一句话：用系统思维揭示 AI 编码助手如何切断文档反馈回路，进而导致文档与代码质量螺旋式下降。
软件文档团队长期依赖开发者行为（阅读文档、提问、提交 issue）作为发现并修正文档问题的信号。随着 AI 编码助手改变开发者获取信息的方式，这些反馈渠道受到冲击却少有人关注：当开发者不再阅读文档、不再提问，文档团队便失去了定位与修复问题所需的信号。本文是一篇立场论文，采用系统思维（systems thinking）方法，刻画了智能体中介的信息获取如何破坏当前维持文档质量的平衡回路（balancing loops），并论证这种破坏会形成不断放大、随时间推移降低文档与代码质量的增强回路（reinforcing loops）。作者进一步识别出若干杠杆点：研究者可据此开发面向智能体中介使用的质量度量与自校正文档系统，系统设计者则可向文档团队暴露智能体的消费模式。文章呼吁研究社区系统性地研究智能体中介的文档消费如何重塑文档及其质量。
Software documentation teams rely on developer activity to identify and correct problems in their content. As AI coding assistants reshape how developers seek information, their impact on software documentation feedback channels has gone largely unnoticed. When developers reduce reading documentation and stop posting questions, documentation teams lose the signals they need to find and fix problems. We use systems thinking to trace how agent-mediated information seeking disrupts the balancing loops that currently contribute to documentation quality and how this disruption would create reinforcing loops that degrade documentation and code quality over time. We identify leverage points where researchers can develop quality metrics and self-correcting documentation systems for agent-mediated use, and system designers can surface agent consumption patterns to documentation teams. Through this position paper, we call on the research community to investigate how agent-mediated documentation consumption reshapes documentation and its quality.