AI can make code cheaper to generate. It does not make engineering judgment cheaper.
This is my working guide to building software with AI. I use AI coding tools to get to runnable versions faster, but I still want the problem, constraints, architecture and definition of done to stay explicit.
From the engineering archive: This is part of my earlier personal technology notebook. The main DadIdeaLab site now focuses on children, digital parenting and playful learning. If you’re here for family ideas, start here →
Start with the problem, not the prompt
Before asking AI to build anything, I try to compress the work into four things: the problem, the relevant context, the constraints and what “done” means.
- Problem: What is actually broken, slow, repetitive or missing?
- Context: What does the current system already do?
- Constraints: What must not change?
- Done: How will I judge the result?
Make the problem smaller before the architecture gets bigger
A complicated system can contain a narrow problem. I often get more leverage from stating that problem clearly than from jumping straight to a new service, cache, database or framework.
Related guide: Small Systems for Removing Repeated Friction
Start product work from repeated friction
Features are easier to judge when they answer a named friction. This is the pattern behind several small tools I keep returning to: notice repeated friction, make the smallest useful intervention then see whether the friction actually disappears.
Field note: Most Product Ideas Start in the Wrong Place
Treat generated code as a proposal
Generation can be fast. Acceptance should stay expensive. I still want to inspect boundaries, failure modes, hidden complexity, tests and behaviour outside the happy path.
Product architecture includes data choices
When AI is inside a product, storage, source traceability and local-versus-cloud choices become part of the user experience rather than invisible implementation details.
Related field notes: Where Do Your Child’s AI Notes Actually Go? and Your Child Can Learn a Lot on YouTube. But What Will They Actually Keep?.
The decision rule I keep using
Use AI to make experiments cheaper. Keep the important engineering decisions inspectable.
