Tools, simulations and experiments. Click any project for architecture and tech detail — then open the live version.
Auditable AI mutations for structured spreadsheet data
Describe a change in plain English. The engine builds a typed plan, previews every cell that changes and every downstream formula that recalculates, then commits atomically — or rolls back entirely. Nothing happens without your approval.
Interactive parametric hurricane track & loss simulator
Drag a start, end, and curve handle to set a storm track on the map; tune pressure, size, radius-of-max-wind and forward speed, then simulate the Holland (1980) parametric wind field and the resulting property losses along the path in real time.
An arbitrage-free volatility surface, built live from any option chain.
Recovers the forward from an option chain, inverts every quote to implied volatility, fits an arbitrage-free SVI/SSVI surface, then differentiates it into a Dupire local-volatility surface — the interactive companion to my MSc dissertation on the inverse problem of option pricing.
Type a change in plain English. The engine reads your workbook, builds a typed mutation plan, and shows you a cell-by-cell diff — every value that changes, every formula that recalculates downstream — before a single byte is written. Commit atomically, or discard entirely. Every operation is logged with a full audit trail.
AI tools for Excel either generate unauditable code or mutate files silently. When something goes wrong — and it does — there is no record of what changed, why, or what else it broke. The Excel AI Engine treats your workbook as a typed, auditable artifact. Every mutation is a structured plan: validated before it runs, previewed before it commits, and logged permanently. The blast radius of any change — every cell and formula that depends on what you touched — is computed and shown to you upfront.
The pipeline runs in four stages:
Download one of these workbooks, upload it to the engine, and try the prompts below. These are real operations the engine handles reliably today.
An interactive parametric hurricane simulator: drag a start point, end point, and a single curve handle to define a storm track, tune its pressure, size, radius-of-max-wind and forward speed, then watch the Holland (1980) gradient wind field and property losses play out along the path in real time.
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.
This is a parametric model — closed-form equations driven by a handful of inputs (track, pressure, radius of max wind, speed) — not a fluid-dynamics solver. Every equation below is quoted directly from the running code, not idealised.
STEP_KM = 25 km. Point count is a consequence of the great-circle distance between start and end, never a fixed constant — the storm always advances the same real-world distance per step regardless of how far the handle is dragged.(points − 1) × Δt. Because spacing is fixed, Δt is constant for a whole run — a faster storm crosses the same ground in less time, so it spends less time exposing any one property to damaging winds (see the loss model below).paratc library at 20 km distance bands out to the storm's size:The interactive companion to my MSc Financial Mathematics dissertation, The Inverse Problem of Option Pricing. It turns a raw option chain into one arbitrage-free implied-volatility surface, then differentiates that surface into the Dupire local-volatility surface σ(S,t) — the minimal model that reprices the entire smile.
Recovering a volatility model from market option prices is an inverse problem, and it is ill-posed: Dupire's local-volatility formula divides by the second derivative of price in strike, which explodes on noisy quotes — feed it raw market data and it returns negative or infinite volatilities. That instability is the theme of the dissertation, and the reason a naive approach fails.
The lab rebuilds the pricing pipeline end to end, entirely client-side. Put–call parity recovers the forward and discount from the chain itself; each out-of-the-money quote is inverted to implied volatility under Black-76; the smile is fitted per expiry with SVI, then tied into a globally arbitrage-free SSVI surface whose butterfly and calendar conditions hold by construction; and that smooth, certified surface is finally differentiated into a positive, well-behaved Dupire local-volatility surface. The arbitrage-free fit is the regularisation that tames the ill-posedness.