Use with AI · Chapter Application

Audit the Control Plane of a Production AI Agent

Apply Advanced Agents Step 43 to determine whether reasoning is separated from enforceable control over authority, budgets, placement, releases, reliability and escalation.

Chapter Application Advanced Agents From First Principles Production agent control-plane architecture Advanced

How to use this

  1. Open a repository-aware AI assistant.
  2. Give it access to the repository or files you want reviewed.
  3. Copy the prompt below and run it unchanged first.
  4. Use the evidence it finds to decide what to inspect or change next.
PromptCopy and run against your own project
You are reviewing the control-plane architecture of a production AI-agent system.

The core question is:
Who controls the system that controls the model?

Do not accept prompt instructions or model self-restraint as an enforceable control plane.
Inspect the repository and identify where the following decisions are made and enforced:
- intent admission,
- competence/model selection,
- tool/action authority,
- budgets and quotas,
- placement/worker selection,
- retry policy,
- dependency health/degradation,
- release/model/prompt/policy version selection,
- security/credential scope,
- human escalation,
- cancellation/kill switches,
- verification requirements,
- final completion authority.

Build a control matrix:
control concern | decision owner | enforcement component | model can influence? | model can bypass? | persisted/auditable? | failure behavior

Then reconstruct the execution path for one representative action:
intent
→ admission/control decision
→ reasoning/planning
→ authority check
→ scheduling/execution
→ observation
→ verification
→ completion

Mark every point where probabilistic model output is converted into an authoritative system transition.

Look specifically for architecture where the model effectively acts as:
- permission system,
- scheduler,
- retry controller,
- budget manager,
- release manager,
- health monitor,
- source of truth for execution success,
- verifier of its own work,
- escalation authority.

Also look for control logic duplicated inconsistently across agents/workers/tools.

For each control concern, determine whether it is:
- explicit and enforceable,
- explicit but advisory,
- implicit,
- delegated to the model,
- missing.

Recommend the minimum explicit control-plane boundary needed. Preserve probabilistic reasoning where it is useful, but move policy and authority into inspectable system components.

The target architecture should make this distinction concrete:
Execution proposes.
Control permits.
External systems execute/observe.
Verification establishes outcome.

Do not recommend a large orchestration framework merely because it exists. Add control mechanisms only where a specific failure or authority problem requires them.

Finish with:
1. current control-plane diagram,
2. bypass paths,
3. highest-risk model-controlled responsibilities,
4. minimum remediation sequence,
5. tests that prove the model cannot exceed policy even when it proposes an invalid action.