什么是 Agentic Engineering？

Salesforce's engineering team evolved from relying on Copilot to building an Agentic engineering system, using three key levers—tool convergence, rule-as-code, and autonomy—to delegate SDLC execution to Agents, achieving a 79% increase in PRs, 151% higher effective output, and completing a 231-person-day API migration in just 13 days.

The article explores the author's realization that the boundaries between 'vibe coding' and 'agentic engineering' are blurring with AI-assisted programming, raising concerns about code quality and responsibility.

哥伦比亚大学Agentic Engineering课程第五讲系统解析Agent工具的定义、调用机制与工程实现，提供完整视频与讲义资源。

老旧代码库中引入代理工程需优先暴露隐藏约束，Teleport案例显示简单提示可胜过复杂系统，Zones和Blast Radius是关键实践。

Thoughtworks团队通过四天实验发现，强制rebase纪律意外催生了代理间计划同步机制，为复杂系统构建提供新思路。

Jon Udell批判‘human in the loop’术语，主张将AI代理作为团队成员协作，强调透明的agentic软件开发流程。

This article explores the necessity and practical methods of transitioning from vibe coding to spec-driven development, emphasizing the advantages of the latter in team collaboration and project management.

Andrej Karpathy提出Software 3.0范式：软件开发正从手写代码（S1.0）和机器学习建模（S2.0）转向以提示工程驱动智能体协作的新阶段，核心能力是设计提示、调试行为与编排AI工作流。

The best way to learn AI is by building with agents; hands-on labs and a new series on Agentic Engineering have been launched.

DHH在播客中畅谈AI对编程的颠覆性影响，但缺乏具体技术方案和实践案例，更适合了解行业趋势而非工程实操。

文章讨论AI原生团队构建方法，但内容不完整，缺乏技术细节和实践案例。