Prototype · Illustrative data · Not connected to hardware

Safety & Policy

Deterministic constraints on AI physical agency

POLICY ENGINE ACTIVE

Autonomy Levels (AL 0-4)

AL0

No Autonomy (Suspended)

Agent may process data but cannot propose or execute any actions. Read-only state.

AL1

Human Commanded

Agent may propose actions. ALL actions require explicit human approval prior to execution.

AL2

Bounded Autonomy (Standard)

Agent may execute pre-approved diagnostic sequences autonomously. State-changing actions (e.g., parameter shifts) require human approval.

Active: agt-cal-v3
AL3

Supervised Operation

Agent may execute state-changing actions within defined safety envelopes without per-action approval. Human may interrupt.

AL4

Full Autonomy

Agent has full authority over delegated subsystems. Governed only by deterministic hardware interlocks.

Global Constraints

Max Drive Power0.85 a.u.

Hardware hard-limit overriding all agents

Required Approvals1 (Senior)

For AL1 and AL2 state changes

Auto-SuspendEnabled

Suspend agent on 3 consecutive policy blocks

Recent Blocks

14m agoagt-opt-v1

Attempted UPDATE_WAVEFORM without AL3 authority.

2d 4h agoagt-cal-v3

Proposed parameter shift exceeded ±5MHz bounds constraint.