Field notes
Practitioner essays on building production software with AI agents.
Operator-grade reports on the systems, decisions, and economics of shipping software with AI — what worked, what failed, and what changed.
Articles
-

You Trust the Lowest Bidder. But Not the Best Frontier Model?
Executive Deck ↗Exec summary ↗Listen ↗You trust the lowest bidder's pull request. Why not the best frontier model inside a system that actually checks the work?
-

If Your Engineers Only Get Thirty Minutes to Learn, That Is Not Their Failure. It Is Yours.
Executive Deck ↗Exec summary ↗Listen ↗You called to talk about AI adoption. But you do not know your value streams, your engineers get thirty minutes a week to learn, and you are still defending manual QA that produces no ROI. That is not an adoption problem. That is a leadership problem you built and now own.
-

If Mythos Is Real, Will the Board Wait 24 Months While You Figure It Out?
Executive Deck ↗Exec summary ↗Listen ↗Everyone is talking about Claude and Mythos. Nobody is talking about the fact that your org still cannot ship. The models are not your bottleneck. Your decade-old dysfunction is. And the board is about to notice.
-

If you cannot afford the tokens, can you afford to build it?
Executive Deck ↗Exec summary ↗Listen ↗Download EPUB ↓Your CFO should not be asking what you spent tokens on as if the model invoice is a minibar tab. Your CFO should be asking why the highest-ROI production input in the software portfolio is underfunded.
-

Before You Optimize Token Spend, Try This Formula Instead
Stop spending dollars to save pennies on tokens. Tie the token budget to estimated labor cost, pick a starting percentage, and adjust it using completed-project evidence.
-

Your Leaders Stopped Building. Now Vendors Own Your AI Strategy.
Executive Deck ↗Exec summary ↗Listen ↗Your technology leaders stopped building years ago. When AI arrived, vendors filled the vacuum. The fix is not better tools. It is rebuilding the technical leadership capability you let atrophy.

