Crawft

Crawft began as a tool for me. For two years I'd been asking what actually changes how people use their screens: first in my research on how Austin teens live with social media, which I presented in London, then in LimitlessMinutes, an app where friends keep each other off their phones, then in TaskGo!, a Mac task app I built whose early Activity tab charted my keyboard and mouse use. By May 2026 I was tracking my own habits with a homemade setup on my Mac. On the evening of May 21 I called it “janky” and asked an AI for something “more sophisticated, more comprehensive, and more robust.” Within about an hour I had two specs. Two days later the first version was running, and I pointed it at the place I knew best: my own school.

Alpha School is the private school in Austin where I'm a student. AI tutors cover academics there in two to three hours each morning, so a large part of every school day happens on a computer, and teachers need to know what happened on it. I know that problem from the student's side of the screen.

That makes Alpha the right first school for Crawft. I'm building it for Alpha right now, and its first beta ran on Macs at Alpha and on my own.

I own the product and every architecture decision, and I log each one in a numbered decision record that now runs past 560 entries. AI agents write the code from my specs and test it the way a user would. Together we've shipped a native Mac app, a production backend on AWS, the dashboards teachers read and a console for setting up schools and their computers.

When I wanted a Windows version, a lead agent split the work into nine milestones, worker agents built each one, and separate reviewer agents approved or rejected every piece. It shipped as a private beta in September. The system behind that work is on the Workshop page.

Crawft is in beta today. Every organization gets the same dashboard, so it works for a company that owns its Macs as well as for a school, and businesses have noticed. I demoed Crawft to Bill Perkins, one of the two investors who made me a $25,000 offer on a pitch show in Hawaii. My roommate from Wharton's summer program introduced me to his family's company group in Brazil, which asked about testing it with its employees, and in September I presented it to their team over a video call.

John Alznauer, my first boss and the founder of the film-marketing startup where I ran sales, offered $20,000 for 5% of Crawft. That offer valued the company at $400,000. I passed, because it wasn't “representative of how much my company was actually worth.” I kept the equity and went back to building.

Alpha comes first. After it, I want Crawft in other private schools, where teachers face the same gap between the work they assign and the work they can see. Businesses can come later. For now, I'm building Crawft for teachers.