Skip to content

Structured Study, Synthetic Conversation, or Causal Experiment: Which One Answers Your Decision

A pricing, packaging, positioning, or launch decision usually gets routed to whichever AI-assisted research tool is open, not the tool that answers the question. That routing mistake is expensive: a team runs a structured study or a synthetic conversation, gets a confident answer, ships on it, and discovers after launch that what people said didn't predict what they did.

Three different questions, three different tools

Before picking a platform, name the question being asked. Three shapes come up repeatedly in consumer and B2B research:

The first two produce stated preference: what a respondent or persona says they'd do. The third produces a causal estimate: which alternative, tested against the others under controlled conditions, moves a defined behavioral outcome. Conflating the three is how a team ends up with a well-organized study or a fluent transcript that still can't say which option to ship.

Where stated preference breaks down

Stated-preference methods, structured or conversational, share the same limit: self-reported interest isn't revealed choice. Recent research testing whether large language models can reproduce human purchase intent found they approximate stated survey responses well: evidence that a structured study and a synthetic-persona conversation measure the same thing, what respondents say, not what they do (LLMs Reproduce Human Purchase Intent via Semantic Similarity Elicitation of Likert Ratings, arXiv). A plausible synthetic conversation or a well-designed opinion study can both replicate the say-do gap instead of closing it, in a faster interface.

Discrete choice experiments exist for this reason. Rather than asking someone to rate or describe a preference, they present controlled trade-offs and infer preference weights from the choices made, a method with a long track record in health and consumer economics (Discrete Choice Model and Analysis, Columbia University Mailman School of Public Health; The use of discrete choice experiments in applied economic analysis, Oxera). The distinction that matters: does the platform ask people what they prefer, or observe which option they choose under controlled, comparable conditions?

Comparison at a glance

Method shapeWhat it producesFits best whenWhere it runs out of road
Structured stated-preference studyRatings or rankings against a fixed protocolStakeholders expect a study-report deliverable and the question maps cleanly onto a survey-and-respondent modelDoesn't isolate which change drives behavior; no built-in comparison group
Open-ended synthetic conversationFree-form persona responses to a promptEarly-stage discovery, hypothesis generation, exploring how a segment talks about a conceptStill stated preference; a fluent answer isn't evidence the choice would hold under real trade-offs
Controlled causal experimentAn estimate of which action moves a defined outcome, with a comparison conditionDeciding between shortlisted prices, messages, or concepts before a launch or spend commitmentNot built for open-ended discovery or large-scale structured data collection on its own

How Subconscious tests the causal question

Subconscious is a causal behavioral platform: it runs controlled experiments on a simulated population and estimates which action moves a decision-specific outcome, rather than eliciting opinions or generating persona conversation. That's the third shape above, not a faster version of the first two. Our best configuration reaches 87% of the measured human ceiling on one study: 0.832 rank correlation against the published human result, where two independent samples of real humans reach 0.959. Across all 43 studies that pass design filters the mean is 0.73 (the causal fidelity paper). It is a validation result, not a guarantee for a new market.

Subconscious can also test or validate studies with real human participants, so a team can move from a simulated experiment to a real-human check without redesigning the study.

Limitations

Subconscious doesn't replace open-ended qualitative discovery, multi-persona panel conversation, or structured survey research outright: those remain legitimate methods for different questions, particularly early-stage discovery. The fidelity figures only mean something attached to their definition and a specific study comparison; they're not a blanket accuracy guarantee. Confidence intervals and segment-level heterogeneity are outputs of a specific study design, not standard features of every study.

Matching the method to the decision

Three questions decide which tool fits:

  1. Is the question about what people say, or which option they'd choose? If the answer only needs to describe attitudes or generate ideas, a structured study or open-ended synthetic conversation is the right shape.
  2. Does the decision carry real downside if stated preference doesn't hold up? A pricing, packaging, or launch call with real spend behind it is where the say-do gap gets expensive, and where a controlled causal comparison earns its cost.
  3. Do you need to compare several alternatives, or just understand one? Comparing which of several prices or messages moves behavior needs random assignment and a comparison condition; understanding how one segment feels about one idea doesn't.

Where the decision is real and reversible mistakes are costly, run the causal comparison before the spend, not after the launch.

Branching path from three question shapes to their matching methods: structured study, synthetic conversation, and controlled causal experiment, the only one producing a causal estimate.
Only the action-shaped question, routed to a controlled experiment, tells you which change moves the outcome.

Explore how the method works, see it applied in the research library or the leaderboard, or book time to walk through a live experiment.