NERA

🎓 NORA - Northeastern Admissions Agent

AI-Powered Admissions Assistant for Northeastern University

NORA is an intelligent admissions evaluation system that uses Google Gemini AI to analyze student applications, score them across multiple criteria, and provide detailed rankings with explanations.

🚀 Live Demo

Try NORA online: Hugging Face Space

✨ Features

🤖 AI-Powered Analysis

• Google Gemini Integration: Advanced AI analysis using Google's latest language model
• Multi-Criteria Evaluation: Scores across Academics, Activities, Essays, and Recommendations
• Intelligent Justifications: Detailed explanations for each scoring decision
• Comprehensive Summaries: AI-generated applicant summaries

📊 Professional Interface

• Streamlit Web UI: Modern, responsive web interface
• Real-time Processing: Live progress tracking and status updates
• Interactive Demos: Multiple demo modes for different use cases
• Professional Styling: Northeastern University branding and modern design

🧪 Robust Testing

• Comprehensive Test Suite: 80%+ test coverage
• Unit Tests: Individual component testing
• Integration Tests: End-to-end workflow validation
• Performance Tests: Load handling and scalability testing

🎯 Demo-Ready

• Multiple Demo Modes: Full Review, Quick Preview, Individual Review
• Professional Presentations: Ready for stakeholder demonstrations
• Interactive Elements: Audience participation capabilities
• Detailed Documentation: Complete demo guides and scenarios

🏗️ Architecture

NORA/
├── agent/                 # Core AI agent logic
│   ├── admissions_agent.py    # Main agent class
│   ├── prompts.py            # AI prompt engineering
│   └── utils.py              # Utility functions
├── ui/                   # User interface
│   └── streamlit_app.py      # Streamlit web application
├── tests/                # Comprehensive test suite
│   ├── test_agent.py         # Agent unit tests
│   ├── test_integration.py   # Integration tests
│   ├── test_performance.py   # Performance tests
│   ├── test_ui.py           # UI component tests
│   └── mocks.py             # Mock data and responses
├── data/                  # Sample data
│   ├── sample_applications.json
│   └── rubric.json
└── docs/                  # Documentation
    ├── DEMO_README.md
    ├── UI_DEMO_GUIDE.md
    └── ROADMAP_SUMMARY.md

🚀 Quick Start

Prerequisites

• Python 3.8+
• Google Gemini API key

Installation

1. Clone the repository

   git clone https://github.com/sp103107/NORA.git
   cd NORA
   

2. Install dependencies

   pip install -r requirements.txt
   

3. Set up your API key

   # Windows PowerShell
   $env:GOOGLE_API_KEY = "your-api-key-here"
   
   # Linux/Mac
   export GOOGLE_API_KEY="your-api-key-here"
   

4. Run the application

   # CLI version
   python app.py
   
   # Web UI
   python -m streamlit run ui/streamlit_app.py
   

🎛️ Demo Modes

1. Full Review Mode 🚀

Complete demonstration with all 10 sample applicants

• Real-time progress tracking
• Professional leaderboard
• Detailed applicant analysis

2. Quick Preview Mode ⚡

Instant demo without API calls

• Sample data display
• UI layout demonstration
• No API key required

3. Individual Review Mode 👤

Focused analysis of specific applicants

• Select individual applicants
• Detailed scoring breakdown
• Interactive analysis

🧪 Testing

Run All Tests

python run_tests.py

Quick Validation

python run_tests.py --quick

Individual Test Suites

# Unit tests
python -m pytest tests/test_agent.py -v
python -m pytest tests/test_utils.py -v
python -m pytest tests/test_ui.py -v

# Integration tests
python -m pytest tests/test_integration.py -v

# Performance tests
python -m pytest tests/test_performance.py -v

📊 Test Results

• Unit Tests: 27/28 passing (96.4%)
• Integration Tests: 11/11 passing (100%)
• Performance Tests: 10/10 passing (100%)
• UI Tests: 11/11 passing (100%)
• Overall Success Rate: 80%+

🎓 Demo Scenarios

Executive Presentation

1. Use Quick Preview for UI overview
2. Demonstrate Full Review for complete workflow
3. Highlight professional leaderboard
4. Show detailed applicant analysis

Technical Deep Dive

1. Start with Individual Review
2. Select different applicants to show variety
3. Expand AI analysis sections
4. Discuss scoring methodology

Interactive Demo

1. Let audience choose applicants
2. Show real-time AI processing
3. Discuss specific scoring decisions
4. Answer methodology questions

🔧 Configuration

Environment Variables

• GOOGLE_API_KEY: Your Google Gemini API key (required)

API Configuration

• Model: gemini-1.5-flash (default)
• Temperature: 0.3 (controlled randomness)
• Max Tokens: Auto-determined by Gemini

🏛️ Scoring Criteria

NORA evaluates applicants across four weighted criteria:

1. Academics (30%): GPA, SAT scores, academic achievements
2. Activities (25%): Extracurricular involvement, leadership roles
3. Essay (25%): Writing quality, personal insight, authenticity
4. Recommendations (20%): Teacher/counselor endorsements

🚀 Deployment

Hugging Face Spaces

The application is deployed on Hugging Face Spaces:

• Space URL: https://huggingface.co/spaces/sp103107/NORA
• Framework: Streamlit
• Python Version: 3.9+

Local Deployment

# Production setup
pip install -r requirements.txt
streamlit run ui/streamlit_app.py --server.port 8501

📈 Performance

• Response Time: ~2-3 seconds per applicant
• Concurrent Users: Supports multiple simultaneous users
• Memory Usage: Optimized for efficient processing
• Scalability: Designed for production workloads

🤝 Contributing

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

📝 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

• Google Gemini: AI model and API
• Streamlit: Web application framework
• Northeastern University: Project inspiration and context
• Open Source Community: Testing frameworks and tools

📞 Contact

• GitHub: @sp103107
• Hugging Face: sp103107
• Project: NORA Repository

---

🎓 NORA Admissions Agent - Northeastern University Powered by Google Gemini AI