In a former shop on Ginnekenstraat, a pedestrian street in the Dutch city of Breda, you can answer a short questionnaire about yourself and walk out less than an hour later holding a perfume that did not exist when you arrived.
The questions are not the ones a sales assistant asks. What colour best represents you. Where would you go right now, if you could go anywhere at all. How would you describe your style.
You answer, a set of algorithms reads your replies, and a machine in the room composes a scent to match, the bottle filled and labelled while you wait.
The company that built the room is called Scentronix, and for the better part of a decade it has argued that the way the world buys perfume is stranger than we admit.
The đź’ś of EU tech
The latest rumblings from the EU tech scene, a story from our wise ol’ founder Boris, and some questionable AI art. It’s free, every week, in your inbox. Sign up now!
Its founders, the Dutch artist and filmmaker Frederik Duerinck and the scent designer Anahita Mekanik, like to frame the strangeness as a question: why should roughly 800 people decide how 8 billion humans smell?
They mean the small guild of master perfumers, the noses, who compose nearly every fragrance on nearly every shelf.
It is a provocation, and like the best provocations it carries a real idea inside it. For most of its history, perfume has been a closed art, beautiful and remote. Software is quietly prising it open.
That kind of sentence tends to make people flinch, because we have been trained to expect the worst when code turns up in a craft built on human hands.
The fear is usually some version of replacement: the algorithm arrives, the artist is shown the door. In perfume, that is not what is happening, and the more closely you look at who is actually building these tools, the more the opposite case takes shape.
The largest names in the business reached the same conclusion years ago. In 2019, the German fragrance house Symrise paired its perfumers with an artificial intelligence system it had built alongside IBM Research and named Philyra, a name drawn from Greek myth.
Philyra had been trained on a vast archive of formulas and performance data, and it could suggest pairings no person would reach for, unburdened by habit or taste.
Working beside it, the Symrise perfumer David Apel composed two fragrances for the Brazilian brand O Boticário, released as the Egeo line in time for the country’s Valentine’s Day.
They were, by most accounts, the first AI-formulated perfumes to go on sale anywhere.
Others followed with machines of their own. Givaudan, the biggest fragrance house in the world, developed Carto, a touchscreen system that lays out a formula as a visual map and feeds it to a robot that mixes a physical sample in seconds, so a perfumer can test an idea almost as quickly as they can have it.
Calice Becker, who created Dior’s J’adore and runs Givaudan’s perfumery school, has said the point of the tool is to let perfumers dare, to try combinations that would never have been obvious choices.
Firmenich, now part of DSM-Firmenich, aimed in the other direction with Scentmate, a service built to help small brands and solo entrepreneurs, the people with no laboratory and no in-house nose, create a fragrance at all.
Not everyone is charmed, and the dissent deserves to be taken seriously. Jean-Claude Ellena, the former in-house perfumer at Hermès and one of the most admired noses alive, has argued that a machine cannot read the thoughts that guide a perfumer through a composition.
He has said, with some sadness, that he pities the junior perfumer who will one day be handed a machine’s draft and asked to perfect it.
Coming from a man who treats perfume as a form of literature, the objection lands. There is a real risk that automation flattens a craft into a workflow, that the strange, intuitive leaps get optimised away.
But the worry assumes a contest, human against machine, and that is not what these tools are. Every one of them keeps the perfumer in the room.
Symrise calls Philyra an apprentice, not a replacement, and appears to mean it. Carto puts the formula on a screen, and a person still decides what is beautiful.
Even Scentronix, the most automated of the lot, routes roughly one customer in 50 to a human perfumer to fix whatever the algorithm has misjudged. The software widens the canvas. It does not sign the painting.
Underneath the commerce, something genuinely new is taking shape, and it is the part that should interest anyone who cares about technology as much as perfume.
Smell is the sense that has always resisted the machine. We taught computers to see and to hear decades ago, but odour, a chaos of molecules binding to receptors in ways we still only partly understand, stayed stubbornly analogue.
That is changing. Researchers at Google have trained neural networks to predict how a molecule will smell from its structure alone, a first rough sketch of a machine nose.
A European project called Odeuropa has used AI to recover the lost scents of historical Europe from centuries of text. Perfume is simply the most commercial edge of a much larger effort to give software a sense it has never had.
The market all of this lands in is large and quietly conservative. Industry estimates put global fragrance sales at around $60bn a year, a business still shaped by a handful of houses, a rotation of celebrity licences, and the same few hundred noses deciding what the rest of us wear.
Set against that, a system that lets a teenager in a pop-up shop, or a small brand with no money for a laboratory, make something that smells like them and only them is not a threat.
It is an enlargement. The pie does not shrink when more people are allowed to bake.
Which returns us to the shop in Breda. The machine there does not know what your perfume ought to smell like.
It knows only what you told it, and it is honest about the gap, which is why a human is kept on hand for the moments when you and the algorithm disagree.
What it offers is not a verdict but an invitation, a chance to treat the oldest and most intimate of the senses as something you compose rather than something you choose from a shelf.
You walk in as a customer. You walk out, an hour later, holding a small bottle that smells like an answer to a question only you were asked, and that did not exist anywhere in the world when you woke that morning.
