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 › L4 · Orchestration
L4 · Orchestration

Disruption-Mitigation Workflow

When the twin predicts a breeder disruption, orchestration triggers a bounded mitigation sequence before the plasma terminates uncontrolled.

THE STACK · click to jumpL7Ecosystem & StrategyL6Experience & VisualizationL5Applications & CopilotsL4OrchestrationL3Twin Modeling & AIL2Data FabricL1Control PlaneL0Foundation▲tlmctl▼L4 · ORCHESTRATIONEvents, workflows, rules, and human routing.1Event Streamingthe backbone2Workflow Enginecampaign procedures3Rules & Safety Boundshard limits4Human-in-the-Loopapproval routing5Schedulerexperiment campaigns6Audit Busfull decision lineageMACHINE TIECoordinates L3 outputs with L5 copilots and human operators.KRONOS FUSION ENERGYAI-NATIVE S.M.A.R.T. GENERATORORCHESTRATIONSHEET 06REV. 2026-08L4 · AI-NATIVE STACK
L4 · Orchestration — its place in the stack (left, click any layer) and its internal components (right). Telemetry rises; control descends.

Predict, then act within bounds

A disruption is a sudden loss of the breeder plasma's confinement that can damage the machine. The twin (L3) forecasts disruption risk from real-time diagnostics; when risk crosses a threshold, orchestration triggers a pre-planned mitigation sequence. Because this is a protective action it runs at high priority, but it still passes the envelope and rate checks, since a mitigation that itself violates magnet limits helps nothing.

The mitigation decision

python
if twin.disruption_risk > RISK_TRIGGER and twin.uncertainty < UNC_MAX:
    action = mitigation_plan(state)          # e.g. controlled termination / injection
    if envelope_ok(action) and rate_ok(action):
        execute(action, token=EMERGENCY_MITIGATION)
    else:
        fallback_safe_termination()          # always-valid last resort
elif twin.uncertainty >= UNC_MAX:
    conservative_rampdown()                  # do not trust an uncertain forecast

Uncertainty gates the response

A high-confidence forecast can trigger a targeted mitigation; a low-confidence one falls back to a conservative controlled ramp-down rather than a specific aggressive intervention. This encodes the principle that the machine should not take a strong action on a prediction it cannot trust, consistent with twin/copilot coordination.

Relationship to hardware protection

Simulation and replay

Disruption mitigation is developed and tuned against replayed and synthetic disruption scenarios in the twin, since the breeder is not built. Every trigger, forecast, and action is journalled so a mitigation can be replayed to ask whether an updated twin would have acted sooner or better.

Content reviewed August 2026 · design-and-simulation stage