the failure greeting and transfer path.

Open in Omniflow

If you want to…Go to
Pick voice providersVoice Models
Set up alertingNotifications
Read the runtime architectureVoice Runtime