What I'm tinkering with: AI prototyping, agent context, and a clinic check-in app built with Claude.

How this Lab went from a long-held idea to a working Webflow section in a few days, with Claude doing most of the building.

Why I fixed a few "small" issues in this Lab's rough wireframes instead of waiting for hi-fi.

A rule I set while designing the cards for this Lab: the resting state has to work on its own.

The six tools I'm exploring to stay current, and the design skill each one is meant to build.

The one change that made Claude's output better on the Check In App: context and reasoning up front.

Taking the April wireframes to a fully styled landing screen with Claude, and what styling taught me about working with AI.

Three waiting room concepts for the Check In App, each with a different idea of what a patient needs while they wait.

What a check-in form should do when a patient can't answer, and where an AI companion might fit.

Two ways to design the moment a check-in form asks something personal, and why I'm combining them.

The restart: in one working session, Claude and I turned the PRD into wireframes for all 8 key screens in Figma, two directions each.

Handing a year of research notes to Claude and getting back a PRD: the plan I keep coming back to when the project gets fuzzy.

Claude doesn't remember yesterday. A short handoff file let me pick up a Figma session exactly where I left off.

What working inside an agent-driven workflow taught me about context, speed and what we trade for it.

When a slow table couldn't be fixed right away, I looked at what design could do to make the wait feel better.

Three ideas from Team Topologies that changed how I see my role between design and engineering.

How a timestamp and one line between tasks helped me stop carrying the last task into the next one.

What the first chapter of Domain-Driven Design taught me about the diagrams designers draw.

Why I moved my personal notes out of Notion and into Obsidian, and what my system looks like now.

Turning interviews and personas into one sentence about what the Check In App does, and why anyone should care.

My check-in research gave me two solid personas. The third, an older patient, stalled because I never talked to anyone like her.

6 of the 8 people I interviewed filled out check-in forms on paper. Before designing a replacement, I wanted to know why paper still wins.

People answered the hard questions anyway. What they couldn't answer was why they were being asked.

The Check In App started with 8 interviews about waiting rooms and health forms. Here's how I ran them and what they changed.

Before interviewing anyone for the Check In App, I planned who to talk to, what to ask and how to ask it.