ai-elements-workflow
AI Elements Workflow
This skill provides comprehensive guidance for building workflow visualizations using Vercel AI Elements with React Flow.
When to Use
- Building interactive node-based workflow interfaces
- Creating process flow visualizations
- Implementing diagram editors with custom nodes and edges
- Adding workflow visualization to AI applications
Setup
1. Create Next.js Project
npx create-next-app@latest ai-workflow && cd ai-workflow
Choose to use Tailwind in the project setup.
2. Install AI Elements
npx ai-elements@latest
This also sets up shadcn/ui if not configured.
3. Install React Flow
npm i @xyflow/react
4. Add Components
Install the workflow components as needed:
npx ai-elements@latest add canvas
npx ai-elements@latest add node
npx ai-elements@latest add edge
npx ai-elements@latest add connection
npx ai-elements@latest add controls
npx ai-elements@latest add panel
npx ai-elements@latest add toolbar
Building a Workflow
Import Components
'use client';
import { Canvas } from '@/components/ai-elements/canvas';
import { Connection } from '@/components/ai-elements/connection';
import { Controls } from '@/components/ai-elements/controls';
import { Edge } from '@/components/ai-elements/edge';
import {
Node,
NodeContent,
NodeDescription,
NodeFooter,
NodeHeader,
NodeTitle,
} from '@/components/ai-elements/node';
import { Panel } from '@/components/ai-elements/panel';
import { Toolbar } from '@/components/ai-elements/toolbar';
import { Button } from '@/components/ui/button';
Define Node IDs
const nodeIds = {
start: 'start',
process1: 'process1',
decision: 'decision',
output1: 'output1',
output2: 'output2',
complete: 'complete',
};
Create Nodes
const nodes = [
{
id: nodeIds.start,
type: 'workflow',
position: { x: 0, y: 0 },
data: {
label: 'Start',
description: 'Initialize workflow',
handles: { target: false, source: true },
content: 'Triggered by user action',
footer: 'Status: Ready',
},
},
// Add more nodes...
];
Create Edges
Use animated for active paths and temporary for conditional/error paths:
const edges = [
{
id: 'edge1',
source: nodeIds.start,
target: nodeIds.process1,
type: 'animated',
},
{
id: 'edge2',
source: nodeIds.decision,
target: nodeIds.output2,
type: 'temporary', // For error/conditional paths
},
];
Define Node Types
const nodeTypes = {
workflow: ({
data,
}: {
data: {
label: string;
description: string;
handles: { target: boolean; source: boolean };
content: string;
footer: string;
};
}) => (
<Node handles={data.handles}>
<NodeHeader>
<NodeTitle>{data.label}</NodeTitle>
<NodeDescription>{data.description}</NodeDescription>
</NodeHeader>
<NodeContent>
<p className="text-sm">{data.content}</p>
</NodeContent>
<NodeFooter>
<p className="text-muted-foreground text-xs">{data.footer}</p>
</NodeFooter>
<Toolbar>
<Button size="sm" variant="ghost">Edit</Button>
<Button size="sm" variant="ghost">Delete</Button>
</Toolbar>
</Node>
),
};
Define Edge Types
const edgeTypes = {
animated: Edge.Animated,
temporary: Edge.Temporary,
};
Render the Canvas
const App = () => (
<Canvas
edges={edges}
edgeTypes={edgeTypes}
fitView
nodes={nodes}
nodeTypes={nodeTypes}
connectionLineComponent={Connection}
>
<Controls />
<Panel position="top-left">
<Button size="sm" variant="secondary">Export</Button>
</Panel>
</Canvas>
);
export default App;
Key Features
| Feature | Description |
|---|---|
| Custom Node Components | Use NodeHeader, NodeTitle, NodeDescription, NodeContent, NodeFooter for structured layouts |
| Node Toolbars | Attach contextual actions to nodes via Toolbar component |
| Handle Configuration | Control connections with handles: { target: boolean, source: boolean } |
| Edge Types | Edge.Animated for active flow, Edge.Temporary for conditional paths |
| Connection Lines | Styled bezier curves when dragging new connections |
| Controls | Zoom in/out and fit view buttons |
| Panels | Position custom UI anywhere on the canvas |
Component Reference
For detailed props and API documentation for each component, see references/components.md.
More from sstobo/convex-skills
betterauth-tanstack-convex
Step-by-step guide for setting up Better Auth authentication with Convex and TanStack Start. This skill should be used when configuring authentication in a Convex + TanStack Start project, troubleshooting auth issues, or implementing sign up/sign in/sign out flows. Covers installation, environment variables, SSR authentication, route handlers, and the expectAuth pattern.
68convex-tanstack
Comprehensive guide for building full-stack applications with Convex and TanStack Start. This skill should be used when working on projects that use Convex as the backend database with TanStack Start (React meta-framework). Covers schema design, queries, mutations, actions, authentication with Better Auth, routing, data fetching patterns, SSR, file storage, scheduling, AI agents, and frontend patterns. Use this when implementing features, debugging issues, or needing guidance on Convex + TanStack Start best practices.
42convex-queries
This skill should be used when implementing Convex query functions. It provides comprehensive guidelines for defining, registering, calling, and optimizing queries, including pagination, full text search, and indexing patterns.
24convex-actions-general
This skill should be used when working with Convex actions, HTTP endpoints, validators, schemas, environment variables, scheduling, file storage, and TypeScript patterns. It provides comprehensive guidelines for function definitions, API design, database limits, and advanced Convex features.
23convex-mutations
This skill should be used when implementing Convex mutation functions. It provides comprehensive guidelines for defining, registering, calling, and scheduling mutations, including database operations, transactions, and scheduled job patterns.
21convex agents tools
Enables agents to call external functions, APIs, and database operations through tool definitions. Use this when agents need to fetch data, perform actions, or integrate with external services while maintaining clean separation.
21