Sophy

is an experimental scent device designed to deliver adaptive, AI-generated aroma compositions using a set of physical cartridges.
I led the entire product design effort: from brand and mobile UX to hardware interface logic, working closely with AI engineers, industrial designers and the founder.

Outcomes

The product was acquired by Symrise AG — a leading global fragrance supplier — at the functional prototype stage.

Working scent diffuser prototype in final design

Adaptive control app

Core AI model

Patent filings and branding

Problem

There was no reference point — scent as an interactive digital medium had no UX conventions. The core challenges:

How do users understand and control invisible, ambient stimuli?

How to avoid smell fatigue from repeated aromas?

How to personalize scent in a meaningful, engaging way?

Goal

Create a flexible system that gives users agency over scent while integrating intelligent automation.

Research

We began by designing a physical scent album of 24 base aroma families. Through a custom-built mobile companion app, we collected user preferences and emotional associations with each scent. This data was used to:

Build individual olfactory profiles

Train a base AI model to generate custom scent cycles

Avoid repeated exposure through adaptive sequencing

Solution

The mobile interface provided both manual and automated control of the scent experience.

Visual scent families, organized around emotions and energy

Real-time control of active blends (what's diffusing now)

Presets & smart playlists, generated by AI or linked to mood

Automation editor — triggers based on time of day, light, sound or user presence

Outcomes

The product was acquired by Symrise AG — a leading global fragrance supplier — at the functional prototype stage.

Working scent diffuser prototype in final design

Adaptive control app

Core AI model

Patent filings and branding