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

# What is Agentalk?

Agentalk is a voice AI platform that lets businesses create AI-powered agents to handle inbound and outbound phone calls.

You configure an agent once, connect it to a phone number, and it handles calls automatically. Agents can make outbound sales calls, book appointments, answer customer questions, or provide technical support.

### How it works

At a high level, Agentalk works in three steps:

1. **Define the agent:** Configure instructions, tone, and behavior.
2. **Connect a phone number:** Assign a number for inbound or outbound calls.
3. **Handle conversations:** The agent interacts with callers and performs actions such as updating contacts or transferring calls.

This allows you to automate phone-based workflows without manual intervention.

### Use cases

Agentalk is designed for any business that relies on phone calls as part of its workflow. Common use cases include:

<table data-card-size="large" data-view="cards"><thead><tr><th></th></tr></thead><tbody><tr><td><p><mark style="color:$primary;"><strong>Sales outreach</strong></mark></p><p>Agents call a list of leads, deliver a pitch, qualify prospects, and transfer promising conversations to a human rep.</p></td></tr><tr><td><p><mark style="color:$primary;"><strong>Appointment booking</strong></mark></p><p>Agents call contacts to schedule or confirm appointments, then update contact records with the outcome.</p></td></tr><tr><td><p><mark style="color:$primary;"><strong>Customer service</strong></mark></p><p>Agents answer inbound calls, handle common questions, and transfer complex cases to a human agent.</p></td></tr><tr><td><p><mark style="color:$primary;"><strong>Technical support</strong></mark></p><p>Agents walk callers through troubleshooting steps or retrieve answers from a connected knowledge base.</p></td></tr></tbody></table>

### Who the platform is built for

Agentalk is designed for different types of users depending on their workflow:

* Businesses use Agentalk to automate phone call workflows without building custom telephony infrastructure.
* Call centers use the live call center dashboard to monitor active calls in real time, listen in silently, and take over calls from the agent when a human touch is needed.
* Agencies manage multiple client organizations from a single Agentalk account. Each organization is independent, with its own agents, phone numbers, contacts, and billing. You can switch between organizations using the navigation selector at the top of the screen.

### Next steps

Here are the recommended next steps after completing this guide:

* [**Setup checklist**](/getting-started/setup-checklist.md)**:** Set up your account and core configuration.
* [**Build your first agent**](/getting-started/build-your-first-agent.md)**:** Build your first agent and run a test call.
* [**AI agents**](/core-concepts/ai-agents.md)**:** Understand how agents are structured and how they work.


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.agentalk.io/getting-started/what-is-agentalk.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.