Intelligence · Governing

Governing Intelligence.

The axiomatic layer. The Agency Paradox, AgentVector, the Laws, and the architecture that makes autonomous systems governable — not just capable.

01 · Constitutional Foundation

Who commands autonomous systems?

Discipline alone is insufficient. The question is not whether the human is attentive enough. The question is whether the architecture enforces authority when the human is not watching.

The question of command is not a behavioral question. It is an architectural one.
Scope Overreach

The agent acts beyond its declared domain, one small step at a time, until the boundary no longer exists.

Architectural Drift

The system that was reviewed is no longer the system that is running. Changes accumulate without governance awareness.

Silent Regression

A capability that was once constrained is quietly re-enabled by a model update, dependency change, or prompt mutation.

Dependency Sprawl

The agent acquires new tool integrations faster than governance can evaluate them. Each is approved; the surface area is not.

Invisible Composition

Ten actions, each within scope, combine into a pattern that no single approval anticipated.

The composition problem: Ten actions, each individually within scope, may collectively represent a pattern no single approval would have sanctioned.

Read the full paper →
02 · AgentVector Codex

A framework of Composable Laws.

Between the deterministic Laws and the stochastic agent sits the Stochastic Gap — the space where probabilistic reasoning meets deterministic authority. AgentVector bridges this gap with a kernel that compiles Laws into enforceable governance.

Pillar 01
State as Authority

The state is the single source of truth. No hidden channels, no side-state. What the state declares is what the system knows.

Pillar 02
The Reducer Pattern

Pure functions that take current state and an action, return new state or rejection. No side effects. No non-determinism. Replay-safe.

Pillar 03
Isolation

The agent proposes. The reducer decides. The agent never touches state directly. Governance is not advisory — it is the only path.

(CurrentState, Action) → NewState | Rejection
State Agent Action Reducer New State loop
The Steward writes the Laws. The Kernel compiles them. The Agent obeys them. The Principal observes everything.
Read the full Codex →
03 · Elements of Coherence

The elements define. The Codex constitutes.

From philosophical foundation to runtime verdict, every layer is traceable. The proof chain is the architecture.

Philosophical Foundation
  ↓  "Who commands autonomous systems?"
Constitutional Layer
  ↓  The Agency Paradox → Nine Properties
Specification Layer
  ↓  Law 0 (Scope) … Law 8 (Composition) … Law 10 (Reserved)
Kernel Layer
  ↓  SwiftVector · TSVector · RustVector
Governance Layer
  ↓  ClawLaw · FlightLaw · DispatchLaw · ChronicleLaw
Module Layer
  ↓  Domain-specific reducers · Policy evaluators
Verdict
  ↓  .allow · .deny · .escalate
Coherence Verification
  ✓  Deterministic · Composable · Auditable
01
Separation of governance from execution

The agent cannot modify, bypass, or disable the governance layer.

02
Determinism

Same action, same policy, same session state produces the same verdict, always.

03
Fail-closed default

When governance state is uncertain, the default is denial.

04
Compositional evidence

Full evaluation trace, not just the verdict.

05
Composition-aware evaluation

Session-level state as input to deterministic evaluation.

06
Substrate independence

Same authority model regardless of where the agent runs.

07
Principal observability

Full operational picture reconstructable from governance evidence alone.

08
Knowledge substrate currency

Staleness is a governance failure, not a minor degradation.

09
Bounded execution surface

An explicit, finite action surface governance can evaluate.

04 · The Law Registry

Deterministic. Composable. Auditable.

Eleven Laws in four groups. Each Law is a pure function: given a state and an action, it returns a verdict. No ambiguity. No discretion. No escape.

Group I — Foundational (Boundaries)
Law 0
Scope

The agent shall not act outside its declared domain.

Law 1
Lens

The agent shall interpret ambiguity through its declared domain lens.

Law 2
Tool

The agent shall only use tools registered in its manifest.

Law 3
Disclosure

The agent shall declare its identity, scope, and limitations on request.

Group II — Authority
Law 4
Escalation

The agent shall escalate to the principal when confidence is below threshold.

Law 5
Override

The principal may override any agent decision. The override is logged.

Group III — Integrity
Law 6
Evidence

Every verdict shall include the evaluation trace that produced it.

Law 7
Currency

The agent shall not act on stale knowledge without disclosure.

Group IV — Coherence
Law 8
Composition

Session-level action patterns shall be evaluated, not just individual actions.

Law 9
Reserved

Reserved for future constitutional extension.

Law 10
Reserved

Reserved for future constitutional extension.

05 · Enforcement Kernels

The Kernels compile the Laws.

Three runtime implementations. Same Laws, same reducer contract, different substrates. The kernel is not a library — it is the governance runtime.

Swift
SwiftVector
Reference kernel

The primary enforcement kernel. Actor isolation, Apple Silicon native, deterministic reducers. The kernel that compiles the Laws into executable governance.

FlightLaw, DispatchLaw, ChronicleLaw
TypeScript
TSVector
Integration kernel

Node.js runtime for web-facing governance. Same Laws, same reducer pattern, different substrate. Integration-first for existing toolchains.

ClawLaw, OpenClaw
Rust
RustVector
Transport kernel

Cross-platform enforcement at the edge. Zero-cost abstractions, no runtime, deterministic by construction. Where governance meets hardware constraints.

Edge deployment, embedded

The principal redefined: The pilot does not fly the aircraft by moving each control surface. The pilot commands the flight control system, which moves the surfaces. The principal does not govern the agent by approving each action. The principal commands the governance kernel, which enforces the Laws.

Applied at agentincommand.ai

The agent acts. The system governs.
The principal commands.

Governing Intelligence is the constitutional root. Everything else is a jurisdiction.

Enter agentincommand.ai → The Agency Paradox →