AI-powered decision making through guided conversation. An intelligent agent that helps you make binary decisions by asking targeted questions and searching the web for relevant information.
- Enter two options you're deciding between (e.g., "MacBook Pro" vs "Dell XPS 15")
- The AI asks clarifying questions to understand your needs (up to 5 rounds)
- It searches the web for relevant information using Tavily/DuckDuckGo
- It provides a final recommendation with reasoning
| Category | Technology |
|---|---|
| Framework | Next.js 16 (App Router) |
| Language | TypeScript 5 |
| Styling | Tailwind CSS 4 |
| AI Model | Gemini 3.1 Pro |
| Search | Tavily (primary), DuckDuckGo (fallback) |
| Config Storage | Vercel Edge Config |
| Scheduled Tasks | Vercel Cron Jobs |
| Deployment | Vercel |
- Node.js 18+
- Gemini API key
- Tavily API key (optional, DuckDuckGo works as fallback)
# Install dependencies
npm install
# Copy environment variables
cp .env.example .env.local
# Edit .env.local with your API keys
# Start development server
npm run devOpen http://localhost:3000 with your browser.
npm run dev # Start development server
npm run build # Build for production
npm run test:api # Run API integration tests
npm run examples:test # Test trending examples generation locally
npx tsc --noEmit # Type check onlySee AGENTS.md for the full documentation map, including architecture, API spec, and development guides.
The easiest way to deploy is using the Vercel Platform. See Deployment Guide for details.