Hello, my name is
AI adoption and engineering. I look at the whole product, not only the code.
Latest post ·
Reading a skill is the cheap part. The work it drives is where the tokens and the time go - every search, file read, retry and wrong turn the agent takes along the way. A good skill makes that work predictable: fewer wrong turns, and the same result tomorrow as today.
This article walks through how I plan and write skills, with a release-notes skill as the running example, and how to test them with tools like skillgrade.
12 min read · Updated
Featured series · 4 parts
A practical, tool-agnostic guide to engineering with AI coding agents.
Executing coding agents from the shell or your desktop executes commands with your user's privileges. Their own guardrails have come a long way, but a prompt injection can hide in many places - open-source packages, images with invisible text, which only the agent reads, harmful instructions inside searched pages, the list goes on.
6 min read ·
A deterministic workflow with AI agents is orchestrated by having efficient system prompts and skills to help you combat context rot and agentic drift, and prevent user steering and general frustration.
10 min read ·
Coding agents forget everything between sessions, and the bigger the codebase grows, the more they have to rediscover before they can do anything useful.
6 min read ·
Reading a skill is the cheap part. The work it drives is where the tokens and the time go - every search, file read, retry and wrong turn the agent takes along the way. A good skill makes that work predictable: fewer wrong turns, and the same result tomorrow as today.
12 min read ·
Writing · 8 posts since Dec 2025
Mental notes
Reading · 12 books
Hover a book to see what it isTap a book to see what it is · 12 books, 7 topics
