I design the parts of a product where money changes hands.

I'm part of Apryse's internal AI team, and I use these tools as a partner on specific parts of my process, not a replacement for the process itself. What that looks like changes depending on what I'm working on, but the judgement always stays mine. When I say something is AI-assisted, it means the AI worked on something I'd already designed myself: a prototype built from my own high-fidelity screens, or copy tightened against a draft I wrote. It's not a shortcut past talking to users. If anything, it just means I get to more of them, sooner.

Prototyping

I can build something that behaves like a live app in under a day, so I'm able to validate a flow with real users in days instead of sprints.

Research

I use it to pressure-test a scoping document against its own goals and hypotheses, to find the gap I've missed. I also use it to transcribe and summarise session recordings, with timestamps, so I can go watch the moment myself instead of just trusting the summary.

Copy

I write warm by default, and I use AI to close the gap between my voice and the product's, so the interface reads as one consistent voice.

Feasibility

I use it to get up to speed on an unfamiliar stack fast enough to ask engineering a better question, sooner. This is exploration only. None of it ships.