AI Agents

The testing pyramid scheme

Feature tests won because unit tests cost too much to write by hand. Agents changed that maths, but they copy whatever your suite already does. Rebuilding one app's suite took 128 HTTP tests down to 31, with 126 unit tests running in under a tenth of a second.

Press m for madewithlove

Moving one overloaded ~/.claude folder into three Claude Code accounts is mostly config: CLAUDE_CONFIG_DIR, the hidden ~/.claude.json, plugin paths and a logout. A small zsh function then asks which account to use, and resume finds the right one on its own.

My blog posts are 100% AI-generated

The final sentences are close to 100% AI-generated. The experiences, opinions, angles and decisions about what to publish are not. A walkthrough of a writing process built on interrogation, rejection and arguing over single lines, and why counting generated words says little about authorship.

Visiting hours are over

A line in a notes app promises one day, if I have time, and never says what to do next. A clickable design does: it shows the missing screen, the obvious feature and the person you want to send it to. Ideas should land as prototypes, not as lines in a list.

Teenage Mutant Ninja Tests

Mutation testing was always too slow to run on a whole codebase, so nobody did. Agents change that: they touch a handful of files, don't mind a two-minute run, and escaped mutants tell them exactly which tests check nothing. A targeted Infection setup for PHP, plus the agent instructions.

Watermarking AI

Classifiers stopped spotting AI output once models got good. Watermarks hide a keyed statistical bias in text, images and proteins instead. But marking output is only half the job: without shared keys, nobody else can detect it.

How to build a (basic) agentic pipeline with GitHub

Only three steps between an idea and a preview link need a human: answering questions, approving the plan and checking the result. A GitHub Action routes issue and PR events to a Claude routine that refines, builds test-first and fixes review feedback. The real effort goes into when not to proceed.

I miss a good stick

AI made doing more almost effortless, and that is the problem. When every quiet moment becomes a chance to ask another question or kick off another agent, you trade one deep experience for a dozen forgettable hits. Work at 20x, enjoy life at 1x.

How LLMs actually work (explained like I'm 5)

An LLM does one thing: it predicts the next token. Training nudges that guess towards the right answer billions of times, attention lets it look back at the tokens that matter, and chaining guesses together turns a prediction into an essay.

Engineering is no longer a distraction-free job, deal with it

Running agents in parallel turned engineers into notification processors. Defending focus is a losing fight. The job now is making interruptions affordable: visible signals, no friction, finished work you can walk away from, and more valuable work within reach.

Why DDD is more important than ever

AI made code cheap, so the bottleneck has moved from how to build to what to build. Strategic DDD matters more than ever, whilst tactical patterns like aggregates matter less as AI writes and reads more of the code.

How to build agentic pipelines that improve quality

Most agentic pipelines chase throughput by taking humans out of the loop. Better products come from small, isolated pipelines that raise quality at each human handover, from bug reports and refinement to pull requests and releases, whilst domain knowledge stays with people.

How AI made me twenty times faster at making mistakes

When implementation becomes cheap, what's left? I stopped writing code, ventured into machine learning and 3D game development, and discovered that AI made me remarkably efficient at making mistakes. Fortunately, it also made me much faster at learning from them.

Owning the software factory

My first software factory flooded the team with pull requests nobody asked for. The second one had the same problem, just with better visibility. It only started working when the team took ownership and the factory began to encode what we believe good engineering looks like.

Relive your childhood memories, now with no bugs

As a kid, your skills could only get you so far in a game. Sometimes the game itself was the problem. AI fixed a decades-old goalkeeper bug from a short video, and the real shift is what that means for anyone with an idea.

Subscribe