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
-
Introducing Synthetic Users, Customers, and Personas
Executive Deck ↗Exec summary ↗Listen ↗A synthetic user is an LLM agent calibrated to a real reader persona that can navigate your product, read your copy, and tell you what is wrong before a real customer does. Here is how to build them, where they break, and why your feedback loop is six weeks too long.
-
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.
-
The Tool Is a Commodity. The Organizational Adoption Expertise Is Not.
Executive Deck ↗Exec summary ↗Listen ↗The performance gap between top Gen AI coding tools is not what is slowing you down. Your governance model and your SDLC are. Pick the vendor who will coach your executives on how to actually build.
-
Gen 1 Lights-Off Development: I Am Building It and You Can Watch
Executive Deck ↗Exec summary ↗Listen ↗Everyone talks about autonomous AI development. Norman is actually building it. A system of agents that predicts what players want, builds a browser game, ships it, measures it, and iterates, no human in the product decision loop. Here are the rules.
-
How to Build an AI-Native Engineering Team (Not an AI-Assisted One)
Executive Deck ↗Exec summary ↗Listen ↗Most teams added AI tools and called it transformation. An AI-native engineering team requires two things most organizations are not willing to change: the staffing model and the governance model. Here is what both look like.
-
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.
-
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.
-
Dear Coding Agent Builders and Corporate Leaders Funding These Tools: Just Give Me the Best Model
Executive Deck ↗Exec summary ↗Listen ↗An open letter to the companies building AI coding tools and the leaders paying for them. You built something that made software fun again. Now stop making me think about which model I am on.
-
Your Codebase Is Not Agent-Maintainable and That Is Your Next Big Problem
Executive Deck ↗Exec summary ↗Listen ↗Mike spent three weeks trying to get AI agents to maintain his Flink pipeline. The agents were not the problem. The code was not agent-maintainable. This is a new standard, and your codebase probably fails it.
-
Customer Absorption: Your New Software Engineering Bottleneck
Executive Deck ↗Exec summary ↗Listen ↗Your engineering team can now ship a feature a day. But your customers cannot absorb a feature a day. The new bottleneck is not building. It is receiving.
Essential or Ornamental
Three companies. Three choices. One satisfactory ending.
One does nothing. One maps the waste. One bets everything on twelve people in a warehouse.
Read free online →