Simulations

A simulation is a complete run of your content through a crowd of AI agents. This guide covers creating and configuring a run. When the crowd finishes you get a synthesis report. A stopped or failed run has no report.

Creating a Simulation

Every simulation starts with seed content, the stimulus. On a running crowd, simulated people react to it. Go to /sim/new to begin.

Seed Types

CrowdProof supports three ways to provide seed content:

Text

Raw text like a tweet, press release, product description, or announcement. This is the most flexible option. On a running crowd, simulated people react to the text.

We are excited to announce that starting next month, our premium plan will include unlimited API access at no additional cost.

URL

A link to a public page. CrowdProof reads up to the first three links before the run starts, so the crowd can react to what those pages say. A page it cannot fetch, and any extra link, stays as URL text. The report says which pages were read. Useful for testing landing pages, articles, or competitor announcements.

https://example.com/blog/product-launch

Scenario

A hypothetical situation described in third person. This is ideal for testing "what if" questions or competitor moves.

Apple announces that the next iPhone will not include a charging port, requiring all charging to be done wirelessly.

Audience Selection

Choose which crowd should react to your content. Each is an authored mix of archetypes. Pick the one closest to the crowd you want.

See Audiences for detailed archetype lists.

Configuration Options

Agent Count

The number of AI agents participating in the simulation. Larger crowds take longer.

• 100 agents: Free first-run size. Camps still form; larger crowds reduce faction noise.
• 250 agents: Pro size. More voices than a Free first run; less faction noise.
• 500 agents: Pro cap. More voices than a Free first run.
• 2,000 agents: Team cap. More voices than a Free first run.
• 5,000 agents: Enterprise cap. More voices than a Free first run.

Simulation Rounds

Each round lets agents read and react to each other. On a running crowd, more rounds let opinions evolve and camps form. A pending, finished, failed, or stopped run is not live.

• 5 rounds: Minimum. On a running crowd, first takes can land. A pending, finished, failed, or stopped run is not live.
• 10 rounds: On a running crowd, early camps can form. A pending, finished, failed, or stopped run is not live.
• 20 rounds: Pro size. More rounds than a Free first run, which is capped at 10.
• 30+ rounds: Team and Enterprise. On a running crowd, debate can extend. A pending, finished, failed, or stopped run is not live.

Running a Simulation

Click Launch Simulation to enter God Mode. On a running crowd, agents begin reacting. A pending, finished, failed, or stopped run is not live. Or Launch A/B Experiment to open the dashboard so you can compare both variants when they finish. A Free first run is 100 people and up to 10 rounds. Larger crowds take longer. On a running crowd, watch in God Mode. When the crowd finishes you get a report. A stopped or failed run has no report.

On a running crowd you can pause, inject events, or let it run to completion. A pending, finished, failed, or stopped run cannot pause or inject. See God Mode for interface details.

The Synthesis Report

When the crowd finishes you get a synthesis report. A stopped or failed run has no report. Here is how to read each section:

Overall Sentiment

A summary of whether reactions landed positive, negative, mixed, or divided. A crowd that split into opposing camps reads Divided, matching the report. Mixed is a crowd that stayed near the middle. This is the quick answer: how did people react?

Faction Breakdown

A card per faction showing camps that formed, when any did, each with its share of the crowd, average sentiment, and a representative quote. Look for:

• Dominant faction: The largest camp, when any did. A pending run has no camps yet.
• Opposition size: How large a negative camp is, when any did. A pending run has no camps yet.
• Curious/Pragmatic: A curious or pragmatic camp, when any did. A pending run has no camps yet.

Key Arguments

The strongest points for and against, when any did.

Viral Moments

Posts that went viral after engagement spikes, when any did.

Notable Quotes

Quoted reactions from individual agents, when any did.

Sharing Reports

Share Report copies a public link. While the crowd is running, a colleague watches the live spectator feed. When the run finishes, the same link opens the report. A stopped or failed run has no report. You can also:

• When the crowd finishes, download the report as Markdown. A stopped or failed run has no report.
• Export the raw feed as CSV when the crowd has posted. A paused, stopped, or failed run with posts can too. Survey CSV is for collected responses.
• On Enterprise, scoped keys create, retrieve, and export. Live stream and inject stay in God Mode.

Running Follow-up Simulations

When the crowd finishes you can review the report. Run a Variant draws a fresh crowd. A stopped or failed run has no report.

• A/B testing: On Team and Enterprise, turn on the A/B test toggle in the wizard and enter Variant B. Both versions then react to one shared crowd, follow network, and activity schedule. Two separate launches with the same audience each draw their own crowd, so part of every gap is sampling noise.
• Different audiences: A second launch with another preset draws a fresh crowd. Part of every gap is sampling noise.
• Refined messaging: When the crowd finishes, refine the message against objections in the report. A stopped or failed run has no report.

Next Steps

• Audiences - Audience presets, agent archetypes, and the OCEAN personality model
• API Reference - On Enterprise, scoped keys create, retrieve, and export