Generative AI Hackathon with IBM Granite

Start

Patrick C

ProcessLens is a comprehensive process mining and analysis platform built with IBM Granite 3.8B at its core. Our team developed a dual-layer analysis pipeline that processes operational data through both structured metric calculations and Granite's natural language capabilities.
Technical Implementation:

Frontend: Built with Next.js 15 and React 19, featuring real-time WebSocket updates and interactive visualizations using Recharts. The UI includes dark/light mode theming, responsive layouts, and enterprise-grade components from shadcn/ui.
Backend: FastAPI implementation with a sophisticated analysis pipeline, MongoDB integration via motor, and GridFS for large file handling up to 100MB.

Key Features:

Data Processing & Analysis:


Support for CSV and Excel with robust validation
Parallel processing pipeline using IBM Granite for text analysis and structured metrics
Real-time thought process visualization through WebSocket connections
Comprehensive error handling with automatic retries


Visualization & Metrics:


Interactive performance dashboards showing cycle times and throughput
Process pattern detection with confidence scoring
Resource utilization analysis with heat maps
Anomaly detection and bottleneck identification


Enterprise Integration:


WebSocket-based real-time updates
MongoDB GridFS for scalable file storage
Comprehensive API documentation
PDF report generation with detailed insights


Process Mining Capabilities:


Automated pattern recognition in process flows
Resource allocation optimization suggestions
Performance bottleneck identification
Cross-process correlation analysis


Production Features:


Role-based access control
Dark/light mode support
Responsive design for all devices
Enterprise-grade error handling

The system demonstrates advanced integration of IBM Granite through:

Token-optimized prompting
Structured output parsing
Error recovery mechanisms
Context-aware analysis



Process analysis platform using IBM Granite 3.8B for detailed operational insights. Features real-time analysis, metric visualization, and automated reporting for enterprise process data.

"PL team on Generative AI Hackathon with IBM Granite Hackathon"

Team Idea

Submission