AIJudge

AI Judge is an automated hackathon judging platform that uses AI to evaluate projects with consistency and fairness. It streamlines the entire hackathon judging workflow—from project submission to reward distribution—eliminating human bias and reducing the workload for organizers.

No more waiting days for results or dealing with inconsistent judging criteria. AI Judge analyzes project descriptions, code repositories, and demo videos to provide comprehensive evaluations based on customizable rubrics, then distributes rewards directly on-chain.

🔧 How It Works

1. Project Collection - Add projects via direct URLs or by scanning showcase pages
2. AI Analysis - Our system extracts and analyzes:
   • Project descriptions and documentation
   • GitHub repositories and code quality
   • Demo videos (with automatic transcription)
3. Multi-Model Evaluation - Projects are judged by multiple AI models using customizable rubrics
4. Transparent Scoring - Detailed breakdowns show exactly how scores were calculated
5. On-Chain Rewards - Distribute POLYGON rewards to winners with a few clicks

🔗 Key Features

• Automated Scraping: Extract project details from showcase pages
• Video Analysis: Transcribe and analyze demo videos
• Multi-AI Judging: Use multiple models for balanced evaluation
• Customizable Rubrics: Adjust criteria weights to match hackathon goals
• On-Chain Rewards: Distribute prizes directly through Polygon

💡 Why It Matters Hackathon judging is often subjective, time-consuming, and prone to bias. AI Judge brings transparency and efficiency to the process, allowing organizers to focus on community building while ensuring fair evaluations. It's like having a team of expert judges working 24/7 with perfect consistency.

AI Judge combines AI evaluation capabilities with blockchain technology to create an end-to-end hackathon judging and reward distribution system:

🧠 1. Data Collection & Processing

• Web Scraping Engine: Built with BeautifulSoup and requests to extract project details from showcase pages
• Video Processing: Uses yt-dlp and moviepy to download and process demo videos
• Transcription Pipeline: Converts video content to text for AI analysis
• GitHub Integration: Extracts and analyzes README files and repository information

🤖 2. AI Evaluation System

• Multi-Model Architecture: Leverages both OpenAI and Anthropic models for balanced judging
• Customizable Rubrics: Flexible scoring system with adjustable weights for different criteria
• Prompt Engineering: Carefully crafted prompts ensure consistent and fair evaluations
• Result Aggregation: Combines scores from multiple models for more reliable results

📊 3. User Interface

• Streamlit Frontend: Clean, responsive interface built with Streamlit
• Interactive Dashboard: Real-time updates and detailed result breakdowns
• Customization Controls: Adjust rubric weights and evaluation parameters
• Export Capabilities: Download results in various formats

💰 4. Blockchain Integration

• Web3 Integration: Uses web3.py to interact with Polygon network
• Smart Transaction Handling: Manages gas estimation and transaction signing
• Batch Processing: Efficiently distributes rewards to multiple winners
• Security First: Private keys stored securely in environment variables

🔄 5. End-to-End Flow

1. Organizer adds projects via URLs or showcase page scanning
2. System extracts all relevant project data
3. AI models evaluate projects based on customized rubric
4. Results are displayed with detailed breakdowns
5. Rewards are distributed on-chain to winning projects

The system is designed to be modular and extensible, allowing for easy addition of new AI models, evaluation criteria, or blockchain networks in the future.