Practitioner essays on building production software with AI agents.

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.

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.

AI coding platforms are becoming the system of record for software production. Govern them as lifecycle infrastructure, not developer preference.

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.

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.

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.

Your token burn is not the problem. It is the first invoice honest enough to show that your engineering work has no value discipline.

Before you optimize token spend, measure the completed work, human attention, cycle time, and risk reduction those tokens bought.

The old software heroes explain the last era. The loudest influencers explain the demo. The builders answering customers in public are the ones closest to the truth.

The irony is familiar: you debate a $400 model bill, approve a $180,000 SOW, and pay an outsider to say what your own engineers already told you.