Most developers think of a folder tree as a way to organize files.
For AI systems, it can be much more than that.
The Interpret-able Context Methodology (ICM), also known as the Model Workspace Protocol (MWP), introduced by Jake Van Clief and David McDermott, explores how structured project workspaces can improve AI reasoning and navigation.
My article explores this idea further and introduces MWP-Tool, an experimental visualization layer that transforms a repository into a navigable terrain map. The objective is to help AI agents and developers discover context through project structure instead of relying solely on larger prompts or increasingly complex retrieval systems.
If the repository already contains hierarchy, relationships, and intent, perhaps the folder tree itself is one of the most valuable context artifacts we have.
mwp-tool repository