ai-coding
Amplify Your AI Agents. Give Them a Computer.
A field guide to agents that check their own work, so you can stop babysitting them.
Writing on AI, engineering leadership & the craft
Hello, I'm Andrew. An engineering leader and builder.
Two decades building software and the teams that build software — currently in digital healthcare, working on what AI changes about the craft. This is where I publish what I learn. Field notes on agentic coding, high-performing teams, and what "done" means when the agents write most of the code. Occasionally in Swedish, when the story demands it.
Building Lotsa on the side — governed AI execution for regulated enterprises. Try Lotsa →
Latest articleAll writing →
A thesis
From prompting to orchestrating.
Where I think AI coding is going. It's reorganising software work along a four-stage progression. The models are good enough. The infrastructure isn't.
Read the argument →Cheat sheets
One-page references for putting it into practice.
- 01Amplify Your AI Agents. Give Them a Computer.
The six verification tiers, the eight proofs every change needs, and a verification contract to paste into CLAUDE.md or AGENTS.md.
- 02AI Coding Workflow
The Scope → Plan → Execute → Verify → Wrap-up cycle, AGENTS.md rules, context hygiene and anti-patterns.
Recent articlesFull archive →
ai-codingFive constraints on the road from delegating to orchestrating AI agents
Long chats, dead agents, skipped tests. Lessons from the road from delegating to orchestrating AI coding agents.
ai-codingClose the loop: verification and heartbeat for AI coding agents
Agents must verify their own work — but the shape of that loop depends on what you're building. Solo work versus team-scale, runners versus workflows.
ai-codingAI isn't magic dust. It's a multiplier.
Executives want AI gains. But AI is a force multiplier — it multiplies whatever you have, including your problems. Why Spotify and Stripe succeeded, what most companies miss,...
About
A short introduction.
Andrew Crookston
Engineering leader, writer
Engineering leader, writer
I've spent the better part of two decades building software and the teams that build software — currently leading engineering at a Swedish healthtech preparing for IPO, where the fun part is shipping AI into healthcare without breaking the things that make it trustworthy.
This is where I think out loud. Field notes on agentic coding, post-mortems on interesting failures, and the occasional Swedish-language piece when the story demands it. Slow writing on fast-moving things.
Also working on
All projects →