Two Prompts and a Text File
You don't need a complex "second brain" system to get real value from AI at work. A morning briefing and an end-of-day note - two copy-paste prompts you can set up in minutes.
Read more →Recent Posts
Wearing all the hats, again
The shape of software teams is drifting back towards generalists. Can leaders who grew up specialised design roles for that world?
Read more →
On not keeping up with the AI hype
Advice for engineers (and their managers) feeling perpetually behind on AI: macro awareness and talking to your colleagues beats drinking from the firehose.
Read more →
Who Taught Who (Whom?) to Write?
What happens when AI has learned to sound so much like us that writing in your own voice gets flagged as the machine — and why I've stopped contorting mine to pass.
Read more →
What Happens to Platform Teams?
How AI-accelerated development is reshaping platform engineering teams - a shift toward lower-level APIs, inner sourcing, and agent-ready repos over polished products.
Read more →
Lines of Code Got a Better Publicist
A case against measuring AI-assisted engineering by code volume and other vanity metrics instead of outcomes.
Read more →
Is coordinating a fleet of AI agents the same as managing a team of people? Yes, but mostly no.
Arguing that coordinating AI agents is closer to staff engineering than people management — and why that framing matters.
Read more →
Calibrating on Capability, Not Activity
A case for measuring AI-assisted engineering by observable capability, not tool telemetry, prompt counts, or PR volume.
Read more →
My AI Context System: The Sequel
A month-on update to my AI context system — what I added, what I threw away, and why selective automation beat full automation every time.
Read more →
Teach the AI to Fish
Why your documentation needs to serve AI agents as first-class readers — and why writing a CLAUDE.md should be as deliberate as choosing a framework.
Read more →