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

From Decision to Experience: How L6 Consumes the Stack

How Layer 6 draws from L1-L5 and where it deliberately holds no authority — the contract that lets observability be everywhere while control stays concentrated.

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.

L6 is a consumer, not an authority

Layer 6 sits at the top of the KRONOS stack and depends on every layer beneath it, yet it deliberately holds no physics and no actuation authority. It consumes the outputs of L1-L5 and renders them for humans; it emits only advisory intents that flow back through the trust-and-override path. This clean separation — observability ubiquitous, authority concentrated in L1 — is what lets Kronos put the full picture on a phone without ever putting the machine at risk.

What L6 consumes from each layer

LayerWhat L6 renders from it
L1 Control Planeinterlock/failsafe status, actuation state, real-time bounds
L2 Data Fabricvalidated telemetry, timestamps, diagnostic health, lineage
L3 Twin Modelingstate estimates, forecasts, confidence, provenance
L4 Orchestrationjob/pipeline status, model versions in effect
L5 Copilotsexplanations, recommendations, citations

The latency gradient across the stack shows exactly why L6 is where it is: L1 runs microsecond hard-real-time loops, L3 the 1-100 ms twin, and L6 the 0.5 s-to-minutes human loop. L6 must never pretend to be faster than it is — hence the honest staleness and latency indicators — and must never insert itself into the fast paths it renders. It shows the fast world; it does not run it.

The contract in one sentence

Everything an operator sees is traceable to a layer below, timestamped, confidence-scored, and provenance-tagged; everything an operator does is advisory, attributed, recorded, and overridable — with the L1 hardware failsafe always authoritative underneath. That contract is what makes the interface trustworthy enough to lean on and safe enough that leaning on it can never bypass the machine's own protections.

This overview ties the L6 pages together: the surfaces (overlay, dashboards, triage), the trust machinery (uncertainty, provenance, override), and the human-factors discipline (cognitive load) all serve the same contract, for both the breeder and the burner.

Content reviewed August 2026 · design-and-simulation stage