Blomfield loop
Tom Blomfield’s five elements of a self-improving loop: sense, decide, act, verify, and learn.
Working notes on how technology changes real systems
I build technology products and teams. Here, I write about building with AI, work, and judgment.
Latest writing
Close loops
When the right action is unclear, progress comes from a simple loop: act, observe, learn—and change what you do next.
Beyond prototypes: shipping trustworthy AI
Three stories about getting AI features into production—from Veriff, NFTPort, and Pactum—drawn from my Nordic Testing Days keynote.
Finding talent is a key job
Finding talent is not a side task to delegate. Leaders need to learn how to spot great people before the obvious signals appear.
A thinking partner is a medium, not a source
A thinking partner's value is in what it pulls out of you, not the text it writes. Five things stock Claude gets wrong, and the 800 words of instructions that fix them.
There will always be something impressive left to do
As AI improves, what counts as impressive will change—but there will always be something impressive left for humans to do.
HTTP 402, still reserved
Payments were in the web's original vision, but HTTP 402 is still reserved. AI agents may give us another chance to solve identity and accountability online.
Great ideas are incubated dumb ones
Many ideas look weak or dumb when they are born. If you shoot them down before incubating them, you will never get anything new.
The low-value work left for humans
AI can do the entire job, except the low-value data shuffling.
Agentic UX ruins the coaching
One more thing that's annoying when using AI as a coach: any amount of reasoning tokens will make me switch away. Latency actually matters here. Two seconds is okay; twenty ruins the flow. There is also something more subtle. I don't take as much responsibility for my thoughts, am not as critical. I don't