BRYAN V.B. NEE-DARKO PRODUCT DESIGN HUMAN & AGENT INTERACTION
I don’t stop at the slide. I build the thing — deployed, testable.
Three projects. Each one answers the same question in a different domain: where does a person stay in the loop, and where has an agent earned the right to act alone? Two of them are running. One is in a closed test, and it says so.
SELECTED WORK THREE CASES
THE LENS
Autonomy isn’t a feature. It’s a design decision about authority
When I design a system that works alongside people, my first question isn’t what it can do. It’s what it’s allowed to do. What can it observe, what can it recommend, and what can it act on by itself? What stays a human call? And is that line just suggested by the interface, or built into the system so nobody crosses it by accident?
ONE AXIS
Observe
→
Recommend
→
Act
The system watches and surfaces patterns.
It proposes, a person decides.
It executes on its own, inside limits someone set.
A PERSON DECIDES
THE SYSTEM ACTS
IN CLOSING
This page is the argument
A deck can describe an interaction model. It cannot be operated. Everything on this page that claims to work can be used right now — open any frame in the series. Nothing is a screenshot of something that exists elsewhere.
The same standard applies to what isn’t finished. One of these three is still in a closed test. It says so at the top, not in a footnote.
HOW I WORK
On my own, I hold the whole chain — framing the problem, designing the system, building it. In my professional work, I design complex B2B and enterprise products together with product, engineering, business and international delivery teams. Both are how I work: taking an unclear idea to something you can use, and developing complex products inside an organisation where that chain is shared.
REACH ME
Say hi.
Next.js, TypeScript, Tailwind. Statically rendered, no backend. Set in IBM Plex Sans and IBM Plex Mono. Built and audited against WCAG 2.2 AA.
BRYAN V.B. NEE-DARKO PRODUCT DESIGN HUMAN & AGENT INTERACTION
I don’t stop at the slide. I build the thing — deployed, testable.
Three projects. Each one answers the same question in a different domain: where does a person stay in the loop, and where has an agent earned the right to act alone? Two of them are running. One is in a closed test, and it says so.
SELECTED WORK THREE CASES
THE LENS
Autonomy isn’t a feature. It’s a design decision about authority
When I design a system that works alongside people, my first question isn’t what it can do. It’s what it’s allowed to do. What can it observe, what can it recommend, and what can it act on by itself? What stays a human call? And is that line just suggested by the interface, or built into the system so nobody crosses it by accident?
ONE AXIS
Observe
The system watches and surfaces patterns.
↓
Recommend
It proposes, a person decides.
↓
Act
It executes on its own, inside limits someone set.
A PERSON DECIDES
THE SYSTEM ACTS
IN CLOSING
This page is the argument
A deck can describe an interaction model. It cannot be operated. Everything on this page that claims to work can be used right now — open any frame in the series. Nothing is a screenshot of something that exists elsewhere.
The same standard applies to what isn’t finished. One of these three is still in a closed test. It says so at the top, not in a footnote.
HOW I WORK
On my own, I hold the whole chain — framing the problem, designing the system, building it. In my professional work, I design complex B2B and enterprise products together with product, engineering, business and international delivery teams. Both are how I work: taking an unclear idea to something you can use, and developing complex products inside an organisation where that chain is shared.
REACH ME
Say hi.
Next.js, TypeScript, Tailwind. Statically rendered, no backend. Set in IBM Plex Sans and IBM Plex Mono. Built and audited against WCAG 2.2 AA.