> For the complete documentation index, see [llms.txt](https://docs.dapta.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.dapta.ai/ai-text-agents/ai-text-agents.md).

# Start here

Text Agents answer your customers in writing — on WhatsApp and on your website. What they do and where to start.

A **Text Agent** is an AI that writes back. It answers on WhatsApp and on your website, using your catalogue, your prices and your policies, and hands the conversation to a person the moment it should.

Your customers keep using the same number and the same app. What changes is who is on the other side.

## What you need to run one

|                              |                                                          |
| ---------------------------- | -------------------------------------------------------- |
| **An agent**                 | Its purpose, instructions, tone and language             |
| **Somewhere to answer**      | A WhatsApp line, the website widget, or both             |
| **Something to answer from** | Company context, and Brains built from your own material |
| **A way to take over**       | Inbox, where your team can step in and step back out     |

***

## Understand it first

{% content-ref url="/pages/TXgOhDoCH3jfppJaD1K2" %}
[Dapta and WhatsApp Business](/ai-text-agents/dapta-and-whatsapp.md)
{% endcontent-ref %}

{% content-ref url="/pages/Fos4bKY11uC0JD7tNfmx" %}
[What people use Text Agents for](/ai-text-agents/use-cases.md)
{% endcontent-ref %}

## Build it

{% content-ref url="/pages/6ZYEbamUuGzBf8w8LKr3" %}
[Create your first Text Agent in Dapta](/ai-text-agents/create-your-first-text-agent-in-dapta.md)
{% endcontent-ref %}

{% content-ref url="/pages/rpTjkAMt8FMFkHXWVvbj" %}
[Setting Up your Text Agent](/ai-text-agents/setting-up-your-text-agent.md)
{% endcontent-ref %}

## Connect it

{% content-ref url="/pages/M1dKoSCdZqAK4LV6ClKR" %}
[Channels and templates](/ai-text-agents/channels.md)
{% endcontent-ref %}

## Operate it

{% content-ref url="/pages/Yd8Dr1GnzSTVXV8kBdd6" %}
[Inbox](/ai-text-agents/inbox.md)
{% endcontent-ref %}

{% content-ref url="/pages/MkxAxYDMYoMqxiASZZPy" %}
[Sequences](/ai-text-agents/campaigns.md)
{% endcontent-ref %}

{% content-ref url="/pages/5ykdx4lfslge16oCKuqw" %}
[Analytics, logs, and exports](/ai-text-agents/analytics-and-logs.md)
{% endcontent-ref %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.dapta.ai/ai-text-agents/ai-text-agents.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.