{"id":692,"date":"2026-03-08T10:00:00","date_gmt":"2026-03-08T09:00:00","guid":{"rendered":"https:\/\/neurostratum.com\/?p=692"},"modified":"2026-05-14T11:55:42","modified_gmt":"2026-05-14T09:55:42","slug":"chaos-to-cartographer","status":"publish","type":"post","link":"https:\/\/neurostratum.com\/index.php\/en\/2026\/03\/08\/chaos-to-cartographer\/","title":{"rendered":"From Chaos to Cartographer: I Handed My Files Over to an AI"},"content":{"rendered":"\n
\n\n
\n

NeuroStratum Projects<\/a><\/p>\n

By Jp@NeuroStratum — Originally published in French on March 8, 2026<\/p>\n<\/div>\n\n

\n

Summary<\/em> — Claude Cowork organizes your files, connects them, and builds a navigable knowledge network. After three weeks, six iterations, and 551 files, I forged six specialized agents that work as a pipeline. This new edition adds The Cartographer<\/em> and The Weaver<\/em> — knowledge mapping and Obsidian-style backlinks. The full v4.1 guide, with the six ready-to-use prompts, is in the resources, along with an interactive demo of The Cartographer<\/em> — an HTML file you can open in your browser to see the connection network in action.<\/p>\n

\u23f1 Estimated reading time: 5 minutes<\/p>\n<\/div>\n\n

\n

Your files are no longer sorted — they’re connected.<\/p>\n<\/blockquote>\n\n

— New edition: six agents, mapping, and backlinks —<\/p>\n\n

This post has grown. The first version told the story of four prompts and 55 files. This one has six, a knowledge network, and 551 files sifted through. If you read the first version, you’re about to discover a pipeline that has changed dimension.<\/p>\n\n

You know the document is somewhere. You downloaded it three weeks ago — or maybe six. You dig through Downloads. 847 files stare back at you in silence. You end up downloading the file again, promising yourself that this time, you’ll tidy up.<\/p>\n\n

You won’t. No one tidies up. Until the day someone else can do it for you — and better than that: connect your files so you can find them by meaning, not only by name.<\/p>\n\n

Cowork: From Advice to Action<\/h2>\n\n

You know Claude’s chat: it advises, analyzes, writes. Cowork is something else. A desktop agent that accesses your files, opens them, reads them, moves them, and renames them. The difference between an architect drawing plans and a mason laying bricks. Except this mason understands the plan. It opens your PDF, identifies that it’s about prompt engineering, and files it accordingly. Striking — but it does nothing without your green light.<\/p>\n\n

First Steps: The Missteps That Changed Everything<\/h2>\n\n

My first instinct? A vague prompt: « organize this folder. » Claude charged in headfirst. It treated a CSV and its XLSX equivalent as duplicates (wrongly), invented a different naming pattern for each file, and acted before showing me its plan. Three immediate lessons: define what counts as a duplicate, impose a naming convention, and require a report before action. Briefing an AI agent is briefing a co-worker — the quality of the deliverable depends on the quality of the briefing.<\/p>\n\n

Six Iterations to Forge the Right Prompt<\/h2>\n\n

The final prompt didn’t materialize out of thin air. Six successive versions, each born from a problem encountered under real conditions. V1 laid the foundations. V2 clarified that different formats aren’t duplicates: throwing away a CSV because you have the XLSX is like throwing away a screwdriver because you own a hammer. V3 introduced hash verification. V4 added EXIF for images. V5 brought media and documents together. And V6 — the turning point — split the processing into two distinct passes, because Claude lost precision when it tried to analyze everything at once.<\/p>\n\n

This prompt wasn’t designed; it was forged. Each adjustment came from the field, not from theory.<\/p>\n\n

Six Agents, One Pipeline — The Great Evolution<\/h2>\n\n

The first version of this post stopped here: four agents, a linear pipeline. But the project kept growing. When a member of the community showed me Obsidian — its backlinks, its graph view, its fluid navigation — the question wasn’t whether to adopt the tool, but how to transplant its principles. Connect rather than sort. The result: two additional agents, and a pipeline whose nature changed.<\/p>\n\n

The Sorter<\/strong> does the initial heavy lifting in two passes: pass 1 for media, a fast and mechanical triage; pass 2 for documents, with deep reading and thematic renaming.<\/p>\n\n

The Scout<\/strong> audits the file tree after sorting. It uncovers redundant folders, misplaced files, and hidden duplicates. Prioritized report, zero action.<\/p>\n\n

The Harmonizer<\/strong> executes your decisions: merges, cleanups, consistent renaming. Report, validation, action, traceability log.<\/p>\n\n

The Observer<\/strong> is the image specialist: thematic sorting enriched by EXIF metadata.<\/p>\n\n

The Cartographer<\/strong> is the agent that changes the game. It reads each file, identifies themes, and weaves a knowledge network: Markdown files by theme, weighted connection JSON, interactive HTML prototype. 27 themes, more than a thousand connections, four view modes. Your files are no longer sorted — they’re connected.<\/p>\n\n

The Weaver<\/strong> completes the picture by injecting bidirectional backlinks into each thematic note. Format [[moc-name]]<\/code>, compatible with Obsidian’s MOC — Map of Content — convention. 132 backlinks across 27 notes, zero content files touched.<\/p>\n\n

The pipeline puts the human at the center. Cowork executes; the human decides. That’s the key.<\/p>\n\n

From 55 to 551 Files: The Crash Test<\/h2>\n\n

First test: 55 files, 17 subfolders. The Scout<\/em> uncovers four groups of overlaps, one hidden duplicate, one orphan .docx. The Harmonizer<\/em> produces 43 renamings. Two requested adjustments; integrated. Impeccable result.<\/p>\n\n

Then the real test: my full AI folder. 551 files, 100 subfolders, one year of accumulation. Final count: 523 files, 84 folders, unified convention, zero real loss. Eighteen duplicates removed by hash. And The Cartographer<\/em> transformed this file tree into a navigable network — a prototype where each file has as many contexts as it has shared themes.<\/p>\n\n

Seeing to Understand: The Interactive Demo<\/h2>\n\n

Words aren’t enough to describe what The Cartographer<\/em> produces — you have to see it. I’ve included a demo version of the HTML prototype in the resources. One file, no installation: you download it, open it in your browser, and navigate the connection network of my 325 files. Four view modes, a density slider to filter weak links, statistics by theme. Spin the graph, click a node, explore. This is the moment when a frozen file tree becomes a living landscape.<\/p>\n\n

The Traps<\/h2>\n\n

Cowork on Windows is still finding its footing. In three weeks: server errors — restart and carry on — a virtualization wall and ten minutes of configuration, plus long sessions that strain the token budget. Nothing fatal, on one condition: always work on copies, never on originals. And for The Observer<\/em>, process images in batches of 10 to 15 — visual analysis is resource-intensive, and beyond that, precision drops.<\/p>\n\n

The Takeaway<\/h2>\n\n

A vague prompt produces a vague result. A forged prompt — six iterations, separate passes, imposed conventions, reports before action — produces professional work. And when you add mapping, sorting your files is no longer enough: you understand them.<\/p>\n\n

I wrote an 11-chapter reference guide — new edition v4.1, with the six copy-and-paste prompts, the 551-file case study, knowledge mapping, and the roadmap toward Obsidian. The guide and The Cartographer<\/em> HTML demo are in the community resources.<\/p>\n\n

If your hard drive looks like mine did before this adventure — an archaeological site where each layer tells the story of a forgotten project — the solution has grown since last time. Six agents, a thousand connections, a knowledge network. And it’s only waiting for your prompt.<\/p>\n\n

Experiment conducted from February to March 2026 in collaboration with Claude (Anthropic). Reproducible methodology — your feedback will help refine it.<\/p>\n\n

\n\n

Written with the support of AI to help organize thoughts and shape language.<\/p>\n

Jp@NeuroStratum<\/p>\n\n

For Further Reading<\/h2>\n\n