Designed an AI-driven prediction service that analyzes historical legal cases and user-provided case details to estimate potential outcomes. The system combines structured case data with LLM-generated insights to produce prediction scores and supporting explanations, helping users evaluate their cases before initiating legal proceedings.
This is such a great example of turning complex data into a visual experience. 🎾🔥
Love how the court becomes part of the analytics instead of just sitting in the background. Really impressive work!
When does a sports dashboard need the court to be more than a background?
In this case, we were designing Deuce a tennis analytics platform that needed to make complex match data feel immediate and spatial, not just numerical.
The brief was clear: analysts and coaches don't just...
Nikit is a local-first AI desktop application I designed and built around my custom ZaqX language model. The project combines a modern desktop interface with local AI inference, context handling, tool controls, and a privacy-focused architecture.
I built the application with React, TypeScript, Vite, Tauri, and CSS Modules, with a modular architecture designed for performance and maintainability. The project also includes a custom small language model and supporting AI infrastructure.
The goal was to create a practical AI workspace that feels like a real product rather than a simple chatbot, while keeping the experience fast, focused, and local-first.