Generative agent simulations offer transformative potential for computational social science (CSS); however, the requirement for sophisticated programming expertise limits their adoption to technical specialists, excluding many domain experts. This paper presents a web-based, open-source platform that democratizes access to the Concordia framework through an intuitive, no-code interface. The system allows researchers to configure, execute, and analyze multi-agent simulations without writing code, bridging the gap between domain expertise and technical implementation. Key technical contributions include a robust reliability layer designed to sustain long-running simulations, incorporating automatic checkpointing and timeout protection to mitigate the external LLM API instability inherent in extended execution times. Additionally, the system features a provider-agnostic adapter supporting both major commercial model APIs and locally hosted models. The platform further streamlines research workflows through configurable game master templates (generic, game-theoretic, questionnaire-based) and automated LLM-powered analysis tools. We evaluate the system across diverse scenarios and discuss the trade-offs between this web interface and the native Concordia Python framework. By eliminating programming barriers while preserving advanced simulation capabilities, this tool serves as both an accessible entry point for non-technical researchers and a rapid prototyping environment for experts.
Ng S. T. Chong (Fri,) studied this question.