LLM

// 2 articles on LLM by Faez Tgh — practical React, Next.js, TypeScript and web-performance write-ups.

Getting Structured Output From LLMs Without the Guesswork

Jul 7, 2026· 5 min·965 words

Asking a model to 'reply in JSON' and hoping is how you end up parsing prose at 2am. Modern models expose schema-constrained output and tool calling that guarantee the shape — the trick is choosing the right one and validating anyway.

AI
LLM
TypeScript

read-postopen

general

A Practical Primer on Retrieval-Augmented Generation (RAG)

Jul 2, 2026· 6 min·1,201 words

An LLM only knows what it was trained on and what you paste into the prompt. RAG is how you give it your own knowledge — your docs, your data — without retraining anything. Here's the pipeline, end to end.

read-postopen

LLM

Getting Structured Output From LLMs Without the Guesswork

A Practical Primer on Retrieval-Augmented Generation (RAG)

# other-topics

LLM

Getting Structured Output From LLMs Without the Guesswork

A Practical Primer on Retrieval-Augmented Generation (RAG)

# other-topics