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
-
Are You Prematurely Optimizing the Machinery Around Your Vendor’s Agent?
Custom skills, agents, routers, and reviewer loops can improve a vendor's agent. Standardizing that extra machinery before it beats the supported baseline is premature optimization.
-
If You Make AI Scarce, Give It All to Your Best Engineers and Learn Something
Executive Deck ↗Exec summary ↗If leadership makes AI inference scarce, do not divide it equally. Give it to your best engineers, aim them at the company’s most important work, and learn what the constraint exposes.
-
Your CRM Can Cost $3.5 Million a Month. Finance Panics Over a $100,000 AI Bill. Introducing the Inference Investment Theory (IIT).
AI value is not an inference metric. Start with product outcome, cycle time, total cost, and cost of delay, then overlay inference investment.
-
The Customer Product Operating Model
Executive Deck ↗Exec summary ↗Listen ↗Your product team spends 60% of their time on coordination that agents handle in minutes. Building is no longer the bottleneck, your customer's capacity to receive what you ship is. The operating model that wins is embarrassingly simple: talk to customers, figure out what to build, ship it, make sure it lands.
-
Would You Spend 150% of the Labor Cost to Ship Today?
Price the outcome before its tokens. A rational token budget is a function of total delivery economics, and even 150% of labor cost can make sense when it buys enough time.
-
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.
-
Every Engineer Has Four Jobs Now: Track the Models, Learn the Techniques, Know the Customer, Build the Software
Being an AI power user is no longer a specialist role. Every engineer must track the models, master the techniques, know the customer, and judge the software agents produce.
-
Everything You Learned About the Testing Pyramid Was Based on a Constraint That No Longer Exists
Executive Deck ↗Exec summary ↗Listen ↗The Testing Pyramid was never a technical ideal. It was a financial compromise based on the cost of human capital. In an agent-driven world, that constraint disappears and the pyramid becomes a square. Equal investment across every test type. Maximum risk buydown. No excuses.
-
Your AI Coding Platform Is Becoming PLM. Stop Running the Decision Like Homecoming Court.
Executive Deck ↗Exec summary ↗Listen ↗Download EPUB ↓AI coding platforms are becoming the system of record for software production. Govern them as lifecycle infrastructure, not developer preference.
-
Before You Build a Token Economics Dashboard, Build a Value Dashboard
Executive Deck ↗Exec summary ↗Listen ↗Download EPUB ↓Before you optimize token spend, measure the completed work, human attention, cycle time, and risk reduction those tokens bought.
Corporate fiction
Three books. One operating problem. No clean hero.
Read 2028, Meridian, and AgentDrivenDevelopment.com’s Survive free online.
Read free online →