> ## Documentation Index
> Fetch the complete documentation index at: https://docs.brightalk.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Create your first outbound AI agent

> Follow a video of about 3 minutes 50 seconds to configure an outbound agent's voice, opening, prompt, and knowledge, then test a conversation in Playground.

Give your AI a clear task before asking it to introduce your service or understand customer needs. This video uses a merchant outreach assistant to demonstrate agent creation, voice selection, product knowledge, and conversation testing.

<video controls playsInline preload="metadata" poster="/images/tutorials/onboarding-agent-cover.png" src="https://mintcdn.com/brightalk/8kP0yKhryCqWW6PP/videos/onboarding-agent-tutorial.mp4?fit=max&auto=format&n=8kP0yKhryCqWW6PP&q=85&s=5e0bfd4de8251a00408a2f910c1a5d46" alt="Brightalk outbound AI agent tutorial with Mandarin narration and Traditional Chinese captions" aria-label="Create your first outbound AI agent, about 3 minutes 50 seconds, Mandarin narration">
  Your browser cannot play this video. Follow the written steps below.
</video>

The video is about **3 minutes 50 seconds**, with Mandarin narration and Traditional Chinese captions. Follow the English instructions below for the same workflow.

## Video chapters

| Time | Topic |
| - | - |
| 0:16 | Create an outbound agent |
| 0:32 | Browse and preview voices |
| 0:50 | Speaking rate and opening |
| 1:10 | Add product knowledge |
| 1:32 | Assign knowledge to the agent |
| 1:50 | Write the system prompt |
| 2:12 | Rewrite with AI and review |
| 2:35 | iPhone call screening |
| 3:04 | Playground testing |
| 3:29 | Save and test again |

## 1. Create an outbound agent

Open **AI agents**, click the plus button in the upper-right corner, choose a blank agent, and set its type to outbound. Give it a name that describes its purpose, such as **Merchant outreach assistant**.

Decide what the call should accomplish first. For example, learn whether the merchant needs help answering calls, then offer a demonstration if they are interested. A clear goal helps you write the opening and follow-up questions.

## 2. Choose a voice and write the opening

Select **Change voice**, choose the language and accent, and preview voices that fit your brand. After bringing a voice back to the agent settings, save the agent to apply it.

Start with a speaking rate close to 1× and adjust after listening. Your opening should identify the assistant, explain the purpose, and ask whether the customer has time.

```text theme={null}
Hello, I am the AI sales assistant for Lightpoint Services.
I would like to learn about your store's call-answering needs. Is now a convenient time?
```

If the conversation needs a customer response, keep the option to hang up automatically after the opening turned off.

## 3. Add and assign knowledge

Open **Knowledge base** in the sidebar and add product or service information. You can upload a file, provide a URL, or paste text. The video demonstrates text: enter a title and service description, submit, wait for processing, and review the content.

Return to the agent's knowledge section, select the new material, and save to complete the assignment.

| Information | Suggested location |
| - | - |
| Service descriptions, product facts, and common questions | Knowledge base |
| Assistant identity, call goal, and conversation flow | System prompt |
| Prices, promotions, and appointment times that have not been provided | Instructions to confirm with a person |

## 4. Write the prompt and use AI editing

Open the system prompt editor and describe the assistant's role, goal, tone, and answer boundaries. Use this structure as a starting point:

```text theme={null}
Role: You are the AI sales assistant for Lightpoint Services.
Goal: Understand the merchant's call-answering needs and offer a demonstration if they are interested.
Conversation: Ask one question at a time, then wait for the customer's answer.
Handling: If they are busy, ask for a better time. If they decline, close politely.
Boundaries: Use the provided product information. Refer unknown prices or promotions to a person.
```

With **AI editing**, choose whether to organize the existing script or rewrite from the current settings. Add instructions for a particular tone or goal before generating. Review the facts and flow afterward. Undo or generate another version if needed, then save the version you want to use.

## 5. Configure iPhone call screening

For the screening workflow shown in the video, enable voicemail detection in advanced settings, set the action to hang up directly, and save. Then enter a short identity and reason for calling and save the screening reply.

When the phone asks who is calling and why, the AI uses this short reply first. It waits for the person to speak before playing the full opening. This feature requires a supported outbound voice and a text opening. Recorded openings and one-time notifications are not supported; follow the eligibility shown in the settings.

## 6. Test the conversation in Playground

Save the agent, then select **Test AI agent** to open Playground. Allow browser microphone access on first use and check your input device.

You can select contact data as conversation context. This test takes place in the browser and does not call the selected contact. Start the test call, wait for the AI to answer, and begin speaking.

Check the following during the test:

* The voice, speaking rate, and opening match your expectations.
* The assistant waits for an answer after each question.
* Product answers agree with the assigned knowledge.
* Busy customers, refusals, and unknown questions follow your handling rules.

Save after each change and start a new test. Before making outbound calls, also check the [AI agent line and availability requirements](https://docs.brightalk.ai/en/concepts/agents.md).

## Next: let your agent retrieve live data

For product stock or price questions, continue with [Connect an API tool](https://docs.brightalk.ai/en/guides/connect-product-api.md) to let the assistant retrieve results from your system.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.