Electrical & Computer Engineering at Cornell. I design systems end to end and put them in front of real users.
Fig. 00 — Step response
Production site for a brokerage with two Long Island offices. Residential, rental and commercial listings share one typed pipeline built on discriminated unions, so invalid state combinations fail to compile rather than reaching the page.
A tent rental business on Long Island. The first site I designed, built, shipped and sold end to end — scoped, delivered and handed over on its own domain.
An experiment in presenting reporting without editorial slant. It runs on sample articles today; the unsolved part is defining “unbiased” precisely enough to measure it.
These interlock. The archiver feeds the tutor; Inkline’s output is built to feed it too. I design schemas with their downstream consumers in mind.
Ingestion pipeline that archives Cornell Canvas courses into a clean, queryable manifest — the foundation layer for a course tutor.
Retrieval-augmented tutor over archived course material, with citations back to source. Consumes the archiver’s schema.
Reads a PDF aloud with the current sentence highlighted. Continuous audio kept in sync with the text is the hard part — and it’s an architecture problem, not an AI problem.
Handwriting-to-text pipeline with a CER/WER eval harness standing as the release gate.
Jurisdiction-aware legal information tool. Escalation-recall evals are the release blocker.
I’m a junior in Electrical & Computer Engineering at Cornell, and I run a small web practice on Long Island. Most of what I know came from shipping things people actually depend on — a brokerage’s listings, a barber’s booking path, a rental business’s entire online presence — and from building the systems I wanted to exist for my own coursework.
More about me →