Skip to main content
An agent is the AI participant on the other end of a phone call. You configure it once, publish it, and assign it to a phone number — then it can place outbound calls or answer inbound ones autonomously.

​
Anatomy of an agent

Every agent has these layers:

​
The configuration sections

The agent edit page builds an agent in six sections, then deploys it:
  1. Instructions — how the conversation opens, and the prompt: who the agent is, what it does, the rules it keeps
  2. Voice & Speech — language, voice, pronunciation, voicemail detection, inactivity nudge
  3. Knowledge & Training — knowledge bases attached
  4. Tools & Actions — tools the agent can call: transfers, escalation, workflows, lookups
  5. Capabilities — built-in abilities such as web search, widgets and camera, each labelled with the channels it works on
  6. Before & After — workflows that run before a conversation starts and after it ends, plus evaluations
  7. Deployment — phone numbers, publishing, SIP
You don’t have to fill every section. Defaults are sensible for most fields.

​
Versioning

Agents are versioned. Edits modify a draft version. Calls always use the latest published version. Click Publish when you’re satisfied with your changes — the new version takes effect on the next call. You can roll back to a prior version from the version history panel.

​
Lifecycle

A published agent without a phone number assignment exists but won’t receive calls. A draft can be tested in the simulator, but won’t take real calls.

​
Organizing many agents

Search, sort and filter the agent list, group agents with your own labels such as Industry or Client, save views and export to CSV. See Finding agents and workflows.