Your AI employees need a handbook
I've seen people try Claude or ChatGPT, get mediocre answers, and conclude AI is overhyped. But the power of agents doing real
4 Mar 2026 · 5 min readCTO building AI products, CIO running enterprise technology. Working notes from both sides. About →
Essays and notes that best show how I think.
I've seen people try Claude or ChatGPT, get mediocre answers, and conclude AI is overhyped. But the power of agents doing real
4 Mar 2026 · 5 min readIn part 1 I covered the straightforward agent use cases: copyediting, onboarding, expense reports, Jira management. Those are about doing existing tasks faster. The
1 Mar 2026 · 4 min readHere's a model I use to think about how AI will change work. Some parts of every activity will cost 1,000x
4 Aug 2025 · 2 min readShorter ideas, quick updates, and experiments in progress.
"Nobody gets fired for buying IBM" used to mean: pick the vendor nobody will question. It was a decision driven by fear, not conviction. I think
I've seen people try Claude or ChatGPT, get mediocre answers, and conclude AI is overhyped. But the power of agents doing real work for every employee
In part 1 I covered the straightforward agent use cases: copyediting, onboarding, expense reports, Jira management. Those are about doing existing tasks faster. The five below are different.
While we're in this mode of rapidly developing agent capabilities, I want to do my part in diffusing knowledge of what agents can do. Since Claude
People sometimes use the word "impossible" too lightly. When I consider whether something is possible, I consider two angles first: 1. Is it logically provably impossible?
Today I published my first agent skill: using Statistics Estonia databases. Often I have some simple question and I know data exists, but I can't be
In 2024, humans created software. In 2025, Claude Code (and Codex, and Cursor, and all the others) created software. In 2026, Claude Code is the software. It'
Reading Shipping at Inference-Speed and with the Christmas holiday on my hands, I again felt a deep desire to ship a side project while getting a feel for
When solving a problem with an existing system, most people tend to add. But often, removing makes a design better. * Dieter Rams's famous principle is "
I used to think shipping an agent product meant building: 1. The core LLM loop. 2. Skills: describing to the LLM how to do particular things (including building