In an old shop on Ginnekenstraat, a pedestrian street in the Dutch city of Breda, you can answer a short questionnaire about yourself and leave less than an hour later with a perfume that didn’t exist when you arrived.
The questions are not what a sales assistant asks. What color represents you best? Where would you go right now, if you could go anywhere? How would you describe your style?
You answer, a set of algorithms reads your answers and a machine in the room composes a matching scent, the bottle is filled and labeled while you wait.
The company that built the room is called. Scentronixand for almost a decade it has been argued that the way the world buys perfumes is stranger than we admit.
The 💜 of EU technology
The latest rumors from the EU tech scene, a story from our wise founder Boris and some questionable AI art. It’s free, every week, in your inbox. Register now!
Its founders, Dutch artist and filmmaker Frederik Duerinck and scent designer Anahita Mekanik, like to pose this strangeness as a question: why should some 800 people decide how 8 billion human beings smell?
They refer to the small guild of master perfumers, the noses, who make up almost every fragrance on almost every shelf.
It is a provocation and, like the best provocations, it carries within it a real idea. For most of its history, perfume has been a closed, beautiful and remote art. The software is opening it silently.
That kind of phrase tends to make people cringe, because we’ve been trained to expect the worst when a code appears on a ship built with human hands.
Fear is usually some version of replacement: the algorithm arrives, the artist is shown the door. In the case of perfume, that is not what is happening, and the closer you look at who is actually building these tools, the more the opposite case becomes apparent.
The biggest names in the industry came to the same conclusion years ago. In 2019, German fragrance house Symrise paired its perfumers with an artificial intelligence system it had built with IBM Research and called Filiraa name taken from Greek myth.
Philyra had been trained with a vast archive of formulas and performance data, and could suggest combinations that no person would choose, unburdened by habit or taste.
Along with him, Symrise perfumer David Apel composed two fragrances for Brazilian brand O Boticário, launched as the Egeo line in time for Valentine’s Day in the country.
They were, by most accounts, the first AI-formulated perfumes to go on sale anywhere.
Others followed with their own machines. Givaudan, the world’s largest fragrance house, developed Carto, a touch-screen system that presents a formula as a visual map and sends it to a robot that mixes a physical sample in seconds, so a perfumer can test an idea almost as quickly as he can come up with it.
Calice Becker, who created Dior’s J’adore and heads the Givaudan school of perfumery, has said the goal of the tool is to allow perfumers to be daring, to try combinations that would never have been obvious choices.
Firmenich, now part of DSM-Firmenich, pointed in the other direction with Scentmate, a service created to help small brands and individual entrepreneurs, people without a laboratory or internal sense of smell, create a fragrance.
Not everyone is delighted and dissent deserves to be taken seriously. Jean-Claude Ellena, former Hermès in-house perfumer and one of the world’s most admired noses, has argued that a machine cannot read the thoughts that guide a perfumer through a composition.
He has said, with some sadness, that he feels sorry for the young perfumer who will one day be given the draft of a machine and asked to perfect it.
Coming from a man who treats perfume as a form of literature, the objection arises. There is a real risk that automation will turn a craft into a workflow, that strange, intuitive leaps will be streamlined.
But worry involves a competition between humans and machines, and those tools are not that. Each of them keeps the perfumer in the room.
Symrise calls Philyra an apprentice, not a replacement, and seems to mean it. Carto puts the formula on a screen and a person still decides what is beautiful.
Even Scentronix, the most automated of them all, directs about one in 50 customers to a human perfumer to fix any mistakes the algorithm has judged. The software expands the canvas. He does not sign the painting.
Beneath the commerce, something genuinely new is taking shape, and it’s the part that should interest anyone who cares as much about technology as they do perfume.
Smell is the sense that has always resisted the machine. We taught computers to see and hear decades ago, but smell, a mess of molecules that bind to receptors in ways we still only partially understand, remained stubbornly analog.
That is changing. Google researchers have trained neural networks to predict what a molecule will smell like Only from its structure does a first sketch of the nose of a machine emerge.
A European project called Odeuropa has used AI to recover the lost aromas of historical Europe of centuries of text. The perfume is simply the most commercial advantage of a much larger effort to give software a meaning it has never had.
The market that all this reaches is large and discreetly conservative. Industry estimates put global fragrance sales at around $60 billion a year, a business still shaped by a handful of houses, a turnover of celebrity licenses and the same hundreds of noses who decide what the rest of us wear.
In contrast, a system that allows a teenager in a temporary store, or a small brand without money for a laboratory, to make something that smells like them and only they are not a threat.
It is an extension. The cake does not shrink when more people are allowed to bake.
Which brings us back to the Breda store. The machine doesn’t know what your perfume should smell like.
It only knows what you told it and is honest about the gap, which is why a human is kept available for times when you and the algorithm disagree.
What it offers is not a verdict but an invitation, an opportunity to treat the oldest, most intimate meaning as something you compose and not something you choose from a shelf.
You enter as a customer. You emerge, an hour later, holding a small bottle that smells like the answer to a question that was only asked of you, and that didn’t exist anywhere in the world when you woke up that morning.
