Slangify-Tutorial

Slangify-Tutorial

← Index

00. Slangify::Tutorial

Using DSLs with LLMs: From Prompt to Structured Output

Suppose you want an LLM to extract structured information from messy text — but you don’t want to hand-write JSON schemas or fragile parsing logic.

Input:

Jane booked a table for 4 at 7:30pm tomorrow at Bistro Verde

Desired output:

"name": "Jane",<br>"party_size": 4,<br>"time": "7:30 PM",<br>"restaurant": "Bistro Verde",<br>"date": "tomorrow"

Slangify lets you define that structure with a DSL, then use an LLM to populate it reliably. This tutorial walks through everything from a first schema to a real-world pipeline.

What you will learn

Understand what Slangify does

Define a simple DSL schema using a Raku Grammar

Connect it to an LLM via LLM::Functions

Generate structured outputs from prompts

Validate and post-process results

See how this fits into a real workflow

Chapters

01. Setup

02. Your First Schema

03. Connecting to an LLM

04. The Generated Output

05. Iteration

06. Validation and Constraints

07. Prompt Engineering Patterns

08. Prompts

09. A Real-World Example

10. Common Pitfalls

11. Next Steps

Prompt Guide

Naturally, the example DSL code shown in this tutorial was itself generated by an LLM Agent (Claude Code). See LINK HERE for the prompts and tweaks we used to get a clean solution - adapt those for your own project.

More Info

Visit https://slangify.org for more information, examples and guidance.

Please ping the https://raku.org/community

This site is open source. Improve this page.