Two decades directing creative work. Four years inside Intel's validation labs deciding whether hardware was good enough to ship. Both halves point at the same job now: design the product, direct the AI that builds it, and refuse the answer that looks fine and isn't.

Case study 01 · Concept · Systems design · Color science · AI direction
High tension, low noise: the line carries the music and nothing else gets through.
Insulator is an offline music player with two interfaces, split by form factor rather than taste. The classic Winamp form is a fixed 275×116 framebuffer, so it belongs where windows dock. A phone has none — so it gets ARC, where you pick a photograph and it becomes the ground the interface sits on.

Case study 02 · Concept · Product design · AI direction
Never write after a failed read.
MoneyLedger is a private, encrypted, offline personal-finance ledger that lives in one HTML file — open it in a browser and it runs. Bad state triggers snapshot recovery, or the app refuses all writes to preserve the corrupt record rather than overwrite it. In daily use on my real finances — 1,595 transactions.
Case study 03 · Concept · Design language · Domain UX
One product, two design languages.
Homestead is a browser suite for designing and running a home renovation, tying design to cost to permits in one place. The expensive mistakes happen in the gaps between tools — you design something you can't afford or can't permit, and find out later. The tool is dark chrome around a light drawing surface; the deliverable is a separate render pass, never a screenshot of the tool.
Case study 04 · Concept · Feasibility · Acoustics · Product scope
The appealing part was the part that doesn’t work.
ST-01 is a design habit at product scale: spec it, measure it, then decide what to build. A five-section feasibility sheet for a shot timer that listens through a phone microphone — the job a competition Range Officer does with a dedicated device — and the obvious feature is the one the physics refuses.

Case study 05 · Concept · Systems design · Initiative
Five tools nobody asked for.
Built inside Intel's validation labs — on the clock, for people still using them, and none of them assigned. The drive cleaner finds what it found, shows you, and asks before it wipes. The bringup script asks separately about kernels, because a test system pinned to a build is destroyed by the update any sane default would run. The 2021 parts database is still what the lab uses.
Why this matters more than the screenshots
Assembling the evidence behind those case studies should have been a screenshot session. Both times it became an audit, because I read the output and didn't believe it.
A permit document counting a garage as conditioned living space. Every expense in a ledger signed + — money leaving, marked as money arriving. A debt goal reading “$12,293.50 of $1,500.00 — 0%”: two true numbers arranged into arithmetic that can't be right. And the serious one: re-running setup deleted transactions silently, with no confirmation and nothing to restore from, then reported success.
Not one of those could fail a test, because not one of them was a calculation. The code did exactly what it was told. A test cannot know that “conditioned space” excludes a garage, or that a plus sign on a debit is a lie. That takes somebody who knows the domain, reads the result, and refuses it.
AI made producing things nearly free, so the value moved to knowing which output to keep. I've been paid to do that since 2019.
See the working method →The system behind all of it
388 hours across 334 sessions, and at that volume the thing that breaks isn't the model being wrong — you catch that. It's drift. So the process got written down: an operating contract, ten workflows that open and close every session the same way, and 91 automated guards that test the method rather than the output. Two of them have gone red and were closed the same day — and the page keeps the count visible rather than quietly turning green.
A dashboard that only ever shows green has stopped being an instrument.
The combination is the moat
I'm a creative director with a product designer's hands. Two decades of concept work — a boutique ad agency, a self-published photography book, commercial video, half a dozen businesses I built and ran — taught me to know good when I see it. Since 2019 I've also been at Intel, validating silicon and server hardware: paid to decide whether something is good enough before a customer ever sees it.
Those felt like two careers until I noticed I keep doing the same thing in both — the lab tools above, a finance app I now run my own money on, a renovation suite for my own house. See the missing tool, build the missing tool. AI made that faster. It didn't change the other half of the job, which is refusing an answer that looks fine and isn't.
Twenty years, narrated — The Path →Same work, different order — that door opens on the craft. Otherwise: I'm looking for a remote role directing AI product or AI creative work, somewhere the taste and the rigor both get used.
Get in touch Creative director door →