Loops, graphs & harnesses – getting quality out of a software factory
Deep-dive on harnessing in agentic coding workflows. I'll share how one code factory can be built, with real examples, design principles and ways to not do it.
Ivo's AI blog
Articles on AI and agentic software development, autonomous agent workflows, dark factories.
Lenny the LLM: Life as a Language Model
A fun short story where you live the life of Lenny the LLM, and on the way, learn the most important terms and concepts related to LLMs. This piece was originally written for //kood AI curriculum.
The Unbearable Brittleness of Autonomy
Success with autonomous coding agents isn't a given. Let's take autonomy apart, see what's inside, and find what we can actually control.
Lies and deception of the Yes-man: How to ensure quality in Agentic workflows, Part 1
Fully autonomous coding workflows break down through compounding mistakes and hallucinations under uncertainty. I share two concepts that help keep the machine producing software instead of chaos, along with practical tactics.
How I use up two Claude Max subscriptions per week
Several people have asked how on earth is it possible to use up all the weekly credits from one Claude Max 220€
How 32 agents write code for me in parallel, with vanilla Claude Code
I made a pretty good breakthrough recently that often truly feels like 30x improved efficiency. Last time I wrote about arriving at
How to Claude Code: Latest insights into spec-driven agentic development (pt 3)
Last 2 weeks have been busy - in addition to a ski trip and a ski marathon (different skis!) I've had
Building a reliable Spec Driven Development workflow, and deleting my src folder to test it (Claude Code pt 2)
"Remember kids, the only difference between screwing around and science is writing it down" - Adam Savage This quote has stayed
Deep into Claude Code in 2026 - learnings and insights (pt1)
Week 1 of Sabattical - did some Claude Code on Opus 4.5. I'm impressed and excited, so sharing some reflections.