How I Stopped Fighting Regex and Finally Extracted Data with LLMs

I spent three days building a regex monster to parse customer emails. It had 47 patterns, each one...

venerdì 5 giugno 2026 New tab

917 words~4 min read

I spent three days building a regex monster to parse customer emails. It had 47 patterns, each one more fragile than the last. A single missing space would break the whole thing. By day four, I wanted to throw my laptop out the window.

That’s when I decided to try something completely different: let a large language model do the heavy lifting.

Here’s the story of how I went from regex hell to a clean, maintainable data extraction pipeline using LLMs — and why I won’t go back to hand-crafted patterns for unstructured text.

The Problem: Messy, Human-Written Text

I was building an internal tool to process support tickets. Customers would write things like:

How I Stopped Fighting Regex and Finally Extracted Data with LLMs

How I Stopped Fighting Regex and Finally Extracted Data with LLMs

Related reading

I stopped fighting with regex for data extraction. Here's how AI saved my…

I spent 3 days writing regexes. Then I asked an AI to do it in 10 minutes.

When Regex Fails: Using LLMs to Extract Structured Data from Messy Pages

How I stopped wrestling with regex and started using AI for data extraction

I spent a week on regex before realizing AI agent was the answer for data…

My 4-Step Regex Debugging Workflow (That Actually Saves Time)

Related reading

I stopped fighting with regex for data extraction. Here's how AI saved my…

I spent 3 days writing regexes. Then I asked an AI to do it in 10 minutes.

When Regex Fails: Using LLMs to Extract Structured Data from Messy Pages

How I stopped wrestling with regex and started using AI for data extraction

I spent a week on regex before realizing AI agent was the answer for data…

My 4-Step Regex Debugging Workflow (That Actually Saves Time)