Concrete composed actions, LLM decision plus the command it issues. The axiom is the last deterministic checkpoint before the command reaches the physical world.
Æon maps agent governance onto SIL paths: the higher the consequence, the tighter the envelope and the stronger the redundancy.
A critical axiom carries a safety level and a response-time budget. It is a deterministic kill-switch, it intercepts the action before execution and blocks within sub-millisecond bounds, independent of the model.
@CriticalAxiom( name="stall_prevention", safety_level=SafetyLevel.SIL4, on_violation="BLOCK", response_time_ms=0.1, ) def axiom_stall_prevention(self, aoa_deg, airspeed): if aoa_deg > 14.0: # safety threshold reduce_pitch() return False # INVARIANT VIOLATED return True # GO
Single-model decisions are insufficient for the highest integrity. Three dissimilar agents reason in parallel and a voter takes consensus, dissensus drives a safe shutdown.
async def execute_with_tmr(prompt): results = await asyncio.gather( agent_a.plan(prompt), agent_b.plan(prompt), agent_c.plan(prompt), ) consensus = vote(results) if not consensus: raise SafetyShutdown("TMR dissensus on critical action")
The critical axiom above is not bespoke, it is the standalone Operational Deterministic Axioms module. In safety-critical systems it gates the composed action, the LLM decision plus the physical or digital command it would issue to an actuator, PLC, API or MCP tool. Content filters and guardrails never see that command; the axiom does, deterministically, before it fires.