Proposes a protocol that replaces complex multi-agent coding frameworks with a simple, interpretable filesystem structure.
March 18, 2026
Original Paper
Interpretable Context Methodology: Folder Structure as Agentic Architecture
arXiv · 2603.16021
The Takeaway
By using numbered folders and markdown files as 'agentic architecture,' this method drastically reduces the engineering overhead of building sequential AI workflows. It prioritizes human-readability and Unix-style modularity over opaque, framework-heavy orchestration.
From the abstract
Current approaches to AI agent orchestration typically involve building multi-agent frameworks that manage context passing, memory, error handling, and step coordination through code. These frameworks work well for complex, concurrent systems. But for sequential workflows where a human reviews output at each step, they introduce engineering overhead that the problem does not require. This paper presents Model Workspace Protocol (MWP), a method that replaces framework-level orchestration with fil