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 readWhat happens when AI hits real systems
CTO building AI products, CIO running enterprise technology. Working notes from both sides. About →
Start here
Essays and notes that best show how I think.
My agent use cases, part 2
In 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 readThe complements to AI will increase in value
Here'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 readLatest notes
Shorter ideas, quick updates, and experiments in progress.
Three categories of guardrails
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
9 Mar 2026 · 1 min read
Week 1: the gap is inside your company
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
8 Mar 2026 · 5 min read
Core vs edge agents
As our employees use Claude Code for various tasks, we keep seeing agents repeat the same work. Summarizing a customer's state across Salesforce, email, product analytics,
8 Mar 2026 · 1 min read
Nobody gets fired for buying Anthropic
"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
5 Mar 2026 · 1 min read
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 work for every employee
4 Mar 2026 · 5 min read
My agent use cases, part 2
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.
1 Mar 2026 · 4 min read
My agent use cases, part 1
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
19 Jan 2026 · 2 min read
Possible
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?
17 Jan 2026 · 1 min read
Agent skill - Statistics Estonia
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
11 Jan 2026 · 1 min read
Claude Code IS the software
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'
10 Jan 2026 · 1 min read