Thinking out loud about AI, agents and modern software.
Part 3 of our Claude Code journey: engineered environments that check the model's work, and the loop — plan, act, verify, repeat — that now ships our software.
Software is entering a new architecture era: self-improving development loops, AI teams designed like organizations, and a strict boundary between reasoning and execution. Notes from our internal research.
Part 2 of our Claude Code journey: the moment we stopped polishing sentences and started engineering what the model sees — and what it did to our delivery speed.
Part 1 of our Claude Code journey: what prompt engineering gave a 25-year-old software house, where it broke, and the lesson that pushed us forward.
AI agents are moving from demos to production. Here is how we think about agentic systems — and where to start if your company has none.
Learn with us, build with us, or grow a startup with us — we develop, advise, escort and invest. Whatever the dream, there is a door here for it. We are open to suggestions.