The 'I know it works' merge moment captures something real: human engineers have a holistic intuition about whether a change is safe that current agents lack. Video-based verification is a fascinating workaround — using visual confirmation of a running application as a proxy for correctness. This suggests the testing problem for async agents is fundamentally different from unit tests: it requires environmental validation, not just logical assertion.

大多数人可能认为高质量软件的创造完全依赖于AI或完全依赖于人类工程师，但作者提出了一个折中的方法，即结合使用AI和直接编码。

大多数人认为糟糕的软件质量是技术限制、时间压力或复杂性的必然结果，但作者断言这实际上是一个有意识的选择。这一观点挑战了软件开发中常见的借口文化，暗示质量问题本质上是责任和决策问题，而非客观约束。

YES. This feel similar to the way that TDD can also improve the code that you write, but with a broader/more comprehensive outlook.