Building with AI
A small collection of the products I had wanted for years, and could finally build once the cost of starting fell.
Derek Fidler20266 min
For most of my career, an idea had to clear a high bar before I could act on it. It needed to be important enough to justify a team, a roadmap and months of engineering time. That left a long list of small, useful products in my head: things I would use every day, but could never quite justify building.
AI changed the maths. I can now make a real version quickly enough to find out whether an annoyance is actually worth solving. These apps are not concept work. Each one has forced me to learn the parts of product development that used to sit just beyond my reach: authentication, bank connections, health data, OAuth, native platforms, distribution and the unglamorous work of earning trust.
Piggy
Piggy is the European budgeting and long-range financial outlook I had wanted to build since redesigning YNAB in 2019. It connects the daily discipline of envelope budgeting with investments, mortgages, retirement and the question of when work becomes optional. Building it meant taking on real bank authorization, investment reporting and a native SwiftUI companion, not just designing a financial dashboard.
Dinnr, Fit Habit and Do It
Dinnr turns recipes scattered across links, screenshots and cookbooks into a usable library and weekly plan. Fit Habit made strength training and body-composition trends more legible without turning them into another streak. Do It is a task manager built around the practical reality that some things matter more than others. Each began with a small frustration I had learned to live with.
The point of the work is not that AI builds products without judgement. It makes judgement more central. When a working version can happen in days, the hard questions become sharper: Is this useful? Is it coherent? Does it earn its place in someone's life? Which ideas deserve to exist?
