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.

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.