This paper proposes a user-interface-driven architecture for multi-user Play-by-Online (PBM) systems in which narrative generation and probabilistic resolution are strictly separated. All rule-based judgment and randomization are executed exclusively on the user side, while AI services provide only narrative generation, translation, and suggestion. This architecture preserves authentic tabletop role-playing dynamics while enabling scalable AI-assisted PBM environments. This document is a conceptual design paper intended to share UI composition, data flow, and architectural design philosophy, rather than an implementation case study. The content is based on the author's original design concepts. AI tools were used solely as auxiliary editing and writing assistance. This record is an English-language edition of the following Japanese version:DOI: 10.5281/zenodo.18405037
kurato (Sun,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: