The Misses Behind the Patterns

If you want to know how I think before the call, this is the fastest way. Four essays, each opening on a real moment a product I worked on lost — or kept — a user’s trust. All four are about the same half-second: the pause before a professional acts on a correct answer. The Patterns library is the reference version of the same ideas: the do’s, don’ts, and demos. This is the story behind them.

The four essays

Adoption · AdTech

The Model Was Right. I Fixed the Wrong Thing.

A recommendation engine that beat the traders it was built for — and sat unused. Two weeks lost to the wrong suspect, and the handover change that moved adoption without touching the model.

Essay →
Failure States · Due Diligence

Design the Failure State First

A model that demoed beautifully and became a coin-flip on real deal data. Why the happy path is the smaller half of the job, and the failure state is where trust is won or lost.

Essay →
Explainability · FinTech

The Explainability Layer: Making AI Legible

A compliance officer asked one question the system couldn’t answer — and a trade went through unsupervised. Why “why this, not that?” is a design problem, not a data-science one.

Essay →
Human-in-the-Loop · EdTech

Human-in-the-Loop: When to Ask, When to Override

An accurate recommender that students skipped anyway — out of click fatigue, not disagreement. When asking for confirmation stops respecting the user and starts taxing them.

Essay →

Shorter pieces, on Substack

Read more on Substack ↗

The Prompt I Paste Before Every Single Prototype

September 2, 2026 · Read on Substack ↗

Nobody Reads Your Portfolio. Fifteen Strangers Skim It.

August 29, 2026 · Read on Substack ↗

The Agentic MVP: Why Your Next Launch Will Be Lovable, Not Just Viable

May 20, 2026 · Read on Substack ↗