---
title: "Discussion on \"Parsing LLM Responses in DataWeave: 3 Layers of Defense\" | Hashnode"
description: "Discussion on \"Parsing LLM Responses in DataWeave: 3 Layers of Defense\". I connected MuleSoft to GPT-4o last quarter for a support ticket classifier. The prompt builder worked (I covered that in a previous post). The LLM call worked. Then the response came back and my parser crashed.\nThe LLM was supposed to return clean J..."
url: "https://hashnode.com/posts/parsing-llm-responses-in-dataweave-3-layers-of-defense/69d2c38139f2e052e736edef"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [Parsing LLM Responses in DataWeave: 3 Layers of Defense](https://thasha.hashnode.dev/parsing-llm-responses-in-dataweave-3-layers-of-defense?utm_source=hashnode&utm_medium=feed)

I connected MuleSoft to GPT-4o last quarter for a support ticket classifier. The prompt builder worked (I covered that in a previous post). The LLM call worked. Then the response came back and my parser crashed. The LLM was supposed to return clean J...

Apr 5 · 5 min read · thasha.hashnode.dev  
Read the article

## Written by

[ThaSha](https://hashnode.com/@thasha)

@thasha

  
[View profile](https://hashnode.com/@thasha)

## Responses

Markdown supported · ⌘↵ to post

No responses yet.