Workflow Editor

Navigate the canvas, toolbar, node panels, and AI agent sidebar.

The workflow editor is where you design automations. Open any workflow from Dashboard → Workflows to access it.

Canvas

  • Drag nodes from the left toolbar onto the canvas.
  • Connect nodes by dragging from an output handle (right side) to an input handle (left side).
  • Click a node to open its configuration panel on the right.
  • Pan by dragging the background; zoom with scroll or the controls in the corner.
  • Select multiple nodes with Shift+click or by dragging a selection box.

Toolbar

Nodes are grouped by category:

CategoryNodes
CoreStart, End
ToolsAction, HTTP Request, AI Agent
LogicCondition, Loop, Delay
DataFunction, Transform, Text

Drag any node onto the canvas. The node name updates automatically based on its type and trigger (e.g. "Every Morning (9am)" for a schedule trigger).

Header actions

ActionDescription
SavePersist your workflow definition
RunExecute the workflow manually
Import / ExportShare encrypted workflow files with your team
VariablesManage workflow-level variables
SettingsWorkflow name, description, and metadata

Node configuration panel

Click any node to open its panel on the right. Each node type has a dedicated configuration UI:

  • Text fields, dropdowns, and code editors for settings
  • Variables button to insert data references from previous nodes
  • Execution Data tab (after a run) to inspect what the node received and produced

AI Agent sidebar

The editor includes a built-in AI Agent chat sidebar. Use it to:

  • Ask questions about your workflow
  • Get help configuring nodes
  • Request workflow changes in natural language

The agent can suggest node additions and modifications. When a workflow step needs app access you haven't connected yet, you'll see an Authentication Required prompt to complete OAuth.

Workflow completion

Workflows do not require an End node. When a node has no outgoing connections, the workflow completes automatically at that point. You can still add an End node if you want to define a specific output action.

Tips

  • Name your nodes clearly — variable pickers and execution logs use these labels.
  • Save frequently; the editor auto-tracks unsaved changes.
  • Use the Execution Data tab after a test run to debug what each node received.