Single prompt agents

Create the agent

On the Agents screen, click Add Agent, choose Single Prompt, and enter a name and voice.

Write the prompt and welcome message

Describe the persona, goal and rules. See Writing a good prompt.

Test in the simulator

Call the agent from the browser panel and read the live transcript.

Deploy

Click Deploy to make the current version live on your phone numbers.

What you configure

Setting	What it does
Prompt	Instructions that govern the whole call. You can reference variables as `[var_name]`.
Welcome Message	If set, the agent says it word for word when it answers, then waits for the caller. If empty, the agent writes its own opening from the prompt, so each call may start a little differently.
Voice	The agent’s voice. Some voices also let you adjust speaking speed from 0.7x to 1.3x.
Agent can end call	When on, you set an End call transition (when to hang up, for example “The caller asks to end the call”) and an End call announcement (the closing line the agent says before hanging up).
Knowledge bases	Attach business information the agent can answer from. See Knowledge base.
Vars provided	Values injected before the call starts, such as a customer name passed in when you place an outbound call. Each can have a default.
Vars extracted	Details pulled from the transcript after the call ends, such as the reason for calling. Shown on the call page and sent in webhooks.
Email summaries	Addresses that receive a summary after each call.
Webhooks	Up to 5 HTTPS endpoints notified when a call ends, with an optional signing secret and custom headers.
Operating hours	Your business hours, available to the prompt as the `[is_open]` variable.
Pronunciation	Override how specific words are spoken. Preview each one with the play button, no test call needed.
STT	Terms the agent should recognize reliably, such as brand, street or product names.
General	Max call length (10, 15 or 20 minutes; default 15) and Block anonymous calls (callers who hide their number hear a short message and the call ends).

Every setting edits the draft. Phone calls keep using the last deployed version until you click Deploy. The simulator always uses the draft.

Managing through the API

Single prompt agents can be created and updated through the public API. The API covers the name, language, voice, prompt, welcome message, provided and extracted variables, and webhooks. A new agent created through the API is deployed right away. See the API reference for agent-create and agent-modify.

Need steps, branching, SMS, transfers or calls to your systems? Move to a flow agent. See Single prompt vs. flow agent.

Get started

Build

Single prompt agents

What you configure

Managing through the API

​What you configure

​Managing through the API

What you configure

Managing through the API