Visual Builder

The node library is on the left side of the builder. It contains all the building blocks you can use to create workflows, organized by category:

• Triggers: Start your workflow—webhooks, schedules, manual triggers, file uploads, API polling
• Processing: Do the work—AI calls, data transformations, logic decisions, code execution
• Input: Collect data—user input, webhooks, file uploads, API endpoints
• Output: Deliver results—interfaces, webhooks, data storage, notifications

You can search for nodes by name or filter by category. Each node shows what it does, what inputs it needs, and what outputs it provides.

To add a node to your workflow:

1. Find the node you want in the library on the left
2. Click and drag it onto the canvas in the center
3. The node appears where you drop it
4. Click on the node to configure its settings

Nodes are automatically arranged on a grid, so they line up neatly. The system places new nodes smartly so they don't overlap with existing ones.

Connections show how data flows through your workflow:

1. Each node has input handles (top) and output handles (bottom)
2. Click and drag from an output handle (bottom) to an input handle (top) to create a connection
3. The system shows a straight line connection as you drag
4. If the connection is valid, it appears in blue; invalid connections are shown in red and won't work

The system automatically validates connections as you make them. If a connection isn't valid—for example, if the data types don't match—you'll see an error message explaining why.

You can have multiple connections from one output to several inputs, or from several outputs to one input. This lets you build complex workflows where one step feeds into many others.

Each node has settings you can customize:

• Basic settings: Required fields like model selection, API keys, prompts
• Advanced settings: Optional parameters like temperature, timeout, retry logic
• Output settings: How results are formatted and delivered

Click on any node to open its configuration panel on the right. Required fields are marked clearly, and the system shows you what each setting does. Some settings use templates where you can reference data from earlier steps using placeholders like {{variable}}.

You can also use variable resolution—if a setting says "Use data from step 1," the system automatically fills it in when the workflow runs.

The canvas is where you build your workflow. You have full control over how you view and work with it:

• Pan: Click and drag on empty space to move around the canvas
• Zoom: Use the zoom controls or mouse wheel to zoom in and out
• Grid: Nodes snap to a grid for clean alignment
• Mini-map: See an overview of your entire workflow in the corner

The canvas uses straight line connections (not curved) for clarity, and nodes are arranged automatically so they don't overlap. You can always reorganize nodes by dragging them to new positions.

With 76+ nodes available, searching helps you find what you need quickly:

• Search bar: Type to search nodes by name or description
• Category filter: Filter by category (Triggers, Processing, Input, Output)
• Subcategory filter: Narrow down further (AI/ML, Web Services, Database, etc.)

The node library shows matching results as you type, and you can combine search with category filters to find exactly what you're looking for.