Designers growing into the role
Grow into the founding role.
You're a designer growing into the founding role.
The job underneath the title has been rebuilt. This path walks the core argument, the new toolchain, and the working methods that replace static handoff.
Before you start
The 10-second version
Before: users did the work, so design meant making the doing easy.
Now: AI does the work, so design means making it easy to tell whether the work is any good.
Who cares? Any team whose users hesitate over an AI output. That hesitation, unanswered on-screen, is why they don't come back. Evaluation design — sources, assumptions, confidence, preview, undo — is the new foundation.
In order
Your reading path
Read the guides in this order — each one builds on the last.
01
The core argument. Execution collapsed, evaluation became the bill, and verification design is now the moat.
02
Figma for intent, Claude Code for behavior, markdown instructions for judgment — with a real example of what an instruction file looks like.
03
Why static state matrices fail, how vertical slices with realistic dummy data become the spec, and what this changes about handoff.
04
Seven interaction patterns worth stealing (receipts, ghost text, preview-then-commit, earned autonomy) and the anti-patterns to name and kill.
05
Iteration when building is nearly free: the five-day loop, the kill rate, and why shipped slop spends user trust.
What you'll walk away with
Takeaways
Every unit of execution effort the AI absorbs is reissued to the user as evaluation effort — design for judging, not just doing.
The toolchain spans three layers: Figma for intent, Claude Code for behavior, markdown instructions for judgment.
Build one feature completely, with realistic dummy data, as working code — the prototype becomes the spec.
Iterate in five-day loops: name the riskiest assumption, build the smallest real version, test it in the real moment, write the learning down.
Begin