Skip to main content
Medical Design Program
<mdp>
Wk 1 1 2 3 4 5
Wk 2 6 7 8 9 10
← Main
< Health Design Sprint >

The Signal-to-Prototype Loop

A repeatable methodology for turning domain expertise into working AI prototypes — developed over 10 years, stress-tested with 200+ students, documented with evidence.

The Three Tools

Every participant already has three tools. The methodology teaches how to combine them.

Your Brain

Domain expertise from years of training and practice. You understand the problems, the workflows, the users. This is the scarce resource — AI can’t replicate it.

Design Thinking

User-centered methodology for structuring insight into action. Journey mapping, jobs to be done, empathy — the bridge between “this is frustrating” and “here’s what to build.”

Generative AI

Large language models as build partners for rapid prototyping. Not replacing expertise — amplifying it. Claude for thinking and synthesis, Lovable and Claude Code for building.

The Loop

Five steps, repeated daily. Each cycle adds a new design lens. Richer planning produces richer builds.

1
Design Facilitation
Structured exercises generate raw group signal — journey maps, empathy maps, pain point voting
2
Artifact Collection
Everything captured: transcripts, video, screenshots, Slack threads, whiteboard photos
3
AI Synthesis
Raw artifacts fed to Claude and structured into a Product Requirements Document — messy in, detailed review, clean out
4
Prototype Generation
PRD produces a working app via Lovable or Claude Code — a fresh build each cycle, not incremental edits
5
Design Critique
Group reviews the prototype through a new design lens — jobs to be done, personas, ethics, accessibility — generating new signal
← Each cycle adds a new design dimension. By end of sprint: 5+ versions of the same app, each reflecting deeper thinking.

Layered PRD Builds

masterplan
user journey
design
features
polish

Students generate a fresh build every day from the enriched PRD — not iterating on yesterday’s build. By Day 5, five versions of the same app reveal how planning depth compounds.

Key Insight

Why rebuild from scratch instead of iterating? Because comparing daily builds makes the planning-to-building relationship concrete. Students see directly: a richer PRD produces a richer app. The build is disposable. The thinking is cumulative.

In the OLD ERA
The hard part was building the app.
In the NEW ERA
The hard part is knowing what app to build.

Evidence

This methodology was developed over 10 years across 9 cohorts and 200+ students at the UVA Medical Design Program. The February 2026 Health Design Sprint stress-tested it in a two-week intensive format, producing 5 production-quality healthcare applications. The entire process is documented: 519 indexed transcript segments, video recordings, artifact collections, and AI-generated course narratives.

The tools don’t replace your thinking. They amplify it. Your domain expertise, design judgment, and structured planning are what make the output good.

See what students built →