---
title: The model should not be the policy engine
series: control-loop
type: opinion
published: 2026-09-06
updated: 2026-09-06
author: tim
confidence: medium
project: authority-compiler
tags:
  - policy
  - agent-systems
  - trust-boundary
exposure:
  basis: architecture-analysis
tested_with: []
domains:
  - agent-systems
  - trust-boundary
thesis: Semantic reasoning can inform policy decisions, but hard constraints, permissions, budgets, and operational invariants should remain outside the reasoning model wherever they can be deterministic.
---

The model may be the best part of a system at interpreting ambiguous intent.
That does not make it the right authority for granting itself permission.

Keep hard constraints, permissions, budgets, and operational invariants outside
the reasoning model where they can be deterministic. Let semantic judgment
inform a policy decision when necessary, but keep the final boundary in a
runtime, credential, or infrastructure layer that can be inspected and
enforced independently.

This is an architectural hypothesis, not a report of a completed implementation
or hands-on test. It connects directly to [Authority Compiler](/work/authority-compiler)
and [A runtime for agents is an authority system](/guides/concept/runtime-as-authority-system).