Building AI Agents that actually work (Full Course)

章节 1：引言与核心概念——聊天模型（Chat Models）与AI智能体（AI Agents）的区别

📝 本节摘要：

本节由主持人Greg开场，点明当前AI领域充斥着晦涩难懂的术语（如Skills, MCPs等），并邀请专家Remy针对初学者进行概念拆解与实战指导。Remy指出，AI的发展已正式从“聊天（Chat）”迈入“智能体（Agent）”的第二阶段，使用智能体能带来10到20倍的生产力飙升。本章的核心在于明确定义了两者的本质区别：聊天模型是“提问与回答”（类似打乒乓球），而AI智能体则是“接收目标与交付结果”。智能体会自动进行规划并执行任务，取代了人类在传统AI问答后需要手动落实的工作。

[原文] [Greg]: i think ai is confusing there i said it i think there's a lot of terms skills mcps agent harnesses that are difficult concepts to understand so i had my friend remy come on the podcast and explain it in the most simple terms possible in this free course on how to master ai agents he breaks down exactly what each piece is how they connect together and the simplest ways beginners could start using them today enjoy the episode

[译文] [Greg]: 我认为人工智能（AI）令人困惑，是的，我直说了。我认为有很多术语，比如“技能（Skills）”、“模型上下文协议（MCPs）”、“智能体平台（Agent Harnesses）”，这些都是很难理解的概念。所以我邀请了我的朋友Remy来播客，在这个关于如何掌握AI智能体（AI Agents）的免费课程中，用最简单的语言来解释它。他精确地拆解了每一个组件是什么，它们是如何连接在一起的，以及初学者今天就可以开始使用它们的最简单方法。请享受这期节目！

[原文] [Greg]: i beg them to come on remy gasill's on the pod you've structured your company where you basically have these folders and md files that run your company and what i want to do today is i want you to teach people in a beginnerfriendly fashion this is only for beginners how they could do the same thing how they can set up their own executive assistant head of marketing chief financial officer basically i want you to bas to tell us the concepts behind all this by the end of this episode remy do you think you can do that

[译文] [Greg]: 我恳求他来参加节目，Remy Gasill现在就在播客上。你构建公司的方式是，你基本上是用这些文件夹和md（Markdown）文件来运营你的公司。而我今天想做的是，我希望你以一种对初学者友好的方式——这完全是为初学者准备的——教教大家他们该如何做同样的事情，他们如何能设置自己的执行助理（Executive Assistant）、营销主管（Head of Marketing）、首席财务官（Chief Financial Officer）。基本上，我希望你在这期节目结束前告诉我们所有这些背后的概念。Remy，你觉得你能做到吗？

[原文] [Remy]: 100% greg we're going to go through all the concept s that make up an ai agent and by the end of this video you will know exactly how you can build up um agents to run complete departments of your life and your company within any agent platform you choose whether it's claude code codeex open claw manis all of them

[译文] [Remy]: 百分之百没问题，Greg。我们将梳理构成AI智能体（AI Agent）的所有概念。在这个视频结束时，你将确切地知道如何建立……呃，智能体，来运营你生活和公司中的完整部门，而且可以在你选择的任何智能体平台（Agent Platform）中进行，无论是Claude Code、CodeEx、OpenClaw、Manis，所有这些都可以。

[原文] [Greg]: all right let's do it

[译文] [Greg]: 好的，我们开始吧。

[原文] [Remy]: sweet so one of the reasons why i really wanted to make this episode is because i feel like the ai landscape is moving into like stage two from chat to agents and most people are getting left behind right now just using the chat models and uh the founders and employees that are utilizing agents are like no word of a lie 10 to 20 times more productive in their day and when you stack that up over days weeks years you're going to just be miles ahead of the competition so i really want to make this episode today to help bring everyone up to where the ai landscape is at the moment and to start using agents to manage every department of your business

[译文] [Remy]: 太棒了。所以我非常想做这期节目的原因之一是，我觉得AI领域正在迈入第二阶段——从聊天（Chat）向智能体（Agents）转变。而现在，大多数仅仅还在使用聊天模型（Chat Models）的人正在被时代抛弃。呃，那些正在利用智能体的创始人和员工，绝不夸张地说，他们每天的生产力要高出10到20倍。当你在几天、几周、几年的时间里将其累加起来时，你将把竞争对手远远甩在后面。所以我今天真的想做这期节目，帮助每个人跟上目前AI领域的步伐，并开始使用智能体来管理你业务的每一个部门。

[原文] [Remy]: so the key thing to understand here is chat models versus age nts because the word agent is thrown around lots online and i'm sure you've seen it greg like ai agents this agents this use this agent for this and it's kind of lost a lot of meaning so i wanted to give start by giving a really clear definition of what an agent actually is

[译文] [Remy]: 所以这里要理解的关键一点是聊天模型（Chat Models）与智能体（Agents）之间的区别。因为“智能体（Agent）”这个词在网上被泛滥使用了，我相信你也见过，Greg，比如“AI智能体这个”、“智能体那个”、“用这个智能体做这个”，它某种程度上已经失去了很多真正的含义。所以我想一开始就给智能体究竟是什么下个非常清晰的定义。

[原文] [Remy]: so the way i think of it is a chat model is question to answer but then an agent is goal to result so moving from just like uh you asking ai replies then you do the work to you giving the agent a task it planning out the task and then executing and then delivering you a result does that make sense

[译文] [Remy]: 所以我的理解方式是，聊天模型（Chat Model）是“提出问题，得到答案（Question to Answer）”，而智能体（Agent）则是“设定目标，交付结果（Goal to Result）”。所以，这就像是从……呃，你提问，AI回答，然后你来做后续的工作；转变为你直接给智能体一个任务，它负责规划这个任务，然后执行，最后把结果交付给你。这说得通吗？

[原文] [Greg]: crystal clear i mean the way i think about it is chat is kind of like pingpong back and forth back and forth and agent is uh you know you're giving it it's a goal i mean the best way yeah you're giving it a goal and you're hoping that over time it gets better and closer to that goal

[译文] [Greg]: 非常清楚。我的意思是，我的理解方式是，聊天（Chat）有点像打乒乓球，来来回回，来来回回。而智能体（Agent）是……你知道，你给它一个目标，我是说最好的方式……对，你给它一个目标，然后你希望随着时间的推移，它变得越来越好，并且越来越接近那个目标。

[原文] [Remy]: exactly yeah that's exactly it and i just think that's a nice way to lay it out in your head is chat is question to answer agent is goal to re sult

[译文] [Remy]: 确实如此。对，完全就是这样。而且我认为在脑海中将其梳理清楚的一个好方法就是：聊天（Chat）是“提问对答案”，而智能体（Agent）是“目标对结果”。