AI didn’t replace the hard parts. It collapsed the distance between a decision and seeing it built.

I rebuilt my entire portfolio in a week. New stack, new brand, new copy — launched and live. That used to be a weeks long project. Now it wasn’t.

But here’s what I learned: the speed wasn’t magic. It came with rules.

Vibe coding works until you treat it like a vending machine. Long, sprawling prompts. Vague goals. “Just figure it out.” That’s where sessions go sideways and you spend three hours debugging something that a clearer prompt would’ve prevented in three minutes.

What actually worked: short prompts. One goal per session. A project PRD set up before the first line of code. When something broke, the better move wasn’t to keep pushing. It was to stop, start a fresh context, and come at the problem from a completely different angle.

Lateral thinking isn’t just a creative tool. It’s a debugging strategy.

The design thinking didn’t get faster. The research didn’t get faster. The strategic decisions still took the time they took. AI didn’t touch any of that and it shouldn’t.

What changed is the gap. The distance between deciding something and seeing it exist. That gap used to be where momentum went to die. Now it’s not.