Working notes on how technology changes real systems
I joined Veriff as its first ML engineer, and almost immediately we realised we needed to scale up the AI effort very fast. I hired ten people in four months, and ended up leading the team myself four or five months in. One of those ten was fresh out of
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.
People worry that if AI keeps improving, there will be nothing impressive left for humans to do. I disagree. What counts as impressive will simply change. A full rewrite of an existing large piece of code today is not trivial, but it's also definitely not impressive anymore. Five
Identity, payments, and accountability online have never really been solved. They're not built into the protocols themselves. Payment was in the web's original vision: Tim Berners-Lee's first HTTP spec already had status code 402, "Payment required", where the client could retry
Estonia announced it will give AI agents digital IDs, and people are kind of skeptical and negative about it. I'm not. I think there's something to this. In general, I try not to shoot down new ideas by arguing against them as a knee-jerk reaction.
I recently used Claude to do the annual report for my holding company. It's an extremely simple company. There are no meaningful decisions to be made here. One invoice this year, and it's obvious how it should be handled. Still, Claude saved me probably an hour
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
Can you build an AI coach? The obvious answer is yes: AI is great at spotting patterns in what you say, and you can ask it to use any style of coaching, any framework. An exec coach I used to work with thinks you can't build an AI
In May 2026 I sat on a panel at Latitude59 in Tallinn called "AI in Your Org: What to Automate, What to Keep Human", with the chief of staff at Hostinger and a co-founder of Sera Leads. Three very different company sizes: 900 people, 150, and 10.
Install a Claude Code skill from any GitHub repo: the desktop steps, the two CLI commands, and why Claude keeps asking for permission afterwards.
Every product team building with AI faces the same question: where does the AI interaction go? Not the model or the prompt, but the affordance: the surface the user sees and interacts with. For my own reference and discussions I wanted to capture these. Even though the chat box is
Could you produce something large and complex just by taking pre-existing specs off the internet and having agents search the program space for you? I tried it.
Coding agents run a search in program space . That's the closest analogy I can find for how to use agents productively. If you think of it as an assistant to whom you give tasks, you'll generally be in too tight a loop, giving feedback every few
There are only three categories of guardrails to prevent harm from agents. First, relying on hard constraints to only allow certain kinds of behaviour. For example, limiting which tokens can be decoded ( structured output ) or exposing only a specific set of tools to an agent. Assuming correct implementation, these guarantee
I committed to sharing something every day in March about our AI transformation at Pactum. The pace is high, not just internally but in the entire world, so there's a lot that happens and a lot to share. This is the week 1 recap, pulling together what I&