> 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-voice-agents/how-to-set-up-your-ai-voice-agent.md).

# Configure your agent

Where everything lives on your voice agent's page: its context, the prompt, tests, voice and call settings, actions, brains, analysis, call log, metrics and channels.

Open your agent from **Voice Agents** to see its page. The prompt is always on the right, and the tabs on top hold everything else. Change what you need, then click **Save changes** at the top right.

{% embed url="<https://files.gitbook.com/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FCy5rSNtQmtqYCGzJlNEB%2Fuploads%2Fgit-blob-bae886fbc323ffedb6e797274ef31a7453a15e8b%2Fvoice-agents-configure-your-agent.mp4?alt=media>" %}

{% file src="/files/WEAMMgxTE0lZ4LjvW50O" %}

## The tabs

| Tab               | What you do there                                                                          |
| ----------------- | ------------------------------------------------------------------------------------------ |
| **Context**       | The company the agent speaks for, and its language, name, purpose, timezone and caller ID. |
| **Test Agent**    | Try the agent by web call, phone call, chat or simulation.                                 |
| **Settings**      | How it sounds and behaves on a call (below).                                               |
| **Call Analysis** | What the agent captures from each call and where it sends it.                              |
| **Call Log**      | Every call, with its recording and transcript.                                             |
| **Metrics**       | How the agent is doing over time.                                                          |
| **Channels**      | Where the agent answers or calls from.                                                     |

The clock next to the agent's name opens its version history, so you can go back to an earlier version.

***

## The prompt

The prompt is the agent's instructions. **Preview** shows it formatted, and **Markdown** shows the plain text.

* **Improve with AI** suggests changes to the whole prompt; you accept or reject them.
* Select part of the text to improve only that part.
* Type `{{` to insert a variable, such as `{{contact_name}}`, that changes on every call.

{% content-ref url="/pages/E4aI8Qcgr3XygWSSNesf" %}
[Improving prompts with AI](https://docs.dapta.ai/ai-voice-agents/how-to-set-up-your-ai-voice-agent/improving-prompts-with-ai.md)
{% endcontent-ref %}

{% content-ref url="/pages/IQOmltvUjLaUpqfOfEI9" %}
[Using dynamic variables](https://docs.dapta.ai/ai-voice-agents/how-to-set-up-your-ai-voice-agent/using-dynamic-variables.md)
{% endcontent-ref %}

***

## Settings

**Settings** groups everything about the call itself. Click a section to open it, and **Learn More** next to a setting for its own guide.

* **Voice Settings**: the **Voice**, **Voice Model**, **Voice Speed**, **Voice Temperature** and **Voice Volume**, and the **LLM Model** that thinks for the agent.
* **Speech Settings**: **Background Sound**, **Responsiveness**, **Interruption Sensitivity**, **Active Listening**, **Boosted Keywords**, **Spoken Format**, **Transcript Formatting Mode**, **Reminder Message Frequency** and **Pronunciation**.
* **Call Settings & Behavior**: **Public call link**, **Voicemail Detection**, **End Call on Silence**, **Max Call Duration**, **Start Behavior** and **Response Delay**.
* **Keypad Input**: let the agent hear the keys a caller presses.
* **Agent Actions**: what the agent can do during a call, such as booking an appointment or ending the call.
* **Brains**: knowledge bases the agent can look things up in.

{% content-ref url="/pages/Mf25ERdxGkiRA0bXiPA6" %}
[Voice Agent Settings Guide](https://docs.dapta.ai/ai-voice-agents/how-to-set-up-your-ai-voice-agent/voice-agent-settings-guide.md)
{% endcontent-ref %}

{% content-ref url="/pages/ep52rgmRRdUR5nGya2Zh" %}
[Agent actions](https://docs.dapta.ai/ai-voice-agents/agent-actions.md)
{% endcontent-ref %}

{% content-ref url="/pages/Jq92s6dbfZDVZjcXS99k" %}
[Brains](https://docs.dapta.ai/ai-voice-agents/how-to-set-up-your-ai-voice-agent/brains.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-voice-agents/how-to-set-up-your-ai-voice-agent.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.
