The team

One director. Four AI collaborators. A new kind of build.

5
Team members
Dave + 4 AI collaborators
90+
Design tokens
Aurora Glass system
63
Logged decisions
Every one traceable to a conflict
2
Products
One system, no changes between them
The relationship

I don’t prompt AI tools. I direct AI collaborators.

01
StrategistContent & Voice

Reads the brief. Finds the argument. Sets the voice the team builds from.

02
DesignerVisual Design & Prototype

Every token, every motion curve, every layout decision. Validated and held.

03
BuilderProduction Engineering

Living spec to running code — held to the design, with drift caught rather than tolerated.

04
ReviewerIndependent check

A second model that doesn't share the first one's assumptions. Reads the work cold and says what's wrong with it before anything ships.

The gap

AI is everywhere as a topic. Governing it is something else.

Describing where AI design is headed is the easy part. The discipline is in the decisions you make when the first approach doesn’t work — under a real brief, a real constraint, a real person with expectations.

I’ve built the longer version of this — not because I had to, but because I wanted to know what it actually takes. The answer is: a method. Not a model.

“The method is what makes the product repeatable.”
Our team
Dave WatersDirector
StrategistContent & Voice
DesignerVisual Design & Prototype
BuilderProduction Engineering
ReviewerIndependent check

Same team, start to finish — from the first alignment conversation to the last commit.

The outcome

What this method produces isn’t theory.

A working codebase built to specification, with every decision traceable back to a brief. A multi-role AI experience running in two worlds. It handles the same question asked four different ways and produces a consistent result — because consistency was designed in from the start.

My role is the one no AI fills: the person who knows when a pass is good enough to ship, when it needs to go back, and why. The working discipline is mine. The team executes it.

The door

Trust drives AI adoption.
A governed system earns it.

Thirty minutes, live. I’ll drive — banking, a hospital floor, or operations, your call. You’ll watch it take one question and hand back the finished thing — a built view, a drafted report, an action ready for your approval — shaped to whoever’s asking, across everything they’re cleared to see. Then you’ll see the guardrail: when the data can’t carry a call, it won’t fake one.