I built a Gem in twenty minutes to handle a framing problem I'd been fighting for months. That part worked. What I didn't expect was what happened when I started giving it stakeholder feedback — and asking it to improve its own instructions.

I sat down to update my resume thinking I knew what I'd accomplished. Months of daily journal entries told me otherwise — not by surfacing things I'd forgotten, but by showing me things I was actively doing that I'd never thought to claim. Turns out the gap between what you do and what you say you do is wider than you think. And it has nothing to do with memory.

I had 387 items of feedback and a process I'd trusted for years. Then AI did the same job — and the uncomfortable part wasn't the time it saved. It was the question I couldn't stop turning over afterward.