§ A publishing practice by Freerk Kalsbeek
Named beforeit was obvious.
I work one layer below where the conversation is happening. Curiosity put me there: I'd rather take a thing apart than take its description on faith. Building taught me to see the structural shift before it has a name.
Right now that's AI, and not at the product layer. I'm less interested in the tools than in what they're changing underneath. How agents will carry intent when they talk to each other. What memory becomes once you stop mistaking retrieval for it. What software becomes when the interface is a conversation.
Not a publication list, just the questions that wouldn't leave me alone. I write essays when the pattern is clear and tinker when it isn't, building a venture only when the idea earns it. Available to think with you on the hard ones.
From the desk
03 / 03- № 001
A process you can argue with
I almost built a publishing pipeline in a workflow builder, then noticed what I'd lose. A node graph gives you nothing to argue with: keep the part you're still reasoning about in the conversation, and push only the settled part down into the loop.
- № 002
Nowhere to put it
My publishing setup was over-engineered, and every morning I still copied last night's draft across by hand. The missing piece wasn't a tool. It was a place for the draft to land the moment I finished writing it.
- № 003
Publish the question
A claim I believe and can't yet prove, published with the hole still in it. A well-posed question, with the route to its answer attached, is a finished piece of work, even before the answer arrives.
§ The list
Essays in your inbox
New writing when the pattern is clear. No cadence, no filler.