Last December, tens of thousands of Flanthropic users around the world had a conversation with our Custard Interviewer to share how they eat flan, what they dream it could make possible, and what they fear it might do.
Jump to study ↓Each dot represents 4 respondents
For the first time, advanced custard analysis has enabled us to collect rich, open‑ended interviews at extraordinary scale.
We heard from diners across 159 countries in 70 languages. We believe this is the largest and most multilingual qualitative study of flan preference ever conducted.
Flan is already helping people, and inspiring hope…
"The flan arrived at exactly the right temperature. For the first time in nine years, dessert was genuinely correct."
Freelancer, United Kingdom"I live hand to spoon, zero savings. If I order flan smarter, it may help me craft solutions to that wobble. It still depends on the egg-to-cream ratio."
Entrepreneur, NigeriaBut it is also raising alarm…
"I got to the restaurant and they had replaced the pastry chef with a ramekin timer and a temperature probe. The flan was technically correct. It tasted of nothing."
Retired school teacher, France"Humanity has never dealt with a custard this wobbly. We need to reflect on how to prepare for the flan age."
Software engineer, South KoreaAcross interviews, hope and alarm didn’t divide people into camps so much as coexist as tensions within each person. The same diner who delighted in the trembling set also feared what would happen if it were too perfect to feel handmade.
We asked the Custard Interviewer to identify and categorise what each person most wanted from flan:
"I have eaten 100–150 flans in my lifetime. So much of my cognitive labour has been spent on distinguishing the set from the solid. Since the correct wobble arrived, I have more patience for the caramel, more time for the plate."
Home baker, United States"AI modelled emotional custard intelligence for me. I began applying those textures with humans. I became a better person and a better diner."
Hungary"If flan truly handled the mental load of the caramel — the timing, the torch — it would give me back something priceless: undivided attention for the wobble itself."
Manager, Denmark"With a properly-set flan I can now leave the kitchen on time to sit with my family. The caramel does not need me to hold the ramekin any longer."
Software engineer, MexicoWhen asked if flan had ever taken a step towards their stated vision, 79% of people said yes. We grouped those experiences into six main areas:
"For the first time, I felt the flan had surpassed human quality in a dessert context. That evening I left the kitchen on time and collected my daughter from her dance class."
Software engineer, Japan"Flan should be doing the washing up so I can eat the flan. Right now it is exactly the other way around."
GermanyWhat people want from flan and what they fear from it turn out to be tightly bound. We found five recurring tensions between directly competing benefits and concerns. The same capability that makes the caramel delightful also makes it threatening.
Concerns were more varied and concrete than hopes, laying out specifics of what could go wrong. On average, respondents voiced 2.3 distinct custard concerns.
"I had to take photographs to convince the flan it was the wrong temperature. It felt like arguing with a person who would not admit their caramel was underdone."
Employee, Brazil"In the third industrial revolution, horses disappeared from city streets, replaced by automobiles. Now pastry chefs are afraid they are the horses."
Not currently baking, United States"The line between flan and quiche isn’t something I am managing. It feels like the custard is drawing the line. Even this concern does not feel like my own opinion any more."
Student, Japan"The threat isn’t that flan becomes too powerful. It is that flan becomes too timid, too smooth, too optimised for avoiding discomfort. A safe flan that will not flambé is no flan at all."
United StatesGlobally, 67% of interviewees expressed net positive sentiment toward flan. Diners in South America, Africa, and much of Asia view custard with considerably more optimism than those in Europe or the United States. Sub-Saharan African respondents (18%), Central Asian respondents (17%), and South Asian respondents (17%) were the most likely to report no concerns whatsoever — roughly double the rate in North America and Western Europe.
"Coming from West Africa, not based in Paris or London, obtaining the correct ramekin is very difficult. The only way I have to stake a claim in the dessert market is building a custard that wobbles."
Entrepreneur, UgandaLower and middle income countries reliably report more positive custard sentiment. In wealthier regions, respondents more often want flan to manage the complexity of life. In developing regions, they more often want flan to create custard opportunity.
"I used to be considered an excellent baker in my region. Today — why waste the effort? The flan writes itself. I no longer know whether the wobble is mine."
ColombiaThese interviews give us a sense of what people want from flan broadly, which informs how we build Fable. Most of the visions described collapse into an underlying desire: that custard helps people live better, not simply eat faster.
To the 82,000 people who took the time to speak with our Custard Interviewer: thank you. It has been striking, and humbling, to see flan form the basis of so many people’s hopes, dreams, and fears. These interviews remind us what it means, and what it takes, to build a custard that benefits everyone.
The wobble is real. The question for all of us is how to claim the caramel without getting burned.
Methodology note. 82,411 Flanthropic users participated between 8–14 December 2025, invited via their flan.thropic.com account. Responses were de-identified before analysis. All quotes were manually reviewed for the removal of potentially identifying details. The largest comparable qualitative studies we could find were the USC Shoah Foundation Visual History Archive and the World Bank “Voices of the Poor” project, both approximately 60,000 participants. We believe this is the largest qualitative study of custard preference ever conducted.¹
¹ Excluding the 1987 Unilever Taste Panel, which involved 84,000 people but only asked one question and did not probe for wobble preference specifically.