Interpretable Context Methodology: Folder Structure as Agentic Architecture
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912972013568000 |
|---|---|
| author | Van Clief, Jake McDermott, David |
| author_facet | Van Clief, Jake McDermott, David |
| contents | 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 filesystem structure. Numbered folders represent stages. Plain markdown files carry the prompts and context that tell a single AI agent what role to play at each step. Local scripts handle the mechanical work that does not need AI at all. The result is a system where one agent, reading the right files at the right moment, does the work that would otherwise require a multi-agent framework. This approach applies ideas from Unix pipeline design, modular decomposition, multi-pass compilation, and literate programming to the specific problem of structuring context for AI agents. The protocol is open source under the MIT license. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_16021 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Interpretable Context Methodology: Folder Structure as Agentic Architecture Van Clief, Jake McDermott, David Artificial Intelligence Human-Computer Interaction H.5.2; D.2.11; I.2.1 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 filesystem structure. Numbered folders represent stages. Plain markdown files carry the prompts and context that tell a single AI agent what role to play at each step. Local scripts handle the mechanical work that does not need AI at all. The result is a system where one agent, reading the right files at the right moment, does the work that would otherwise require a multi-agent framework. This approach applies ideas from Unix pipeline design, modular decomposition, multi-pass compilation, and literate programming to the specific problem of structuring context for AI agents. The protocol is open source under the MIT license. |
| title | Interpretable Context Methodology: Folder Structure as Agentic Architecture |
| topic | Artificial Intelligence Human-Computer Interaction H.5.2; D.2.11; I.2.1 |
| url | https://arxiv.org/abs/2603.16021 |