Conversational AI safety
My Ph.D. research at the University of Miami, advised by Dr. Ubbo Visser.
I work on what happens when a language model is deployed somewhere the stakes are human, like a counseling or companion chatbot. That means instruments, built with clinicians, that measure whether a model is actually following the protocols a good counselor would, and lightweight monitors that catch problems during a conversation instead of in an audit afterward. I'm advised by Dr. Ubbo Visser in the Department of Computer Science.
- Clinician-validated fidelity instruments adapted for machine-generated text
- Lightweight runtime monitors that flag protocol violations during a conversation, not in an audit afterward
- First-author paper under review (2026), available on request
Swift Student Challenge
Three winning entries, three years apart. Apple picks a few hundred student projects a year; these were three of them.
University of Miami coursework
Graduate coursework from the first year of the Ph.D.: an automated theorem prover in Prolog, 3D models for robotics from photos, and a set of AI search and game worlds.
DYTM
"Do You Trust Me": a deterministic verification layer for LLM code generation, with property-based-test contracts between what you ask for and the code you get.
Liftgraph
A super simple, ad-free lifting tracker with weight charts and rest timers.
Chorale
Playing tests for music teachers: assign once, sync everywhere, including Google Classroom.
Chorale lets music teachers assign playing tests, collect recordings, and export grades in one place. The iOS app goes beyond the browser with on-device recording and App Clips that open an activity in seconds, and everything stays in sync with Google Classroom.
- An iOS app and a web app at gochorale.com
- Deep sync with the Google Classroom API
- App Clips launch an activity without installing anything
delt
An experiment in multi-agent software development with a corporate-style hierarchy of agents.
FBFD
A field reference app built for the Franklin-Bingham Fire Department in Michigan.
A custom React Native app for the Franklin-Bingham Fire Department in Michigan, built front end to back end, that gives firefighters one-tap access to the phone numbers, locations, and data they need on a call.
- 300+ critical data items with quick actions for calls and directions
- Usability-tested with firefighters, deployed through iOS and Android enterprise distribution
- Admin roles for managing shared content and access
The Mood Meter
Log how you feel on a two-axis color grid, straight into Apple Health.
University of Michigan coursework
27 course projects from my CS degree, each with its own icon, from seam carving and a MapReduce to a search engine.
Dynamic Project Management Lab
Research software for Dr. SangHyun Lee's lab at Michigan: a wearable fatigue monitor, a creativity study app, and sensor tooling.
CORE
A clinical-research access platform. First place at the Michigan Ross Business+Tech Innovation Jam and a U-M Center for Entrepreneurship Fuel Award.
CORE connects people to clinical research. Researchers publish studies on the web or in the apps, and participants find studies that fit them through a matchmaking system. I co-founded it and led the engineering.
- 1st place, Michigan Ross Business+Tech Innovation Jam ($7,000)
- U-M Center for Entrepreneurship Fuel Award ($7,500)
- SwiftUI apps and a Next.js platform
Metrics for Product Zone
Track your Apple Retail sales metrics, with an Apple Watch app for logging on the go.
Neodex
A Pokédex for Apple platforms: species, moves, items, Abilities, and a team builder.
StreakPal
Reminders that whisk you to Snapchat before a streak slips away.