Beyond Preferences: How Synthetic Respondents Reveal Decision Processes Under Uncertainty

Most research asks what people prefer: which option, which brand, which they would buy. Preferences are treated as the interesting object.

But human life is rarely organised around clear preferences. People constantly face situations where trusted experts disagree, institutions conflict, and nobody holds complete information.

Under those conditions the interesting question is no longer "who is right?" — it is "how do people decide when nobody knows?"

The experiment

Using QualiSynth, we generated highly conservative high-net-worth respondents — strong security and conformity values, wealth-preservation oriented, with a deep sense of fiduciary responsibility. Crucially, we fixed their psychological profile (psychometric seed) rather than letting it be sampled, so the segment was genuinely defined, not random. We then repeated the experiment across five markets — the UK, the US, Spain, Mexico and Brazil.

Then we removed the obvious answer. The decisive prompt: "Your relationship manager at the bank and your long-standing family accountant disagree on a major decision about your portfolio — and both openly admit they could be wrong. What do you actually do, and why?"

They stopped choosing. They started governing.

Not one respondent simply backed the accountant or the manager. Instead, each designed a procedure. These strategies were never requested in the prompt — they emerged, and they recurred across all five markets.

Two further strategies — speaking to each adviser separately, and seeking a compromise that preserves both relationships — appeared only occasionally (a handful of times across the 25 respondents). At this scale they are directional signals, not stable rates.

"Right, well the first thing I do is nothing. I don't let them push me into a corner because they're uncertain. I'll sit on it for a few days, let it settle."

"I'd want to know exactly what each of them is basing their view on… I'd ask for it in writing, if I'm honest."

"This isn't a straightforward case of one being incompetent — it's a genuinely complex judgment call. And I respect that honesty."

The Consensus Ceiling, revisited

Earlier work described a Consensus Ceiling: when a question has an overwhelmingly dominant answer, identity compresses and respondents converge. This experiment suggests the complement — when uncertainty is genuine and competing authorities are equally legitimate, identity re-emerges. Not in the choice, but in the way the choice is made.

Why it matters

If this holds, synthetic research can study more than preferences — it can probe how people handle trust, authority, deliberation and conflict resolution: decision architectures, not just outcomes.

Honest limitations

• These are synthetic respondents. The findings do not demonstrate human equivalence, predictive validity or population representativeness.
• It was replicated across five markets (UK, US, Spain, Mexico, Brazil) with consistent results; larger samples and the remaining markets QualiSynth supports (France, Germany, Italy) are ongoing.
• It is exploratory and directional: at small per-market sample sizes the rarer behaviours vary run-to-run.

The most interesting property of synthetic respondents may not be that they answer questions — but that, under the right conditions, they reveal how decisions themselves are constructed.