---
title: "Quickstart: your first text agent"
description: "Create a text agent, choose its model, chat with it, and get the one-line embed code for your website. About five minutes."
---

A text agent answers in writing: on a web page through the widget, or in Slack,
Telegram, Microsoft Teams, WhatsApp and Discord through a deployment. This page
creates one and ends with the embed code for a website.

:::note[Before you start]
You need a Callab AI account with a workspace and **AI Agents** in your sidebar.
:::

## Create the agent

1. **Open the wizard**

    In the sidebar choose **AI Agents**, then **Create Agent**.

2. **Choose text, then a single prompt**

    Pick **Text Agent**, then **Single Prompt Agent**.

3. **Start from scratch**

    Choose **Start from scratch**. The agent is created at once, named
    **New Text Agent**, and opens in its workspace. There is no voice step: a text
    agent has a model instead of a voice.

<video src="/media/get-started/create-text-agent.mp4" autoplay loop muted playsinline></video>

*Creating a text agent takes three choices.*

## Name it and pick a model

1. **Rename it**

    Under **General**, replace the name with your own and add a one-line
    **Description**. Set **Language** to the language your customers write in.

2. **Choose the model**

    Under **Model**, pick the LLM that answers, for example **GPT-5.4 Mini**. The
    choice can be changed at any time.

3. **Write the prompt and save**

    Fill **Agent Identity**, **Tasks** and **Guardrails** as in the
    [voice quickstart](/get-started/quickstart-voice-agent#write-the-prompt), then
    **Save**.

![The Model section of a text agent.](/media/get-started/text-agent-model.webp)

## Chat with it

Under **Testing**, choose **Chat**. Type a message and send it. The reply streams in,
and each turn shows its response time.

<video src="/media/get-started/chat-test-text.mp4" autoplay loop muted playsinline></video>

*The Chat test.*

## Get the embed code

1. **Open the widget**

    Under **Release**, choose **Widget**. The configurator shows a live preview on
    the right; the presets and the **Layout**, **Avatar**, **Text**, **Colors** and
    **Features** panels change it.

2. **Copy the code**

    Choose **Embed Code**, then **Copy**. It is one custom element and one script
    tag. Paste it before the closing `body` tag of any page.

3. **Make the agent public**

    An embedded agent has to be reachable without signing in. Choose **Share
    agent** at the top of the workspace, then turn on **Agent Visibility**.

![The embed code for a text agent.](/media/get-started/widget-embed-code.webp)

## Verify

- **Conversations** in the main sidebar lists the chat within a few seconds: the
  agent, the channel (**Web**), turns, tokens and status.
- Open it to read the thread, the model that answered and the token usage per turn.

## Troubleshooting

- **The widget loads but the agent does not answer.** The agent is still private.
  Turn on **Agent Visibility** under **Share agent**.
- **The reply says the model does not exist.** The agent still has the model it was
  created with. Pick one under **Model** and save.
- **The reply is in the wrong language.** Set **Language** under **General**, and
  say so in **Guardrails** as well.

## What next

**[Deploy to Slack or WhatsApp](/deploy/bot-deployments/overview)**

Put the same agent in the apps your customers already use.

**[Style the widget](/deploy/widget-and-embed/widget-designer)**

Presets, colours, labels and placement.

**[Give it knowledge](/build/tools/knowledge-base)**

Answer from your own documents.

**[Capture outcomes](/build/outcomes)**

Structured fields after every conversation.