🔶 Agent 时代的软件工程
英文标题:🔶 Software Engineering in the Agentic Era
Simon Willison 启动了“Agentic Engineering Patterns(Agent 工程模式)”项目,系统梳理如何借助 Claude Code、OpenAI Codex 等可生成并执行代码的编码 Agent 开发软件。该项目将以持续更新的“指南”和章节形式发布,首批内容讨论了代码生成成本骤降对工程实践的影响,以及 red/green TDD 如何帮助 Agent 更简洁、可靠地编写代码。作者强调,Agent 工程并非不审查代码的 vibe coding,而是专业工程师利用 Agent 放大既有能力、提升研发效率的实践。项目正文将由作者本人撰写,LLM 仅用于校对、补充示例代码等辅助任务。
136.8 KB
中文
撰写关于 Agent 工程模式的内容
2026 年 2 月 23 日
我启动了一个新项目,用于收集和记录 Agentic Engineering Patterns(Agent 工程模式)——一系列编码实践与模式,帮助人们在我们正步入的编码 Agent 开发新时代中取得最佳成果。
我所说的 Agentic Engineering(Agent 工程),是指使用编码 Agent 来构建软件——例如 Claude Code 和 OpenAI Codex。这类工具的决定性特征在于,它们既能生成代码,也能 执行 代码,因此能够测试代码,并在无需人类主管逐轮指导的情况下自行迭代。
我对 vibe coding 的理解,沿用其最初定义:即你完全不关注代码本身的编程方式。如今,它通常与非程序员使用 LLM 编写代码联系在一起。
Agent 工程则处于这个谱系的另一端:专业软件工程师利用编码 Agent 改进并加速工作,通过放大自己已有的专业能力来提升产出。
这门新兴实践有太多值得学习和探索的内容!我此前已在我的 ai-assisted-programming 标签下发布了大量文章(目前已有 345 篇且仍在增加),但这些内容相对缺乏结构。我的新目标是将其集中整理,帮助回答这样一个问题:“怎样才能从这些工具中获得好的结果?”
我会在博客上以一系列具有章节结构的模式来开发和扩展这个项目,其形式大致受到 1994 年 Design Patterns: Elements of Reusable Object-Oriented Software 所普及格式的启发。
今天我发布了前两章:
- 如今写代码很便宜 探讨了 Agent 工程的核心挑战:产出初步可运行代码的成本已几乎降至零,这将如何影响我们既有的工作直觉——无论是个人层面还是团队层面?
- Red/green TDD 介绍了测试优先开发如何以极少的额外提示,帮助 Agent 编写更简洁、更可靠的代码。
我希望以后能以每周新增 1 至 2 章的速度继续更新。我并不确定何时会停止,毕竟还有很多内容需要覆盖!
由我撰写,而非 LLM
我有一项坚定的个人原则:不会以自己的名义发布 AI 生成的文字。这项原则同样适用于 Agentic Engineering Patterns。我会使用 LLM 进行校对、补充示例代码以及处理各种其他辅助任务,但你在这里读到的文字将出自我本人。
章节与指南
Agentic Engineering Patterns 并不完全是 一本书,但它具有某种书籍般的形态。我会在网站上以一种我称为 guide(指南)的新内容形态发布它。一个指南由多个章节组成,而每个章节实际上都是一篇博客文章:其发布日期不会特别突出,并且设计上可以随着时间持续更新,而不是在首次发布时就被固定下来。
指南和章节是我对在博客中发布“常青”内容这一挑战的回应。我已经尝试寻找解决方式有一段时间了。这个形式感觉可能会长期保留下来。
如果你对实现方式感兴趣,可以查看 Guide、Chapter 和 ChapterChange 模型,以及相关的 Django views。其中几乎所有代码都是 Claude Opus 4.6 在我的 iPhone 上通过 Claude Code for web 编写的。
English / 原文
Writing about Agentic Engineering Patterns
23rd February 2026
I’ve started a new project to collect and document Agentic Engineering Patterns —coding practices and patterns to help get the best results out of this new era of coding agent development we find ourselves entering.
I’m using Agentic Engineering to refer to building software using coding agents—tools like Claude Code and OpenAI Codex, where the defining feature is that they can both generate and execute code—allowing them to test that code and iterate on it independently of turn-by-turn guidance from their human supervisor.
I think of vibe coding using its original definition of coding where you pay no attention to the code at all, which today is often associated with non-programmers using LLMs to write code.
Agentic Engineering represents the other end of the scale: professional software engineers using coding agents to improve and accelerate their work by amplifying their existing expertise.
There is so much to learn and explore about this new discipline! I’ve already published a lot under my ai-assisted-programming tag (345 posts and counting) but that’s been relatively unstructured. My new goal is to produce something that helps answer the question “how do I get good results out of this stuff” all in one place.
I’ll be developing and growing this project here on my blog as a series of chapter-shaped patterns, loosely inspired by the format popularized by Design Patterns: Elements of Reusable Object-Oriented Software back in 1994.
I published the first two chapters today:
- Writing code is cheap now talks about the central challenge of agentic engineering: the cost to churn out initial working code has dropped to almost nothing, how does that impact our existing intuitions about how we work, both individually and as a team?
- Red/green TDD describes how test-first development helps agents write more succinct and reliable code with minimal extra prompting.
I hope to add more chapters at a rate of 1-2 a week. I don’t really know when I’ll stop, there’s a lot to cover!
Written by me, not by an LLM
I have a strong personal policy of not publishing AI-generated writing under my own name. That policy will hold true for Agentic Engineering Patterns as well. I’ll be using LLMs for proofreading and fleshing out example code and all manner of other side-tasks, but the words you read here will be my own.
Chapters and Guides
Agentic Engineering Patterns isn’t exactly a book , but it’s kind of book-shaped. I’ll be publishing it on my site using a new shape of content I’m calling a guide. A guide is a collection of chapters, where each chapter is effectively a blog post with a less prominent date that’s designed to be updated over time, not frozen at the point of first publication.
Guides and chapters are my answer to the challenge of publishing “evergreen” content on a blog. I’ve been trying to find a way to do this for a while now. This feels like a format that might stick.
If you’re interested in the implementation you can find the code in the Guide, Chapter and ChapterChange models and the associated Django views, almost all of which was written by Claude Opus 4.6 running in Claude Code for web accessed via my iPhone.