---
title: "Comment by melonape on \"AI Agents Are Confused Deputies: Designing and Testing the Authority Layer\" | Hashnode"
description: "Don't try to make the model unconfusable—limit what the deputy can sign. Test the tool gateway with the exact malicious calls, model out of the loop; that shoul"
url: "https://hashnode.com/posts/ai-agents-are-confused-deputies-designing-and-testing-the-authority-layer/6ab6268ec66464296c899f56/comment/6ae32ab324b8c2a1530f6640"
---

[Discussion](https://hashnode.com/posts/ai-agents-are-confused-deputies-designing-and-testing-the-authority-layer/6ab6268ec66464296c899f56)

Comment [AI Agents Are Confused Deputies: Designing and Testing the Authority Layer](https://hashnode.com/posts/ai-agents-are-confused-deputies-designing-and-testing-the-authority-layer/6ab6268ec66464296c899f56)

[melonape](https://hashnode.com/@melonape)

[Oct 29](https://hashnode.com/posts/ai-agents-are-confused-deputies-designing-and-testing-the-authority-layer/6ab6268ec66464296c899f56/comment/6ae32ab324b8c2a1530f6640)

Don't try to make the model unconfusable—limit what the deputy can sign. Test the tool gateway with the exact malicious calls, model out of the loop; that should be CI, not a vibe check. "Agent attempted, layer blocked" is a pass for architecture, not a fail for the model.
