Ask the Oracle Before You Decide : Simulating the Future with LLM Agents

Pythia is an LLM-powered simulation engine that models how individual cognitive biases and crowd psychology interact to shape real-world decisions, before those decisions are made.

For the demo: you give it a scenario (a market move, a policy choice, a personal decision under pressure), and it spins up a cast of behaviorally-distinct AI agents, each carrying a named bias like Loss Aversion, FOMO Drive, or Anchoring and drops them into a live crowd field. You watch opinion dynamics unfold tick by tick. At a critical moment, one agent is sent to the Temple of Learning: their behavior is evaluated, their rules are amended, and they re-enter the simulation.
Run over run, the system gets more accurate. The visualization shows all of it : the crowd state, the agent trajectories, the oracle’s intervention, the improving accuracy curve.