Millions of simulated people online

Ask millions of people first.

AI-native decision research with cited market evidence, simulated audiences, structured interviews, and explicit uncertainty.

link · idea · prd · question

no demo call · first study free · evidence and uncertainty included

Why it's different

A panel you can question and audit.

Crowdproof connects simulated audience reactions, structured interviews, cited market context, and uncertainty in one inspectable research record.

Interview them

simulated

Miguel ReyesSkeptics

41 · Toronto ON · UX lead · agent #112,406

“The pricing page buried the per-seat math. I closed the tab there.”

What would change your mind?
“A calculator with my headcount, and the overage policy in plain words.”

stratified interviews · transcripts attached in full

Trace the evidence

auditable

evidence map · pricing · segment comparison · cited sources

Follow a finding back to its simulated respondents, segment differences, interview evidence, and cited market sources.

provenance labels · transcripts · citations · uncertainty

study typesFlagship launch simulationMessage testPricing studyMarket scanConcept screen

How it works

One question in. One sim-week out.

Every study produces an inspectable research process: market evidence, simulated responses, interviews, and a decision report.

Ask

Type a question or paste a link, idea, or PRD. Crowdproof researches the market context, frames the decision, and briefs the simulated society.

Simulate

Target a cohort by age, gender, race, region, income, or education. You can also let the audience emerge from 1,000,000 census-seeded agents. Launch studies diffuse through six simulated social channels.

Observe & interview

Agents react through simulated social channels, answer structured surveys, and join stratified simulated interviews.

Decide

You get a funnel with uncertainty ranges, churn reasons ranked by segment, and every transcript attached.

Run #213 · pricing page v2

Simulating

Research market evidence

cited public sources

Seed society

1,000,000 agents · ACS-2024

Simulate diffusion

72 sim-hours · 6 channels

Run simulated interviews

structured by segment

Interview cohorts

stratified · n = 128

Build funnel report

P10–P90 across 9 seeds

seed 42 · ACS-2024 · SIR-social v2.3
CI: bootstrap, 10K resamples

The output

A funnel, not a vibe.

Reach → engaged → tried → retained: a count of simulated people at every stage, the drops between stages with ranked reasons, and uncertainty shown directly on the chart.

run #213 · pricing page v2 · n = 1,000,000 · 72 sim-hoursP10–P90 across 9 seeds

reach

412K± 18K

−156K · −38%never engaged: one mention, no second touch

engaged

256K± 14K

−116K · −45%skeptics exit at the per-seat pricing table

tried

140K± 11K

−66K · −47%no clear win inside the first session

retained

74K± 9K

h0 → h72 · retained = 18.0% of reach

simulated · bootstrap CIs, 10K resamples · churn reasons from 128 attached interviews

Methodology & honesty

Simulated evidence, labeled as such.

Every artifact carries its provenance. simulated for interviews, surveys, and modeled outcomes; cited sources for external evidence. Nothing here pretends to be a human.

society1M agents seeded from US census (ACS-2024): age, gender, race/ethnicity, region, education, occupation, income, media diet. Target a cohort (up to 1,000 per study) or let the audience emerge. Every report shows the cohort composition.

evidenceMarket claims are grounded in cited public sources. Simulated responses and derived findings remain clearly labeled.

interviewsStratified across segments; transcripts attached in full, never summarized away.

seeds & rangesEvery study executes across multiple seeds. We report P10–P90 ranges, not point estimates. A wide range means the result remains uncertain, and the report says so.

Read the methodology →methodology v2.3 · changelog public

retained % · 9 seeds · run #213

10%18%26%

reported: 18.0% (P10 14.2 – P90 22.4)

Pricing

Meter by depth, not by seats.

Credits track real model usage across cited research, simulated audience work, interviews, scenario analysis, and report generation. New accounts receive 1,000 credits.

market evidence · cited→+ simulated audience · modeled→+ interviews · structured→+ decision report · actionable

Traditional research

$20k–$60k/study

4–8 weeks per study

The manual route, through an agency or DIY: recruiting, panels, moderation, synthesis.

·Audience survey $6k–$15k

·Eight 1:1 interviews $4k–$12k

·Any iteration starts the clock again

for comparison only

Most common

Starter

$19/mo

1,500 credits / mo

For one researcher or PM validating a roadmap.

·Cited market research

·Simulated interviews

·Decision reports

Start Starter

Pro

$49/mo

4,500 credits / mo

For continuous, deeper testing.

·Deeper research runs

·Audience segmentation

·Continued follow-up

Start Pro

Business

$199/mo

22,000 credits / mo

For teams running continuous decision research.

·High-volume research

·Scenario analysis

·Priority capacity

Start Business

traditional range = typical published U.S. agency & panel rates, shown for comparison only · every plan reports P10–P90 ranges and full methodology · honesty is not a paid feature

FAQ

Questions, answered plainly.

Directionally, at funnel scale. We backtest against launches and campaigns with known outcomes and publish the calibration report quarterly. We do not claim to predict individuals. We test whether the funnel shape, leak points, and segment rankings hold up. The ranges show where uncertainty remains.

Crowdproof combines cited public market evidence with explicitly simulated audience research, structured simulated interviews, and scenario analysis. The report keeps those evidence classes separate.

No. Crowdproof replaces participant recruitment and conventional interviews with a census-shaped synthetic panel, so teams can make product, pricing, positioning, and promotion decisions in one workflow. Every interview remains explicitly labeled simulated, with the agent ID and model version attached.

Study time depends on the question, research depth, evidence availability, and model execution. Crowdproof shows progress from actual completed work rather than promising a fixed completion time.

Crowdproof provides conversation deletion and isolates tenant research data. Consult the current privacy policy for the exact retention, subprocessors, model-training, backup, and deletion boundaries.

The report still names the best-supported option, shows the uncertainty band, and tells you what would narrow it: more seeds, a deeper pipeline stage, or a tighter cohort. You get a decision, its confidence, and the business signals that should trigger an adjustment.