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

# Quick Start

> Build your first workflow in 5 minutes

# Quick Start

Let's create a simple workflow that responds to a webhook with an AI-generated message.

## Step 1: Create a New Workflow

1. Open MachinaOs at `http://localhost:3000`
2. Click **File > New Workflow** or press `Ctrl+N`
3. You'll see an empty canvas with a component palette on the left

## Step 2: Add a Webhook Trigger

1. In the component palette, expand **Utilities**
2. Drag **Webhook Trigger** onto the canvas
3. Click the node to select it, then click the **gear icon** to configure:

```
Path: hello
Method: POST
```

<Tip>
  Your webhook will be available at `http://localhost:3010/webhook/hello`
</Tip>

## Step 3: Add an AI Chat Model

1. Expand **AI Models** in the palette
2. Drag **OpenAI Chat Model** onto the canvas
3. Position it to the right of the Webhook Trigger
4. Connect them by dragging from the Webhook's output handle to the AI model's input handle

### Configure the AI Model

Click the gear icon and set:

```
Model: gpt-5.5
Temperature: 0.7
```

<Tip>
  Pick any model the provider offers. OpenAI currently exposes GPT-5.5 / 5.4 / 5.2, GPT-4.1 / 4.1-mini / 4.1-nano, o3 / o4-mini, and GPT-4o / 4o-mini.
</Tip>

<Warning>
  You need an OpenAI API key. Click the **key icon** in the toolbar to add it.
</Warning>

## Step 4: Set the Prompt

In the AI model's parameters, set the **Prompt**:

```
You are a friendly assistant. The user sent: {{webhookTrigger.body}}

Respond with a helpful greeting.
```

<Info>
  The `{{webhookTrigger.body}}` syntax pulls data from the webhook's output.
</Info>

## Step 5: Add a Webhook Response

1. Drag **Webhook Response** from Utilities
2. Connect the AI model's output to the Webhook Response input
3. Configure it:

```
Status Code: 200
Body: {{openaiChatModel.response}}
Content Type: application/json
```

## Step 6: Deploy and Test

1. Click the **Deploy** button (purple) in the toolbar
2. Your workflow is now listening for webhooks

### Test with curl

```bash theme={null}
curl -X POST http://localhost:3010/webhook/hello \
  -H "Content-Type: application/json" \
  -d '{"message": "Hello from curl!"}'
```

You should receive an AI-generated response!

## Your First Workflow

Your completed workflow looks like this:

```
[Webhook Trigger] --> [OpenAI Chat] --> [Webhook Response]
```

<Check>
  Congratulations! You've built your first MachinaOs workflow.
</Check>

## What's Next?

<CardGroup cols={2}>
  <Card title="AI Agent Tutorial" icon="robot" href="/tutorials/ai-agent-workflow">
    Build an AI agent with memory and tools
  </Card>

  <Card title="WhatsApp Automation" icon="whatsapp" href="/tutorials/whatsapp-automation">
    Automate WhatsApp messages
  </Card>

  <Card title="Node Catalog" icon="grid" href="/nodes/overview">
    Explore every node category
  </Card>

  <Card title="Deployment" icon="server" href="/deployment/production">
    Deploy to production
  </Card>
</CardGroup>
