How do you design for

How do you design for someone who is already panicking?

It's March. Summer looks thin. A charter operator is staring at empty August weeks, and every instinct says: drop the price, now. Some of those weeks would have filled anyway. Nobody knows which ones — and that's the whole problem.

I've been designing Bonaca — a revenue-decision copilot for professional yacht charter fleets. It reads bookings, seasonality and competitor pricing, then tells the operator when to hold a price and when to let it go — with the reasoning shown. The operator always decides.

No client, no brief. I started with a market I know — Croatian charter, where a boat books sixteen weeks out of fifty-two — and designed backwards from the worst moment of the operator's year.

Three decisions define the product:

→ Confidence is never a percentage. It's a sea state — a calm line, a ripple, chop. Read instantly, like water. → The crisis screen is the calmest screen. No red, no alarms. A scared user needs clarity, not urgency. → The system admits when it was wrong — and says what it cost. Trust is built in November, not in March.

A tool that misleads someone once doesn't get opened twice. That was the entire design brief.

And if you're building a product where a user has to trust an expensive call — an AI copilot, a fintech tool, anything high-stakes — this is exactly the kind of problem I take on. Let's talk.