Writing
Notes on solo founding, engineering, and machine learning.
Did the bet work?
Ten weeks after rewriting StudyPDF around one agent: the retention curve roughly doubled at every week I can observe, and the metric I actually promised did not move at all.
100,000 users, and the number that is going down
Fifteen thousand registrations later: organic traffic quadrupled year over year, monthly active users have fallen three months running, and the iPhone app went live two days ago.
I rewrote my entire product. Here's the bet.
I wrote about StudyPDF's retention problem, then deleted most of the product and rebuilt it around one idea: the moat is memory, not a smarter model.
How I run an 85,000-user AI study platform solo
A 22-year-old founder on building a production AI product without a team, using Claude Code as a small army.