fleet: 6 agents · evo-x2 ⇄ macbook0.04% err

The Levels of AI Orchestration

L0 to L7 — what the human actually does at each rung, how I work there, and where I honestly sit. Scroll to climb.

Lineage

This ladder stands on prior art. Those frameworks measure a system's autonomy. This one measures a different axis — how much of the loop the human still occupies, and what they built to hand the rest away.

youmodel
L0

Chat / copy-paste

Open a model in a browser tab; paste code in, paste the answer back.

I kept a tab open and moved text by hand. The editor had no idea the model existed. I climbed past this the moment the model could see my files instead of my clipboard.

L1

Autocomplete & approve-each-step

Inline suggestions you accept or reject; an agent that asks before every action.

The model shortened my keystrokes but I still drove every one of them. Every action waited on my approval. Useful — and not yet orchestration.

L2

One autonomous agent, supervised

Hand an agent a whole task; let it edit, run, and iterate while you watch.

I gave an agent a task and let it run — intervening on drift, not approving each step. The unit of my attention became the task, not the keystroke.

L3

A few parallel agents

Two or three sessions at once; context-switch between them, reviewing and unblocking.

My scarce resource stopped being typing and became attention. I ran a few sessions in parallel and moved between them — the first time the work outran one cursor.

L4

Multi-machine fleet, away-from-keyboard

Many agents across machines, controllable remotely. You route, prioritize, resolve conflicts.

Agents across a Linux box and a remote Mac, driven over Tailscale. Air-traffic control, not typing — and the work keeps moving when I step away from the desk.

L5you are here

Platform-builder

Engineer the substrate the fleet runs on — gates, coordination, telemetry, independent review.

This is where I actually sit. I build the substrate the fleet runs on: hooks that gate on real exit codes, cross-machine file locks, telemetry that records everything, and an independent reviewer drawn from a different model family so its blind spots aren't mine. The substrate is the work; the agents are what runs on it.

  • 38.9k tool calls
  • 0.04% tool-call error rate
  • 476 autonomous subagents
  • different model family reviewer
L6🔒 not lived yet

Autonomy-platform owner

The control plane becomes something other people can trust and operate.

Locked — toggle “preview the gap” to read it.

L7🔒 not lived yet

Recursive / self-directing

The system improves its own orchestration; humans set objectives and constraints.

Locked — toggle “preview the gap” to read it.