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.

这揭示了Agent在认知上的盲区：它容易陷入“代码视角”的自证预言，以为单元测试通过就等于功能完整。引入端到端浏览器自动化测试，是强迫Agent站在“用户视角”去验证，这是从开发者思维向产品思维跨越的关键。

Adaptive Stress Testing with Reward Augmentation for Autonomous Vehicle Validation

Sturniolo, S., Waites, W., Colbourn, T., Manheim, D., & Panovska-Griffiths, J. (2020). Testing, tracing and isolation in compartmental models. MedRxiv, 2020.05.14.20101808. https://doi.org/10.1101/2020.05.14.20101808