什么是代理工程？

什么是代理工程？
What is agentic engineering?

原始链接: https://simonwillison.net/guides/agentic-engineering-patterns/what-is-agentic-engineering/

## 代理工程：摘要代理工程利用“编码代理”——如Claude Code或Gemini CLI等既能编写又能执行代码的AI——来构建软件。这些代理通过迭代生成和运行代码的循环运作，由用户定义的目标驱动。执行代码的能力至关重要，将LLM的输出从建议转变为可证明的有效解决方案。然而，代理工程并不能取代软件工程师。相反，它将重点从编写代码转移到定义需要编写的代码、权衡解决方案以及确保质量。成功需要为代理提供合适的工具、详细的问题规范以及验证和迭代改进的流程。重要的是，代理通过更新的指令和工具集学习，而不是固有记忆。这个不断发展的领域需要持续学习和适应，有可能通过提高生产力和代码质量来解锁更雄心勃勃且具有影响力的软件项目。本指南旨在记录与这些快速发展的工具合作的有效且适应性强的模式。

## Agentic 工程：摘要 Hacker News 上讨论了一种名为“Agentic 工程”的方法，即*与* AI 编码代理一起开发软件，而非*通过*传统方式。有些人认为这只是现有软件工程中的一种新技术，而另一些人则认为关键区别在于：**责任归属**。传统上，工程师对其代码负全责；而使用 AI 生成的代码，这条界限变得模糊。核心思想是利用这些“代理”将文档自动转换为可运行的代码，超越了旧的“瀑布式”文档方法的局限性。它正在演进，不再仅仅是简单的“提示工程”——即复制/粘贴代码片段——而是允许 AI 直接修改代码库。然而，也存在怀疑论。一些人预计随着最初的炒作消退，会出现“修正”，并指出人们可能高估了当前 AI 的能力。争论的焦点在于 *何时* 使用 Agentic 工程比传统方法更合适，以及它是否代表一门新的学科，还仅仅是工作流程的转变。

原文

I use the term agentic engineering to describe the practice of developing software with the assistance of coding agents.

What are coding agents? They're agents that can both write and execute code. Popular examples include Claude Code, OpenAI Codex, and Gemini CLI.

What's an agent? Clearly defining that term is a challenge that has frustrated AI researchers since at least the 1990s but the definition I've come to accept, at least in the field of Large Language Models (LLMs) like GPT-5 and Gemini and Claude, is this one:

Agents run tools in a loop to achieve a goal

You prompt the coding agent to define a goal. The agent then generates and executes code in a loop until that goal has been met.

Code execution is the defining capability that makes agentic engineering possible. Without the ability to directly run the code, anything output by an LLM is of limited value. With code execution, these agents can start iterating towards software that demonstrably works.

Agentic engineering

Now that we have software that can write working code, what is there left for us humans to do?

The answer is so much stuff.

Writing code has never been the sole activity of a software engineer. The craft has always been figuring out what code to write. Any given software problem has dozens of potential solutions, each with their own tradeoffs. Our job is to navigate those options and find the ones that are the best fit for our unique set of circumstances and requirements.

Getting great results out of coding agents is a deep subject in its own right, especially now as the field continues to evolve at a bewildering rate.

We need to provide our coding agents with the tools they need to solve our problems, specify those problems in the right level of detail, and verify and iterate on the results until we are confident they address our problems in a robust and credible way.

LLMs don't learn from their past mistakes, but coding agents can, provided we deliberately update our instructions and tool harnesses to account for what we learn along the way.

Used effectively, coding agents can help us be much more ambitious with the projects we take on. Agentic engineering should help us produce more, better quality code that solves more impactful problems.

About this guide

Just like the field it attempts to cover, Agentic Engineering Patterns is very much a work in progress. My goal is to identify and describe patterns for working with these tools that demonstrably get results, and that are unlikely to become outdated as the tools advance.

I'll continue adding more chapters as new techniques emerge. No chapter should be considered finished. I'll be updating existing chapters as our understanding of these patterns evolves.