---
title: "Comment by Kartik N V J K on \"Structured Output Beats Prompt Tweaking: A Practical Eval Loop\" | Hashnode"
description: "Ten days of calling parser breaks prompt problems sounds familiar to me. I'd still watch for a reply that passes the schema with a wrong value, the right vendor"
url: "https://hashnode.com/posts/structured-output-beats-prompt-tweaking-a-practical-eval-loop/6ae1855c2095097a8f491333/comment/6ae34fb8cabb70c219e8bd16"
---

[Discussion](https://hashnode.com/posts/structured-output-beats-prompt-tweaking-a-practical-eval-loop/6ae1855c2095097a8f491333)

Comment [Structured Output Beats Prompt Tweaking: A Practical Eval Loop](https://hashnode.com/posts/structured-output-beats-prompt-tweaking-a-practical-eval-loop/6ae1855c2095097a8f491333)

[Kartik N V J K](https://hashnode.com/@kartik-nvj)

[Oct 29](https://hashnode.com/posts/structured-output-beats-prompt-tweaking-a-practical-eval-loop/6ae1855c2095097a8f491333/comment/6ae34fb8cabb70c219e8bd16)

Ten days of calling parser breaks prompt problems sounds familiar to me. I'd still watch for a reply that passes the schema with a wrong value, the right vendor and a confidently wrong amount, which only your field-level accuracy on the fifty examples would catch. When the failure rate dropped by half, did that count both kinds or just schema failures?
