An intelligent case dashboard powered by AI that automates customer support workflows with smart email generation and swipe-to-review suggestions. View, filter, and manage support cases in real-time, quickly accept or decline agent suggestions based on the AI agent's confidence score, and send tone-adapted emails based on case context.

Live Demo: [Add your deployment link here]

Video Walkthrough: [Add YouTube/Loom link here]

• Node.js 18+ and npm/yarn/pnpm
• MongoDB Atlas account (free tier available)
• Google AI Studio account for Gemini API key

1. Clone the repository

git clone https://github.com/yourusername/ai-orchestrator.git
cd ai-orchestrator

2. Install dependencies

npm install
# or
yarn install
# or
pnpm install

3. Set up environment variables

Create a .env.local file in the root directory:

MONGODB_URI=mongodb+srv://username:password@cluster.mongodb.net/ai-orchestrator?retryWrites=true&w=majority
GEMINI_API_KEY=your_gemini_api_key_here

See Environment Variables for detailed setup.

4. Run the development server

npm run dev
# or
yarn dev
# or
pnpm dev

5. Open your browser

Navigate to http://localhost:3000

1. Create a free account at MongoDB Atlas
2. Create a new cluster (free tier M0)
3. Create a database user (Database Access)
4. Whitelist your IP or allow access from anywhere (Network Access)
5. Get connection string: Cluster → Connect → Connect your application
6. Replace <password> and <dbname> in connection string

1. Visit Google AI Studio
2. Sign in with Google account
3. Click "Get API Key"
4. Create new API key or use existing
5. Copy and paste into .env.local

ai-orchestrator/
├── app/
│   ├── api/
│   │   ├── cases/
│   │   │   ├── route.ts          # GET, POST cases
│   │   │   └── [id]/route.ts     # GET, PATCH, DELETE case by ID
│   │   ├── agents/
│   │   │   └── route.ts          # GET agents
│   │   ├── drafts/
│   │   │   ├── route.ts          # GET drafts
│   │   │   └── generate/route.ts # POST generate AI draft
│   │   └── gemini/
│   │       └── analyze/route.ts  # POST analyze case priority
│   ├── layout.tsx                # Root layout
│   ├── page.tsx                  # Main dashboard page
│   └── globals.css               # Global styles
├── lib/
│   ├── mongodb.ts                # MongoDB connection
│   └── gemini.ts                 # Gemini AI utilities
├── models/
│   ├── Case.ts                   # Case TypeScript interface
│   ├── Agent.ts                  # Agent TypeScript interface
│   └── Draft.ts                  # Draft TypeScript interface
├── public/                       # Static assets
├── .env.local                    # Environment variables (not in git)
├── .gitignore
├── package.json
├── tailwind.config.ts
├── tsconfig.json
└── README.md

• [Gabby] - @github - Frontend Developer
• [Sophia] - @github - Frontend Developer
• [Arwa] - @github - Backend Developer
• [Shuncheng] - @github - Backend Developer

• Google Gemini AI for powering intelligent agent automation
• MongoDB Atlas for reliable cloud database hosting
• Next.js for React framework
• Tailwind CSS for responsive design
• UI/UX design and initial component development assisted by Claude AI by Anthropic
• Code editing and development workflow assisted by Cursor

Built with ❤️ for SwampHacks XI 2026