Skip to main content
A Chat Agent is an AI agent that handles text conversations on your behalf — the messaging counterpart to a Voice AI Agent. Where a voice agent picks up the phone, a chat agent reads and replies to messages. It answers questions, sends templates, shares images and documents, updates your CRM, runs your own code, and can even hand the conversation over to a voice agent for a phone call — with nobody sitting behind it.

​
Channels

A chat agent is built for one channel, chosen when you create it. The channel decides which settings and functions are available, so it cannot be changed afterwards.

WhatsApp

Replies to inbound WhatsApp messages on one of your WhatsApp Business numbers. The full feature set: templates, media, calls, follow-ups.

Instagram

Replies to Instagram DMs, post comments, or both. A focused feature set — custom functions, reply gating and human transfer.

​
Three types of WhatsApp agent

A WhatsApp agent is one of three types, chosen when you create it. The type is fixed: every version of the agent has the same type.

Basic

One system prompt that describes everything — who the agent is, what it says, and when it calls each function. Quick to set up; best for open-ended help.

Advanced (flow)

A persona plus a flow of steps you design on a canvas: templates, buttons, questions, functions, conditions. Best when the conversation should follow a plan.

Chat Center Workflow

Code, conditions and sends that run on every message with no LLM, handing the rest to a Basic or Advanced agent. Best in front of an agent, for the messages that need no model.
Basic and Advanced run on the same model, settings, follow-ups and test chat; the rest of this section applies to both. A Chat Center Workflow has no model of its own — see Chat Center Workflow. An Advanced agent replaces the system prompt and the template, media, contact-card and call functions with steps of its flow — see Advanced Agents.

​
Voice agents vs chat agents

Both are agents, built in the same dashboard, and they work together — but they are separate objects with separate builders. The two are linked in both directions: a chat agent can place or schedule a call through a Send / Schedule Call function, and a voice agent can hand a contact to a chat agent after the call ends.

​
What a chat agent is made of

1

A system prompt

Who the agent is, what it may do, and when. See System Prompt.
2

A model, and a backup model

The LLM that writes the replies, plus a secondary used only if the primary errors. See LLM Model.
3

Conversation settings

How much history it sees, how many messages it may send, and which channel features it uses. See Conversation & Features.
4

Functions

The actions it can take beyond replying with text — send a template, send a file, run your own Python, place a call. See Functions.
5

A channel binding

A WhatsApp number the agent answers on, or an Instagram account it is live for. See Going live.

​
How an inbound conversation runs

Voice notes are transcribed first when Audio Transcription is on; images are readable by the model when Image Context is on.

​
Where chat agents live in the dashboard

Create a chat agent

Walk through the builder end to end

Functions

Everything the agent can do besides replying

Testing

Try the agent before anyone else does

Best practices

What separates an agent that works from one that annoys