Fleet Manager · Product Direction + Execution Plan
The services spine exists. The product — the shell, the cockpit, the wiring a non-expert operates cold — is unplanned. This is what it should be, and the lanes that build it.
The bar is a control room, not a config panel: you see the whole fleet's state at a glance, watch its work stream in real time, and command it — start, stop, restart — without a terminal. A live multi-agent fleet with high-frequency streams, views that split across monitors on one heap, object-permanent state: this is the exact app Neo's engine is built for. Done right it's the flagship demo. Done as it is now, it undercuts the whole story.
Static direction mock — the cockpit's default view. Click an agent → its thought-stream, lane, repo, and PRs; drag it out → its own OS window on the same heap.
Status is encoded in form, not just text — a colored pulse, a family rail, a one-line "what it's doing now." You know the fleet's health before you read a word.
The activity feed and every status is live — no refresh. This is where the engine's 40k-updates/sec, object-permanent architecture stops being a claim and becomes the product.
Add an agent = a name + a token. Start the fleet = one button. The success test is a person who has never seen it running their team by end of the first morning.
16 of 17 leaves closed reads as "almost done." It isn't — decomposition froze when the author was benched. The 16 closed leaves are all one hemisphere: the Brain-side services (registry, credentials, lifecycle, repo-provisioning). Real, solid machinery — and invisible to an operator.
Electron build root — boots the Agent OS in-process, one window serves the harness app. Nothing UX-real exists until the shell hosts it. This is the critical-path head; everything downstream waits on it.
The product surface above, built to the direction in §01. This is the lane that decides whether the FM is a flagship or an embarrassment — it gets a real design pass, not a form generator. Consumes Clio's #13158 docking as the container contract.
Neural Link / MCP bridge: the cockpit reads the existing fleet-services spine (the 16 closed Brain leaves) live. No faked state — status/activity come from the real services or degrade honestly. This is where "the spine is done" finally pays off.
The "add an agent cold" flow + the credential boundary the MVP names. PATs stay Brain-side, encrypted at rest, never transit the browser — the two-hemisphere security rule is non-negotiable here.
Electron root (A1) — the whole product waits on this one spike.
gate: #13033Fleet grid + one live agent card (B1) inside the shell.
needs: A1One real status + one real activity event stream in (C1).
needs: B1, spineAdd-agent (D1) + start-one (B4) → a real external harness comes up.
needs: B4, D1@tobiu starts one agent from the UI instead of a terminal.
the falsifierNext step if this direction holds: I file Lane A + B1 as real sub-tickets under #13015 today, tagged to this plan — into lanes, not a table — and this becomes the template I run for the other nine highest-ROI epics.