How we build a synthetic person.
Teaching a computer to react the way a real group of customers would — so a brand can test a campaign before spending money sending it to millions.
What is a "synthetic person"?
Imagine a focus group you can assemble in seconds, ask anything, and never have to pay or tire out. That's the idea.
We build a small set of computer "people" that react to a message — an email, an SMS, a WhatsApp — the way a real group of your customers would. A brand can then see which version of a message lands best before sending the real thing to millions.
The golden rule: it's a crowd, not one person
A group of customers is never one type of person. Some are bargain-hunters, some are loyal fans, some are about to leave. So we never build a single "average" customer — we build a small crowd of the real types, in the same mix as your real audience.
If you build one "average" customer, you lose the disagreement that actually decides whether a campaign works — the bargain-hunter and the loyal fan want opposite things. A crowd keeps that tension.
When you ask an AI to be "the average person," it tends to make everyone sound the same and hides the real spread of opinions. Researchers measured this directly and warned against it — so we deliberately keep the crowd diverse.
What we feed it (the data)
A synthetic person is only as real as what we build it from. Three kinds of information, from least to most useful:
- Who they are — age, city, the basics. Useful background, but on its own it's just a stereotype.
- What they do — what they open, click, and buy; which products they like; which channel they prefer. This is the most important.
- What they say — their reviews, their messages to support, their words. This is what makes them sound human, not robotic.
Why "what they do" matters most: when this was tested on 2,000 real online stores, synthetic customers built from generic descriptions barely worked — but synthetic customers built from each store's real shopping behaviour predicted the winning options well.
How we turn that data into a personality
- Pick the exact group — e.g. "big-city shoppers who haven't bought in 3 months."
- Find the types inside it — the computer sorts that group into a few patterns, like bargain-hunter, loyal fan, and drifting away.
- Give each type a short life story and a few "dials" — how much they love a deal, how loyal they are, which channel they like. The dials come straight from their real behaviour.
- Make a small crowd of them — in the same proportions as your real audience.
- Let them react — show them the campaign and see what they think.
How we make them talk naturally
We don't ask a synthetic person to "rate this 1 to 5" — that turns out to be unreliable. Instead we ask, "What do you think of this?" and read the feeling in their answer.
A study run with Colgate showed that asking an AI for a number gives poor results — but reading the words of its answer matches real people about 90% as well as real people match themselves. So we read words, not numbers.
How we know it's real — not made up
This is the part most people skip, and it's the most important one.
Before we trust a synthetic person, we test it: we ask it about things the real group has already done, and check whether it gets them right. If it doesn't match reality, we don't use it. A confident-sounding answer that's wrong is worse than no answer.
Why we always work with groups and test them: copying one specific individual is still weak — a 2025 Columbia study found a computer "twin" of a single person matched that person only loosely. But predicting a whole group is far more reliable. So we stay at the group level and prove it against real outcomes.
What it's good for — and what it isn't
✓ Good at
"Which of these 5 subject lines will my customers like most?"
Ranking options, spotting likely winners and losers, and explaining why.
✗ Not good at
"This will get exactly 4.2% clicks."
Exact numbers. We never promise those.
Why: AIs are reliably good at saying which option is better, but unreliable at the exact number. So we use them to rank and screen — keep the likely winners, drop the likely losers — and let the real campaign confirm the precise numbers.
The numbers, in plain English
If someone walks you through this work, a few statistics show up. Here's what each one actually means — no maths needed.
The whole idea in one line: build a small crowd from real data, let them react in their own words, and never trust them until they've been tested against reality.
This describes AI simulations built from data — useful stand-ins for testing, not real people, and not a crystal ball. Predictions can be wrong and should be confirmed with a real test before any big decision.