LC Studio — Project Hub

Everything
I'm building.

Tools, simulations and experiments. Click any project for architecture and tech detail — then open the live version.

01
Productivity Tool
2025

Excel AI Engine

AI-powered Excel mutation console

A natural language interface for transforming Excel workbooks. Drop a spreadsheet, describe your intent, and the engine rewrites formulas, restructures data, and applies formatting.

Next.js 14 OpenAI GPT-4o SheetJS TypeScript Vercel
View project
02
Scientific Computing
2025

Hurricane Simulator

Real-time atmospheric dynamics engine

A physics-based simulation modelling the formation and evolution of tropical cyclones. Adjustable sea-surface temperature, wind shear, and Coriolis parameters drive a real-time atmospheric grid.

Python NumPy / SciPy WebGL FastAPI Canvas API
View project

Excel AI Engine

A natural language interface for transforming Excel workbooks. Drop a spreadsheet, describe your intent in plain English, and the engine rewrites formulas, restructures data, and applies formatting — no manual editing required.

The Problem

Excel is extraordinarily powerful, but it demands deep manual effort. Most users spend hours reformatting data, writing formulas from scratch, and applying repetitive transformations. The Excel AI Engine replaces that friction with a single prompt — bridging the gap between spreadsheet complexity and natural language.

Architecture

The pipeline runs in four stages:

01 — Workbook Ingestion
SheetJS parses the .xlsx file into a structured JSON representation of each sheet's cells, data types, named ranges, and formulas.
02 — Context Embedding
The cell structure is summarised into a condensed prompt context, preserving column semantics and formula patterns without token overload.
03 — AI Completion
GPT-4o receives the context and the user's natural language prompt, returning a structured diff object describing every mutation to apply.
04 — Safe Application
Mutations are validated against the original schema before writing, ensuring no unintended data loss or formula corruption during the rewrite.
Tech Stack
Next.js 14
Frontend + API Routes
OpenAI GPT-4o
AI Completion Engine
SheetJS / xlsx
Workbook Parsing
TypeScript
Type Safety
Vercel
Hosting + Edge
Ready to explore it?
Opens the full interface in a new tab
Open Project

Hurricane Simulator

A physics-based simulation modelling the formation and evolution of tropical cyclones. Adjustable sea-surface temperature, wind shear, and Coriolis parameters drive a discretised atmospheric grid that resolves in real time.

The Problem

Atmospheric simulation is largely locked inside opaque academic or government systems — difficult to explore, modify, or understand intuitively. This project makes the physics of hurricane formation visible and interactive: a learning tool as much as an engineering one.

Architecture

A real-time physics loop feeds a WebGL renderer:

01 — Atmospheric Grid
A discretised 2D grid models air pressure, temperature, humidity, and wind velocity at each node. Boundary conditions set sea-surface temperature and large-scale wind shear.
02 — Physics Solver
NumPy solves a simplified system of the primitive atmospheric equations at each timestep — pressure gradients, Coriolis deflection, moisture flux, and latent heat release.
03 — WebGL Renderer
Output is streamed to a Canvas via WebGL shaders, visualising wind vectors, pressure isolines, and intensity bands with sub-frame latency.
04 — FastAPI Backend
Heavy compute runs off the main thread on a Python FastAPI server, keeping the browser UI responsive while physics ticks at high frequency.
Tech Stack
Python 3.12
Physics Simulation
NumPy / SciPy
Numerical Solvers
WebGL
Real-time Rendering
FastAPI
Compute Backend
Canvas API
Visualisation Layer
Still in development
No live URL yet — check back soon.
Coming Soon