Research seriesL2paper
When one engineer holds the full context, plan, and intent for a feature, driving it end-to-end with an AI coding assistant can beat splitting the work across a team. This series builds the argument from evidence: why shared development pays a coordination tax that grows with team size, why context and cognitive load — not typing speed — are the real bottleneck, what AI assistants actually change by compressing the design-implement-test-refactor loop into a single continuous flow, when the single-conductor model delivers faster and more consistent results, and where genuine collaboration still wins. Grounded in Brooks' communication-overhead law, Conway's Law, cognitive-load and flow research, the GitHub Copilot productivity randomized trial, and the DORA delivery-performance findings.
Every extra person on a task adds communication paths, context transfers, and a serial fraction that no amount of parallel effort can outrun.
The scarce resource in software work is not typing speed or headcount, but the human working memory that holds a problem whole.
The lever an AI coding assistant pulls is not typing speed; it is the latency of the loop between writing a change and knowing whether it worked.
For bounded, well-planned work, one engineer holding the whole and directing AI like a conductor keeps every part in rhythm that a divided team cannot.
The single-owner model is powerful and bounded; naming exactly where a second mind earns its cost is what keeps the model honest.