Ideas in practice
Writing
Practical notes on building, operating, and improving LLM applications.
The Worst Bugs Said Nothing: Building a Tool That Checks AI Plugins
What fourteen rounds of adversarial testing taught me while building neckbeard, a tool that reads a Claude Code plugin before you install it. The dangerous failures were never wrong answers. They were silences.
September 25, 2026 · 4 minVibe Coding, One Year Later: Agentic Workflows and Engineered Loops
What changed when an agentic loop inside an editor became asynchronous, context-managed work, and why engineering the loop now matters as much as the model.
August 18, 2026 · 8 minVibe Coding Is No Joke. It Actually Works.
What I learned in my first three months of vibe coding, including the original 15-rule checklist for working effectively with AI coding tools.
April 29, 2025 · 4 minAdding Logging Traces, Ratings and Unit Tests to your Chat Assistant
In this series of articles, we will delve into the intricacies of creating a multi-user chat assistant using AWS serverless and OpenAI.
July 21, 2024 · 7 minFrom Zero to Hero: Building and Deploying Your First Multi-User Chat Assistant with Lambda, OpenAI Assistant API, and TypeScript
In this series of articles, we will delve into the intricacies of creating a multi-user chat assistant using AWS serverless and OpenAI.
June 25, 2024 · 6 minFrom Zero to Hero: Want to Cheaply Build a Robust Multi-User Chat Assistant? 🤖
In this series of articles, we will delve into the intricacies of creating a multi-user chat assistant using AWS serverless and OpenAI.
June 24, 2024 · 5 min