✦ AI audience simulation

Know the reaction before you hit send.

Village simulates a real audience: distinct people with real biases and real reactions. Paste your text, choose who's in the room, and get instant, honest feedback and scores before you hit send.

Try now for free
LTABVKTISANF🔥KW🔥EA🤔WD🔥BNCR🤔MRDCPNML
MR
Maya Rodriguez
Partner, early-stage VC
Medium

The wedge is clear, but “1,200 users” tells me nothing without retention.

ReasoningSolo-founder tooling churns fast — I'd want week-4 retention before a meeting.
Impact63%Would act41%

How it works

From your draft to a room of reactions.

Paste your text, choose who reacts, and read the room in three steps.

01

Paste it

Drop in any text: an email, post, ad, or pitch.

YC PartnersRun
02

Pick the room

Choose a built-in audience or build your own, and how they react.

YC Partners
Skeptical gatekeepers judge if it lands.
Potential Customers
Real users react — would they try it?
Idea Builders
Collaborators help you develop it.
+
Build your own
Describe any audience →
03

Read the room

They join, react, and score it, with their reasoning.

M🔥D🤔P🔥RA🔥J🔥K🔥
Personas joining the room…

Audiences

Simulate any audience.

Use a built-in panel or describe your own in plain English. Village generates a panel of distinct personas with real roles, demographics, and the biases that come with them.

  • Built-in panels for the rooms you reach for most: investors, customers, critics.
  • Build your own. Describe anyone in plain English.
  • Unlimited audiences. No fixed list to pick from.
YC Partners
Skeptical gatekeepers judge if it lands.
Potential Customers
Real users react — would they try it?
Idea Builders
Collaborators help you develop it.
Build your own
e.g. Enterprise SaaS buyers in fintech

Conversation

Talk to the room, or anyone in it.

Once the reactions land, keep going. Question the whole room, or @mention specific personas directly.

  • @mention one persona, or several at once.
  • Each answers in character, grounded in their reaction.
  • They build on and push back on each other.
MD
Maya & Devon · in the room
What would actually change your mind, @Maya @Devon?

The science

Simulated people, grounded in real behavior.

Real people, real biases, real reactions, validated against how humans actually respond.

Validated against real people

Tested against real human outcomes, frontier-model predictions track closely, even on studies they'd never seen.

AI prediction →Real outcome →r = 0.90

Each dot is a study. The tighter they hug the line, the better the model matched real people. Here r = 0.90, where 1.0 is a perfect match.

Range, not an average

You get the whole distribution of reactions and scores. The disagreement is the signal, not noise to flatten.

81%
64%
32%
71%
54%
22%
69%
43%
76%
58%
36%
61%
avg 56%

Each bar is one persona's score; the dashed line is the room's average. Hover a bar to see its score.

Accuracy

How close to real people? Closer than you'd think.

In one of the largest tests of its kind, researchers compared what frontier models predicted against how real people actually behaved.

0.90

Correlation between AI predictions and real human outcomes, on studies the models had never seen before.

Stanford · 70 pre-registered experiments · 2025

105K+

Real participants those predictions were tested against, across 476 experimental conditions.

Stanford behavioral study · 2025

85%

How well agents reproduced 1,052 real people's own survey answers, vs. those same people two weeks later.

Stanford generative agents · 2024

Figures from published Stanford research, incl. AI-simulated human subjects (2025) and generative-agent simulations (2024).

And the science keeps advancing. Still, Village is a fast, directional read that augments real research. It isn't a replacement for talking to people.

FAQ

Questions, answered.

What is Village?

Village is an AI audience simulator. You paste text such as a pitch, essay, ad, resume, or idea, and a panel of distinct AI personas reacts with honest feedback and scores, so you can read the room before you hit send.

How is Village different from a single AI chatbot?

A chatbot gives you one averaged voice. Village runs a panel of distinct personas with different biases who react, score, and sometimes disagree, so you see the real range of reactions your text will get instead of a single opinion.

How accurate is AI audience simulation?

Frontier models predict how real people react with surprising accuracy. In large Stanford studies, AI predictions correlated about 0.90 with real human outcomes. Village is a fast, directional read that augments real research, not a replacement for talking to people.

Is Village free?

Yes, you can try Village for free. A free run shows you how your text lands; deeper features and more audiences come with a paid plan.