All Topics
All Topics
Technology
Technology
Design
Design
Programming
Programming
Science
Science
News
News
Gaming
Gaming
Entertainment
Entertainment
Business
Business
Finance
Finance
Sports
Sports
Health
Health
Food
Food
Travel
Travel
Art
Art
Music
Music
Books
Books
Education
Education
Politics
Politics
Personal
Personal
No algorithm. No AI slop. No ads. Just RSS. Pro-human. Indie writers. Real journalism. Open web. Chronological. Hand toasted.

Parastore: Open-source 3D retail simulation with LLM-powered synthetic consumers for product testing

By

KYEONGEOP LIM

4d ago· 1 min readenProduct

Summary

Parastore is an open-source (MIT) 3D retail simulation platform where LLM-powered synthetic consumers physically walk through virtual stores, browse shelves, make purchase decisions, and generate revenue data. Developed by Intellicia, it features 12 behavioral patterns, grammar-constrained actions, randomized context (mood, budget, company), and impulse-buy logic. The simulation has been validated against real POS data with a 0.955 Spearman correlation. Built with Python/FastAPI and React/Three.js, it supports any LLM backend and is designed to help brands test products and messaging without traditional surveys.

Key quotes

· 3 pulled
Instead of answering surveys, our synthetic consumers now physically walk through stores.
They browse, pick up items, impulse-buy snacks near the checkout, and generate revenue data — all in a 3D simulation.
We're open-sourcing the entire simulation framework (MIT license) because we believe agent-based behavioral simulation
Snippet from the RSS feed
Parastore is an open-source (MIT) retail simulation where LLM-powered synthetic consumers walk through a 3D virtual store, browse shelves, and make purchase decisions. Each consumer follows one of 12 behavioral patterns with grammar-constrained actions, r

You might also wanna read