How it works
From variants to verdict in hours.
Cars are designed in crash simulation and confirmed with one physical test. Chips are simulated before a single one is manufactured. A campaign is the same shape: a study, productised. Here is what running it first looks like for your creative.
Upload your variants
Two to five creative concepts: paid social ads, donation appeals, brand campaigns. Finished or rough — if you could show it to a focus group, you can show it to us. Tell us who the campaign is for: demographic, market, intent.
Your audience responds, synthetically
We run your creative against thousands of simulated respondents matched to, and trained on, your actual target demographic. Nobody performs for a moderator. Nobody misrepresents who they are to qualify for the session. The respondents who matter are in the room, because we build the room.
Get the winner and the why
A ranked prediction with dimension-level scores and the reasoning behind them — language you can take into a creative review and defend. Delivered in hours, not weeks.
The report
What lands in your inbox
Not a 60-slide readout six weeks later. A decision-ready answer.
The predicted winner
A clear head-to-head verdict across your variants, not a mush of "directional findings."
Dimension scores
How each variant performs on attention, clarity, emotional response, and intent for your audience.
The reasoning
Why the winner wins, in plain language. The argument you bring to the room when the senior director disagrees.
A validation path
A recommended A/B design to confirm the prediction in market whenever you want to check us.
For teams
The 90-day validation pilot
For brands that want proof on their own campaigns, not someone else's case study.
- 3–5 creative concepts — tested against synthetic audiences matched to your target demographic.
- A/B test designed in from day one — so the prediction is checked against real in-market performance.
- Outcome metric agreed up front — campaign revenue or conversion rate against a held-out control — defined before the test starts, not after.
- 90 days, fixed scope — a defined engagement, not an open-ended research retainer.
FAQ
The questions marketers actually ask
How do I know the predictions are accurate?
We validate against reality. A multi-national charity ran our prediction against a live A/B test — our pick generated 13.5% more donation revenue. Every pilot includes an A/B test with a success metric agreed before we start.
Is this a survey panel?
No. There are no recruited panelists, no gift cards, no incentive games. Your creative is tested against AI-simulated respondents matched to and trained on your actual target demographic.
What do you need from us?
Your creative variants and a description of your target audience. That is enough for a head-to-head test. For pilots, we also agree on the outcome metric up front.
How fast are results?
Hours. A focus group takes 3–6 weeks. A properly powered A/B test takes 1–4 weeks and burns media budget on the losing variant while it runs.
What does it cost?
The head-to-head ad test is free. Structured pilots are scoped to your campaign and priced as a fraction of one properly powered A/B test. Talk to us.
Can it test more than ads?
Ad creative is what we have validated with live revenue results, so it is where we start. Packaging and new product concept testing are in early access with select brands.
Put it to the test
Run the study before you run the campaign.
A campaign is a study you pay for in media. We run it first, against a simulated audience, then structure a pilot with live A/B validation built in and a success metric agreed up front. We win when the prediction holds.