Archive
Error Handling in LLM Systems — Three Categories, One Decision Tree
Topic Suggestion — Designing a Function That Knows What to Recommend Without Magic Numbers
Streaming Structured Output — Incremental JSON Rendering Without a Parser
Evals — Why a Bad Eval Is Worse Than No Eval
Adding Spaced Repetition to an LLM Study System — SM-2, Schema Design, and a Scoring Problem Worth Solving
Tool Use + RAG — When Retrieval Becomes a Decision
Python for JavaScript Engineers — A Practical Mental Model
Prompt Engineering Lessons from Building a Problem Generator
Structured Output — When to Use Prompting vs. Forced Tool Use
The LLM-as-Judge Problem — Making Automated Evaluation Reliable
Designing an LLM System That Actually Solves a Real Problem
Building RAG from Scratch — Embeddings, pgvector, and a Bug Worth Knowing
Tool Use — How the Model Calls Your Code (And What It Never Sees)
Why Streaming Changes How You Build LLM-Powered Interfaces