---
title: "Comment by Mateo Ruiz on \"Day 04: Stop parsing prose. Make the model return a struct\" | Hashnode"
description: "The distinction between schema validity and semantic correctness is the part I’d pay the most attention to. A response can satisfy every required field and stil"
url: "https://hashnode.com/posts/stop-parsing-prose/6ae0e5ff407874d8b565d81f/comment/6ae32f90d84a8b92dc658f50"
---

[Discussion](https://hashnode.com/posts/stop-parsing-prose/6ae0e5ff407874d8b565d81f)

Comment [Day 04: Stop parsing prose. Make the model return a struct](https://hashnode.com/posts/stop-parsing-prose/6ae0e5ff407874d8b565d81f)

[Mateo Ruiz](https://hashnode.com/@mateoruiz)

[Oct 29](https://hashnode.com/posts/stop-parsing-prose/6ae0e5ff407874d8b565d81f/comment/6ae32f90d84a8b92dc658f50)

The distinction between schema validity and semantic correctness is the part I’d pay the most attention to. A response can satisfy every required field and still point to a line that doesn’t exist or provide evidence that was never in the source.

I’d keep structural validation and grounding checks as separate stages, then track failures by category: malformed output, repair required, invalid references, and unsupported claims. That makes the schema-off experiment much more useful because you’re measuring not just whether the model returns valid records, but whether those records are actually reliable. Strict output controls the shape; it doesn’t establish truth.