Skip to content

What we learn from building

We build our own products and software for companies, with agents and checks. Here we write down what works, what went wrong and how we go about it.

All articles

  • Build logs

    The tech behind Plens

    KNMI radar, Open-Meteo, openrouteservice and the PDOK Locatieserver: which source Plens uses for what, on which terms, and where it went wrong.

    , 8 min read

  • AI at work

    AI agents for business: where do you start?

    Putting AI agents to work starts with one process, a written goal and checks that run from the first version. A step-by-step plan with examples, pitfalls and the rules.

    , 10 min read

  • AI at work

    Running your own AI models: when and how?

    Private AI means models on machines you control. When a self-hosted LLM pays off, which options and tools exist, what you give up and how we do it with Northstar One.

    , 8 min read

  • Agentic engineering

    How does an AI code review by a council of agents work?

    One model reading your code finds a lot and misses a lot. A council puts several specialists on the same code, has their findings checked and leaves the decision to a person.

    , 6 min read

  • Agentic engineering

    ARCS: how we let AI agents build, with checks

    An agent that approves its own work misses its own mistakes. This is how ARCS keeps making and judging apart, and how we decide where a person has the final say.

    , 7 min read

  • Decision models

    Jev by TypeSafe, explained

    Jev does not write text. It takes a state and a few typed questions and returns an answer with probabilities for each. What that gets you, and where it stops.

    , 8 min read

  • Agentic engineering

    What is agentic engineering?

    Building software with AI agents while people set the goal, the limits and the final check. Where the term comes from, how it works and what breaks without checks.

    , 10 min read

RSS feed