A research instrument for generating realistic multi-character conversations using isolated sub-agents under a method-actor architecture.

Each experiment is a single dialogue scene. The 4-window viewer shows what each actor was thinking (private) and saying (public) in real time, alongside the coordinator's routing log and the clean transcript. See README.md for the project shape, or methodology/ for the design rationale.

The pilots above surfaced four classes of failure: cross-perspective word leakage, named-technique over-deployment in thinking, third-person POV slips, and locked-fact violations in thinking. The profile, scene, and orchestration methodologies, the actor system prompt, and the audit procedure were rewritten. The experiments below run under the revised framework.