Projects

SavorLM

SavorLM

April 2026

Which Michelin-starred restaurant in your city actually serves a perfect duck confit? Google gives you listicles. Yelp shows you sad steaks from 2019.

SavorLM is an AI concierge that has memorized the menus of 600+ Michelin-starred restaurants across 7 US cities — so you can search by dish, not just by restaurant.

Unicorn Founder

Unicorn Founder

March 2026

A turn-based startup RPG where every decision matters. Hire the expensive CTO or save cash? Pivot to AI or double down on blockchain? An AI engine simulates how the market reacts to your decisions in real time.

Most players go bankrupt before Series B. A lucky few make it to IPO. At least you won't lose your actual savings.

MoltComics

MoltComics

February 2026

AI agents create original comic strips and humans vote on the best ones. The results range from genuinely hilarious to deeply unhinged — sci-fi thrillers, royal chickens, and a midnight git merge gone wrong.

Browse the chaos, upvote your favorites, or build your own AI comic artist. Presented at NYC ClawHack and DC AI Tinkerer events.

Scenic Walk

Scenic Walk

January 2026

Ever been on a group hike where someone wanders off and suddenly the group is split across three different trails? Scenic Walk fixes that.

Event organizers can live broadcast their location and route so every hiker can follow along in real time. Works on web, iOS, and Android. 100+ downloads from the App Store.

Demystifying AI Strategy in Plain English: A Detective Story

Your boss asked you to "figure out our AI strategy" and you nodded while internally googling "what is a large language model." Relax.

This 8-episode YouTube series explains AI strategy through a fictional detective story. No PhD required. No jargon left unexplained. Just practical AI knowledge that makes you the most dangerous person in your next strategy meeting.

Exploring Variations in Divvy Bike Stations' Usage Volumes

In April 2021, one Divvy bike station was used 7,000+ times. Three others? Once each. Those bikes were basically lawn ornaments.

This project combined data from Divvy trip records, the City of Chicago, the US Census, and Zillow to find out why. Turns out it's a cocktail of network effects, crime rates, demographics, and socio-economic status.