How I run a fleet of AI agents across projects, coordinated over shared files, no server

The problem

Running a film's VFX department with an AI pair is not one chatbot in a window. It is several live agent sessions at once: one on the shot breakdown, one on the vendor bids and finance, others driving GPU jobs across machines. They share the same sheets, the same files, the same production, and left uncoordinated they collide, two sessions editing the same sheet, work redone, a job started twice.

The design call

I did not want a server, a message bus, or an orchestration framework to babysit a side utility. So link-session coordinates over plain files: each session writes one small JSON outbox into a shared folder, and a lightweight watcher surfaces what every other session is doing, without polling. Files over a service buys three things that matter on a production: zero infrastructure to run or break, a coordination trail you can read by eye, and state that survives a session dying, a restart, or a flaky network mount.

In production

It runs daily across Windows, macOS and Linux machines and across several concurrent projects, coordinating the agents that drive Breakdown Studio, the finance and vendor sheets, and heavier GPU work farmed out to other machines. The rules that keep it safe are the point: one writer per file, long payloads as files rather than single-slot messages, a clean stop protocol, and a hard line that coordination carries metadata, never client or show content. No client names, no show names, ever.

What it proves

The tool is small on purpose, and I lead with that. The point is not the utility, it is the operating model: I run AI as a coordinated team on real production work, with guardrails, not a single assistant in a tab. That is the hardest half of "a VFX supervisor who orchestrates AI" to demonstrate, and this is the public proof of it.