A To-Do App Doesn't Prove Anything
Most “I built this with AI” portfolios pick something safe. Safe projects hide the only question worth answering: can you ship something that has to feel right?
Search for portfolios built with AI and you get a wall of the same three projects. A calculator. A to-do app. A weather dashboard. Clean, competent, forgettable.
They are all safe in the same way: nothing about them has to feel like anything. A to-do app either saves the item or it does not. There's no version of it that works but feels wrong.
Game Feel Cannot Be Prompted
So I built an arcade game. You spell words mid-flight to cast spells, which means timing, responsiveness and difficulty curve all have to land or the whole thing is unpleasant to touch.
That's the whole point of picking it. You can't describe your way to good game feel. There's no prompt for "make the jump satisfying". You build it, play it, notice it's slightly wrong, and change one number. Then again. Then again.
Most of the Work Was Deleting
The model was genuinely fast at producing mechanics. It would happily give me another mode, another power-up, another system. Each one worked in isolation.
Almost all of them made the game worse, because a game isn't a list of features — it's a small number of things that combine well. Scope discipline was most of the design work, and it's the part that no amount of generation speed helps with.
Pick the Project That Can Fail
If you want to know whether someone can ship with AI, look at whether they picked something that could have come out bad. A to-do app can't really fail. A game can fail while every individual piece works.
That gap — between working and being good — is where the design job now lives, and it's exactly what a safe portfolio project is built to avoid.
What shipped, and what I cut to get there, is in the Fire Lion case study.
Related UX Design Articles
What One Person Can Actually Ship Now
I have four products live that I built by myself. The useful version of that story is the one that includes where solo stops working, which is not where people expect.
The Work Is Deleting, Not Generating
AI made producing screens almost free. That moved the bottleneck from making things to deciding which ones to throw away — and no model will do that part for you.
In Regulated Work, Design for the Gates — Not the AI
A pharma email takes two weeks and touches five teams in five tools. The AI's job is the work between the humans, not the work the humans are legally required to do.