SYNTHETIC AUDIENCE RESEARCH PLATFORM

Audience research at the speed of the decision.

Census-grounded synthetic panels of 20 to 1,000 respondents deliver moderated qualitative findings in minutes. Every study begins with a structured research brief and ends with an evidence-cited executive summary. Methodology published.

NO PAYMENT CARD REQUIRED · FIRST FIVE STUDIES COMPLIMENTARY

THE RESEARCH CATALOG
METHODOLOGY

Four methodological principles distinguish synthetic audience research from general-purpose LLM prompting. All four are instrumented on every study.

RESPONDENTS

Census-grounded OCEAN panels.

Respondents are sampled from published demographic distributions (US ACS 2023, UK ONS 2021, AU ABS 2021). Big Five personality traits are drawn from Rentfrow 2008 (US states) and Schmitt 2007 (cross-cultural). Each persona is persistent across studies.

MODERATION

Protocol-driven intake.

Every study begins with a structured research brief — decision, success criteria, evaluation dimensions, target audience — produced by a senior-moderator model and reviewable by the researcher before the instrument is fielded.

OBSERVATION

Native multimodal stimulus.

Video creative is observed via Gemini 2.5 and Qwen-VL native inference. No transcript proxies. A strategy-panel layer reviews from the brief for analytic diversity alongside the respondent panel.

TRANSPARENCY

Transparent degradation.

Respondents whose observation channel fails mid-study are excluded from the verdict set. Role composition, degradation reasons, and literal-read risk are disclosed on every report.

READ THE FULL METHODOLOGY PAPER

ENGAGEMENT PRICING

Priced per study. First five studies complimentary. Volume and enterprise agreements available on request. Traditional qualitative panels are referenced for context, not substitution.

Opinion instruments

Pulse

$0.30

PER STUDY, 20 RESPONDENTS

  • ·20 – 1,000 respondents per study
  • ·Sentiment distribution, demographic crosstabs, verbatim excerpts
  • ·Independent vote, moderated debate, and A/B instruments
  • ·Report export (PDF)
Field a Pulse study

STANDARD

Creative evaluation studies

Screening Room — Balanced Insight

$0.99

PER STUDY

  • ·150 respondents, native multimodal observation
  • ·Protocol-driven moderator intake and research brief
  • ·Strategy-panel analyst layer (senior-analyst lens)
  • ·Executive summary, ranked leaderboard, respondent quotes
Commission a study

High-stakes creative decisions

Screening Room — Deep Review

$4.99

PER STUDY

  • ·400 respondents, six expert analytic lenses
  • ·Three-round moderated debate round
  • ·Extended executive summary with strategic implications
  • ·Ten post-study follow-up questions included
Commission a Deep Review

QUICK PULSE SCREENING INSTRUMENT · $0.19 · 35 RESPONDENTS · FOR EARLY-STAGE HYPOTHESIS TESTING

ACCOUNT PLANS

Studies are metered against a prepaid wallet. Account plans modify the per-call rate and unlock larger panels. The Screening Room is available on every plan; panel size and API access are what change.

PAY-AS-YOU-GO

Free

$0

PAY-AS-YOU-GO

  • ·$5 welcome credit on signup
  • ·Pulse panels up to 50 respondents
  • ·All Screening Room tiers available
  • ·Full PAYG metered rate
Open an account

RECOMMENDED

PER MONTH

Pro

$25

PER MONTH

  • ·$25 monthly wallet credit
  • ·15% discount on all metered usage
  • ·Pulse panels up to 750 respondents
  • ·Developer API access
Subscribe to Pro

PER MONTH

Enterprise

$100

PER MONTH

  • ·$100 monthly wallet credit
  • ·25% discount on all metered usage
  • ·Pulse panels up to 2,000 respondents
  • ·Invoicing and custom audience segments
Subscribe to Enterprise
METHODOLOGY FAQ

How does this differ from prompting a general LLM?

Each respondent is a persistent persona sampled from census distributions — OCEAN traits, occupation, life stage, media diet — with a demographic identity that survives across studies. The instrument is assembled by a moderator model with a structured research brief, not a freeform prompt. Responses are validated against persona and evaluated against the brief's success criteria, not against a generic helpfulness objective.

How does synthetic respondent data compare to human panels?

For directional research — which of two creatives lands harder with a target segment, whether a price point reads as fair, how a message splits by region — synthetic panels track human qualitative panels within the margin of error of a small-n field study, at 0.01–0.1% of the cost. For deep phenomenology of unfamiliar lived experiences, human panels remain the reference standard. The platform flags when a study falls into the latter category.

What is the data-handling posture for uploaded creative?

Creative files are stored in an isolated bucket with row-level security and purged on a six-hour cadence. Uploaded material is not used for model training. Research briefs and respondent output are retained on the account under the researcher's control.

Can audience definitions be customized?

Yes. Twenty-seven demographic presets ship by default (US general, Gen Z, UK metro, AU metro, tech early-adopters, category-specific segments). Custom audience definitions are available via the developer API and enterprise engagements.

Make creative decisions on evidence.

Field your first study in thirty seconds. Methodology and sample reports available on request.

Commission a study →