Amanda Cathey — process

Human judgment at the center. AI at the edges.

A walk through how I actually work, from research through a shipped, reviewed design, and exactly where AI fits along the way.

AI is genuinely useful for synthesis and speed. It doesn't decide what's right for the person on the other end of a workflow, that's still my job.

This is the principle behind everything on this page.

My process

Four stages, the same ones I've used on regulated, high-stakes products for over a decade. AI shows up at specific points, never all of them.

The process Where AI helps
1

Discover

Talk to the people who'll actually use this. Interviews, usability testing, support feedback, heuristic audits, understand what's actually breaking down before proposing anything.

AI helps here

Clustering findings across interviews faster, so patterns surface sooner. It doesn't decide what the pattern means, that's still mine to interpret.

2

Define

Turn what I learned into a clear problem statement, often different from the original ask. This is where I push back if the real problem is bigger than the requested feature.

3

Design

Sitemap, prototype, and design in Figma using our design system. Test early rather than waiting for a polished version.

AI helps here

Fast first-pass prototypes to react to sooner, and structured documentation drafted from a plain description, which I still review and correct.

4

Validate

Usability testing before shipping, then watching real adoption after launch. Stakeholder check-ins happen throughout this whole process, not just at the end.

Where design meets code

The step most people don't see: how a finished design actually becomes a working feature, and where a human has to be the one who signs off.

01

Design in Figma

Structure, real tokens, documented components, same as always.

02

Figma MCP exposes real design data

Actual color tokens and component names, not a screenshot guess, plus links to design system documentation.

03

An AI coding agent drafts a first pass

Claude Code, Codex, whichever a team has standardized on, generates a starting implementation grounded in that real data.

04

A person reviews before it ships

Every time. The AI's confidence is not the same thing as correctness, especially in a regulated workflow.

The best design disappears.
What remains is trust.
— the principle behind every stage above