Skip to content
Working modelProject

Authority Compiler

Deriving the capability surface available to an agent from delegation, policy, evidence, risk, and current task state.

State
working-model
Updated
2026-09-06
Owner
Tim
Area
agent-runtime / permissions / policy

Current question
How should evidence unlock temporary authority without allowing the reasoning model to redefine its own boundaries?

Read markdown

Why this exists

Tool-using agents can be technically capable of actions that the current task has not authorized. The problem is to preserve delegation scope as work is planned, delegated, and continued beyond one context window.

Current model

The working model treats effective authority as the intersection of user authority, organization policy, agent role, delegated scope, current task scope, operational state, and temporary capability leases. The reasoning model may propose a transition; an authority layer decides whether that transition is admissible.

What is unproven

No runtime, SDK, capability broker, or implementation is claimed here. No experiment has yet shown that capability attenuation or lease expiry works in a real agent system.

Next experiment

Define a small state model for one delegated subtask and test whether its available actions narrow when evidence becomes stale or verification fails.

Artifacts

Open questions

  1. 01Which authority decisions can remain deterministic at the runtime boundary?
  2. 02How should temporary capability leases expire when evidence becomes stale?

Next

Model capability attenuation across delegated subagents.