Skip to main content
The counterpart to knowledge search: one finds an answer, this one admits there isn’t one. Without it the agent’s only options are to guess or to apologise into the void, and you never learn it happened.

​
The two triggers

Each switchable, per agent. Turning one off removes the capability, rather than asking the model to refrain. A model that has a tool will eventually use it; a model without one cannot.
A business with nobody watching the inbox should turn escalation off entirely. An escalation nobody answers is worse than a straight “I don’t know”, because the customer waits for something that is not coming.

​
What happens when it fires

1

The conversation is flagged

Status changes to escalated and it surfaces in the inbox.
2

A note is written for whoever picks it up

One sentence on what the customer wants and what the agent could not find — written for a colleague, not for a log.
3

Your integrations fire

Outbound webhooks are delivered, and if you have connected one, a helpdesk ticket opens in Zendesk or Salesforce with the transcript.
4

The customer is told

The agent says a person will follow up. It does not go quiet.

​
On a phone call: putting the caller through

With Call transfer chosen in Hand over to a person, a caller on the phone is also put through to the number you give. Choose how:
  • Cold (the default) — the phone rings and the caller is connected as soon as someone answers.
  • Warm — whoever answers first hears a short spoken summary of who is calling and what they need, then the caller is connected. The caller hears the phone ringing meanwhile. Add Press 1 to accept and the caller is connected only once that person presses 1, so a voicemail never takes the call; choose Connect after the summary to connect as soon as it has played.
Press 1 to accept is not available on Telnyx numbers yet. The details are on Voice.

​
Escalation from a failed action

The case worth planning for. When a custom action times out, returns a 500, or cannot be reached, the agent is told the lookup failed. It does not invent an answer and it does not pretend the tool succeeded. What it does next depends on whether escalation is available:
Switch escalation on wherever you have custom actions. The failure mode of “I could not check that” is far better when there is somebody to pass it to — and your API will be down at some point, whatever your uptime target says.
The same applies when a customer hits the per-conversation action limit: the agent stops calling and hands over rather than continuing without the information.

​
Once a person takes over

The agent stops replying to that thread entirely. Two voices answering the same customer, contradicting each other, is worse than a slower answer. When a teammate replies, the agent later reads that reply as its own prior turn — so if the conversation returns to it, it does not re-answer something a person just handled.

​
It escalates once

The agent is told to call it once per conversation. Calling it again does not make anybody arrive sooner, and a thread that escalates four times is four notifications about one problem.

​
If flagging fails

If the escalation cannot be recorded for some reason, the agent still tells the customer a person will follow up — because the conversation is in the inbox either way, and promising nothing is worse than promising something you will honour by reading it.

Inbox

Where escalations land, and how taking over works.

Helpdesk

Escalations as Zendesk or Salesforce tickets, with replies routed back.

Custom API

The actions whose failures escalation catches.

Analytics

“Needed a person” over time — not a failure metric, a working one.