Overview

Civic competence—the ability to navigate disagreement, weigh values, and reach collective decisions—is a learned skill, not an innate trait. But opportunities to practice are scarce. Citizens’ assemblies and deliberative polls reach only a small fraction of the population.

Agora addresses this gap by creating a training ground for building consensus.

First, an AI interviewer conducts voice interviews with ninety American workers about their experiences and beliefs on a contentious topic: the ideal minimum wage. These interviews serve as source data for an LLM to predict how each interviewee might respond to different minimum wage policies. Predictions (which comparative evaluations found to be 85% accurate to interviewee beliefs) are always cited using verbatim voice clips from the original interviews.

The result is a simulated, but deeply human, population with which users can test their ability to find consensus.

Users write a policy about the minimum wage (e.g., “Raise the minimum wage to $25 an hour”). Each interviewee is represented as an anonymized avatar, positioned along a spectrum based on their predicted level of support. Clicking an avatar reveals a dynamically curated voice clip from their interview, along with a summary explaining their perspective. As users revise the policy, the system updates support predictions in real time, shifting avatars and generating new explanations.

The result is an interactive feedback loop where users iteratively refine their ideas while listening to the lived experiences behind different positions. By encouraging engagement with both others’ views and the reasoning behind them, Agora supports the perspective-taking and empathy essential to civic competence.