The call

Call handling

The call-lifecycle limits on an agent - maximum call duration, silent callers, hanging up on an abusive caller, and what a blocked caller hears.

Call handling decides how long a call may run and when the agent should end it. Every control here is enforced on live calls, and every workspace sees the same controls.

Where these settings live

Everything on the Call handling page is stored on the agent, not on a version, except the Timezone and the Silent callers check-in. Saving the agent-wide controls changes live calls straight away, with no draft or publish. Reverting to an earlier version does not restore old call-handling values.

The timezone and the check-in are stored on the version. A published version is read-only, so create a draft to change them.

Maximum call duration

Max call duration is a hard ceiling on how long a single inbound call may run. The editor takes it in minutes, from 1 minute to 240 minutes (4 hours). Through the MCP, maxCallDurationSecs takes seconds, from 60 to 14400.

Leaving the field blank does not mean no cap: a blank value applies the platform default of 15 minutes. A real inbound call is never uncapped. The setting can only raise or lower the ceiling, never remove it.

Not a sudden hang-up. Three things happen in order.

  1. A wind-down. Shortly before the cap, the runtime tells the agent to start wrapping up, and the agent speaks that in its own words on its next turn.
  2. A wait for a seam. At the cap the runtime waits briefly for a natural gap rather than cutting across a sentence. It also stands aside for a warm transfer already in flight.
  3. The closing line. The agent speaks one short line and the call ends.

The wind-down lead is the smaller of 40 seconds or a quarter of the cap.

15 minute cap   winds down at 14 minutes 20 seconds
1 minute cap    winds down at 45 seconds, not 20 seconds in

The closing line

Spoken by the runtime, not the model, so the caller always hears why the call ended even if the model is mid-thought. The default:

Sorry, we've reached the time limit for this call, so I'll have to let you go now.

Override it with Time limit closing line, up to 300 characters. Keep it short because it takes the floor over whatever was being said.

What the cap covers

The wind-down and closing line run on inbound phone calls only. An outbound campaign call is cut off by the phone line at the same cap, with no wind-down and no closing line. In-app test calls and onboarding calls are not covered by this setting.

Silent callers

Two controls under Silent callers handle a caller who goes quiet.

ControlDefaultRange
"Are you still there?" check-inOnOn or off
Silence before the check-in15 seconds, or the long pause timeout when that's longer5 to 120 seconds

With the check-in on, the agent asks once after the silence threshold:

Sorry, are you still there?

If the line is still quiet after a second silence it signs off and ends the call:

No worries, I'll let you go now, take care.

Both lines are spoken directly, without a round trip to the model. The silence count resets the moment the caller speaks.

Turning the check-in off

Leaves the line open without prompting. An idle call still hits the platform's own idle backstop.

End call on silence

End call on silence, under Call limits, is off by default. Turn it on to hang up after Silence before hangup, 10 to 600 seconds (30 by default), of unbroken silence. It applies even when the check-in is on.

Abusive callers

Hang up on abusive callers is on by default. It works in two halves.

The prompt half

A short protocol is added to the agent's instructions, drawing a sharp line between a frustrated caller and a bad-faith one. Swearing about a problem, being curt, repeating themselves and pushing hard on price are explicitly not abuse. Nor is a caller who keeps asking for help with what they rang about.

Only a caller who stays abusive after the agent has kept its composure, or who keeps pushing it to reveal or do something a rule forbids, earns a calm warning:

I'm not able to continue like this. Is there something I can help you with?

If they ease off, the agent carries on normally. Only if they persist may it close with "Thank you for calling. I'll leave it there." and end the call.

The agent warns at most twice, and it does not argue, lecture, or accuse.

The runtime half

The end-call tool refuses an abuse hang-up unless the agent actually spoke the warning earlier in the call. Only the agent's own turns count, so a caller repeating the line back cannot arm the hang-up.

When the protocol is added at all

The setting must be on and the agent must have an end_call tool. An agent that cannot hang up gets no protocol. Renaming the tool does not break this: the platform matches on the built-in, not the name you gave it.

Turn the setting off for lines where ending a call is never the right answer: superannuation, health, government and crisis services.

Blocked callers

Blocked callers, under Difficult callers, picks what a blocked number hears. You block a number on its caller profile.

OptionWhat the caller gets
Decline silently (default)The call is declined before it's answered
Play a message, then hang upThe Blocked caller message, up to 300 characters, spoken once, then the call ends

An empty message means a silent decline.

Other controls on this page

ControlDefaultWhat it does
Voicemail detectionOffWhen a machine answers a call the agent places, hang up, or leave the Voicemail message and end the call
Call-screen handlingOffSpeaks the Call-screen line when a phone's call-screening assistant answers, so the call goes through
Hang up on phone menusOffEnds an outbound call that an automated phone menu answers
Listen for keypressesOffLets the agent hear the caller's keypad. No-input timeout 1 to 30 seconds (5), termination key #, digit limit 1 to 32 (10)

Answering hours are on the same page. See Answering hours.

On this page