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
-
The Engineers Who Can’t Use AI Agents Don’t Have a Tools Problem
Executive Deck ↗Exec summary ↗Listen ↗Your engineers struggling with AI agents don’t need better tools or training. They need permission to work differently and the organizational barriers removed that punish speed.
-
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.
-
The Premature Primitive Problem: More AI Agents, Same Broken Delivery
Executive Deck ↗Exec summary ↗Download EPUB ↓Friends who now lead engineering organizations keep asking about missing AI returns. I’d look at what their agents can actually test and deploy.
-
Stop Reviewing Code. Start Proving It Works. My Take on AI in the Quality Process of Software.
Executive Deck ↗Exec summary ↗Listen ↗Code review was supposed to be about rigor. It became a rubber stamp. AI review will not fix it. What fixes it is building systems that prove correctness. Continuous delivery, not ceremony.
-
We Kissed Specs and PRDs Goodbye. Product Managers Pass POCs Now.
Executive Deck ↗Exec summary ↗Listen ↗Nobody looks forward to backlog grooming. Nobody ever did. AI made it possible to skip the ceremony and hand engineering a working proof of concept instead of a story card. Here is what changes when you let it.
-
Senior: What Does That Mean?
Exec summary ↗AI is exposing senior engineers who have the title without the judgment, technical skill, and leadership the role requires.
-
If You Are Tracking Activities Without Outcomes, You Have Already Lost
Executive Deck ↗Exec summary ↗Listen ↗People trained. Workshops delivered. Pilots launched. These are activities, not outcomes. If your transformation dashboard is full of activity metrics and empty of business results, you are measuring your own comfort, not your progress.
-
Put Tokens in the P&L, Not in a Developer Expense Report
Exec summary ↗Token costs are production costs, not developer allowances. Put them in the portfolio P&L, measure human plus AI labor against accepted outcomes, and stop mistaking visible inference bills for economic governance.
-
Dear Developer: Why AI Adoption Is Slow
Executive Deck ↗Exec summary ↗Listen ↗Download EPUB ↓A letter from the executive seat to developers, managers, and directors on why AI adoption slows down when speed outruns trust, authority, and production reality.
-
Stop Budgeting Tokens by Engineer. Budget the Work.
Executive Deck ↗Exec summary ↗Per-engineer token caps optimize the most visible cost while hiding labor, delay, and business value. Budget AI production by accepted outcome, not individual contributor.
Corporate fiction
Three books. One operating problem. No clean hero.
Read 2028, Meridian, and AgentDrivenDevelopment.com’s Survive free online.
Read free online →