This note argues for a structured architecture to manage knowledge in systems with human and AI participants, suggesting implications for cognitive organization.
Version 2. Updated structure and clarifications. This version supersedes v1.A research programme involving multiple human and AI participants faces a structural problem: how does the system know what it knows? This note argues the answer requires an architecture — a structured agent configuration (multilogue), an operational logic for managing divergence (isomorphism of CDSA and orchestration), and a stratified memory system (epistemological stack). All three components operate by the same schema.
No takes yet. Share an insight, caveat, or question.
Roman Kir (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: