什么是代理人？

Welcome to 2025’s edition of “term so overused to mean so many different things that it starts to lose any real meaning in conversation because everyone is confidently using it to refer to different things.”

欢迎来到 2025 年的“这个术语被过度使用，以至于意味着许多不同的东西，以至于在对话中开始失去任何真正的意义，因为每个人都自信地用它来指代不同的事物。”

If you are a builder trying to build agentic solutions, this article might not be for you. This article is for those who have been in a meeting, a board room, or a conversation, with someone talking about AI agents and are either (a) not really sure what an agent is and how it is different from the generative AI capabilities we’ve seen so far, (b) not really sure the person using the term knows what an agent is, or (c) might have thought that they knew what an agent is until reading the first sentence of this article.

如果你是一个试图构建代理解决方案的开发者，这篇文章可能不适合你。这篇文章是为那些在会议、董事会或对话中，听到有人谈论 AI 代理，并且 (a) 不太确定代理是什么以及它与我们迄今看到的生成 AI 能力有何不同，(b) 不太确定使用这个术语的人是否知道代理是什么，或者 (c) 可能在阅读这篇文章的第一句之前认为自己知道代理是什么的人。

While we will reference Windsurf in this article to make some theoretical concepts more tractable, this is not a sales pitch.

虽然我们将在本文中提到 Windsurf 以使一些理论概念更易于理解，但这并不是一次销售推介。

Let’s get started.

让我们开始吧。

The very basic core idea

非常基本的核心思想

To answer the title of this article, an agentic AI system can simply be thought of as a system that takes a user input and then performs alternating calls to:

为了回答本文的标题，代理 AI 系统可以简单地被视为一个接受用户输入并执行交替调用的系统：

• An LLM (we call this the “reasoning model”) to decide what action to take given the input, potential additional automatically retrieved context, and the accumulating conversation. The reasoning model will output (a) text that reasons through what the next action should be and (b) structured information to specify the action (which action, value for input parameters of the action, etc). The output “action” could also be that there are no actions left to be taken.

  一个 LLM（我们称之为“推理模型”）根据输入、潜在的额外自动检索的上下文和累积的对话来决定采取什么行动。推理模型将输出 (a) 理清下一步行动应该是什么的文本，以及 (b) 结构化信息以指定该行动（哪个行动、行动的输入参数值等）。输出的“行动”也可能是没有剩余的行动可采取。

• Tools, which don’t have...