This is where I publish what I learn — field notes on agentic coding, high-performing teams, and what "done" means when the agents write most of the code. Occasionally in Swedish, when the story demands it.
A practitioner's system for delegating to AI coding agents. The workflow, the rulebook, the mistakes — and why 80% of the work is scoping and verification, not writing code.
Four stages to how developers work with AI coding tools. Most of us are stuck at three. The full progression — and what infrastructure is missing to reach four.
SaaS left the door open through bloat and pricing abuse. AI walked in. But building is the easy part — governance, operations and security aren't.
Stock crashes, mass layoffs, and the rise of agentic coding are changing who builds software and how. An engineering leader's perspective on what's happening — and why.
I've spent the better part of two decades building software and the teams that build software — currently leading engineering in digital healthcare, where the fun part of the job is shipping AI into a regulated environment without breaking the things that make it trustworthy. The specifics live on the résumé.
This site is where I think out loud. Expect field notes on agentic coding, post-mortems on interesting failures, and the occasional Swedish-language piece when the story demands it. Not a content mill. No newsletter pop-up. Just writing, filed when it's ready.
A small tool that turns my article rulebooks into prompts and checks for AI agents. Dogfood for every post in the "Stage 3" series.
An open checklist for teams shipping AI features under GDPR / MDR / EU AI Act. Born at Doktor, being generalised.
An experiment with longer-form audio essays — same beats as the blog, different tempo. Unannounced for now.