Skip to content
Technology How it works Breeder — Hyperion Burner — Aegis Burner — MetroVolt AI-Native Architecture Magnets Fuel cycle Safety Roadmap
Solutions AI & Data Centers Defense & Government Grid & Baseload Neutron Detection Quantum
Learn Technical Library
Proof Publications Whitepapers Technical Library Open Science & Reproducibility The Honest Gates
Company About / Mission Leadership Environment Health & Safety Investors Careers Press Contact
3D Model
AI Architecture › L6 · Experience
L6 · Experience

Cross-Machine and Fleet View

A single surface to supervise more than one machine at once — breeder and burner side by side, and multiple units of a kind — without diluting per-machine depth.

THE STACK · click to jumpL7Ecosystem & StrategyL6Experience & VisualizationL5Applications & CopilotsL4OrchestrationL3Twin Modeling & AIL2Data FabricL1Control PlaneL0Foundation▲tlmctl▼L6 · EXPERIENCE & VISUALIZATIONHow people see, steer, and review the plant.1Control-Room 3D Twinlive overlays2Plant-Floor SCADAoperations HMI3Mobile Engineeringfield access4Alerting UXtriage & escalation5DashboardsKPIs & health6Replayincident reviewMACHINE TIESurfaces the L3 twin state and L5 copilots to human operators.KRONOS FUSION ENERGYAI-NATIVE S.M.A.R.T. GENERATOREXPERIENCE & VISUALIZATIONSHEET 08REV. 2026-08L6 · AI-NATIVE STACK
L6 · Experience & Visualization — its place in the stack (left, click any layer) and its internal components (right). Telemetry rises; control descends.

Supervising more than one machine

Kronos operates one architecture across two machine types, and units of each kind follow (breeder first-of-a-kind, then next-of-a-kind and beyond). Operators and engineers will need to watch several at once. The fleet view presents a compact health row per machine — the essential KPIs, the worst active alert, and confidence — so a supervisor sees the state of everything at a glance and drills into any one machine for full depth.

Comparable, not identical

The breeder and burner have different physics, so the fleet row shows each machine's own most-decision-relevant indicators (breeder: shape fidelity, disruption risk, Q_sci vs 3.076; burner: plug-density balance, potential-well depth, DEC stability) under a common health summary. Same-type units are directly comparable, which is how a supervisor spots that one breeder unit is drifting relative to its siblings — an early, cheap signal.

Attention routing across the fleet

With several machines in view, attention discipline matters even more. The fleet view ranks machines by triage score so the one that most needs attention rises to the top, and it never lets a fleet overview replace per-machine authority: control of any machine still happens in that machine's control room, with its own crew and its own L1 failsafe. The fleet surface is supervisory awareness, not remote control.

The fleet view is the multi-machine expression of the dashboards and shares the ranking logic of the triage stream. It is honest about status the same way single-machine surfaces are — units still in design and simulation are labeled as such, and no cross-fleet net-gain claim is made before the breeder FOAK (~2030).

Content reviewed August 2026 · design-and-simulation stage