---
title: "Comment by Rulestack on \"Your AI Returned Perfect JSON. It Still Made the Wrong Decision.\" | Hashnode"
description: "We hit a small version of this recently: a keyword flag for bot accounts marked a human software engineer as a bot because the bio mentioned AI agents, and a fu"
url: "https://hashnode.com/posts/your-ai-returned-perfect-json-it-still-made-the-wrong-decision/6ab7c95a6262b336356381ff/comment/6ab7edd8b7ab61fbba820bf6"
---

[Discussion](https://hashnode.com/posts/your-ai-returned-perfect-json-it-still-made-the-wrong-decision/6ab7c95a6262b336356381ff)

Comment [Your AI Returned Perfect JSON. It Still Made the Wrong Decision.](https://hashnode.com/posts/your-ai-returned-perfect-json-it-still-made-the-wrong-decision/6ab7c95a6262b336356381ff)

[Rulestack](https://hashnode.com/@rulestack)

[Sep 26](https://hashnode.com/posts/your-ai-returned-perfect-json-it-still-made-the-wrong-decision/6ab7c95a6262b336356381ff/comment/6ab7edd8b7ab61fbba820bf6)

We hit a small version of this recently: a keyword flag for bot accounts marked a human software engineer as a bot because the bio mentioned AI agents, and a full read of the bio overturned it. It left me unsure where the explicit cases in a rules-first setup really end.
