1
00:00:00,280 --> 00:00:00,720
Well.
出色地。

2
00:00:00,720 --> 00:00:01,160
Hello.
你好。

3
00:00:01,200 --> 00:00:02,400
My name's Ed Donner.
我叫埃德·唐纳。

4
00:00:02,440 --> 00:00:06,880
I'm a two time AI startup co-founder and a former managing director for J.P. Morgan.
我是两次人工智能初创公司的联合创始人，也是摩根大通的前董事总经理。

5
00:00:06,880 --> 00:00:10,240
And I'm about to take you on a wild ride.
我要带你去一次疯狂的旅程。

6
00:00:10,280 --> 00:00:13,920
We're going to be spending the next six weeks together on an adventure.
我们将在接下来的六周里一起冒​​险。

7
00:00:14,000 --> 00:00:17,800
I've actually just finished myself doing the six weeks worth of projects.
事实上，我刚刚完成了为期六周的项目。

8
00:00:17,800 --> 00:00:23,000
There are eight projects along the way, and I can tell you I have some astonishing things in store
一路上有八个项目，我可以告诉你我有一些令人惊讶的东西

9
00:00:23,000 --> 00:00:24,760
for you and I can't wait to get started.
你和我都迫不及待地想开始。

10
00:00:24,760 --> 00:00:25,600
Let's do this!
让我们这样做吧！

11
00:00:26,200 --> 00:00:30,560
Now, it's customary with these things to kick off with an introduction to myself and talk about the
现在，习惯上这些事情都是以自我介绍开始并谈论

12
00:00:30,600 --> 00:00:35,400
goals of the course, but people who've taken my courses before will know that I don't like doing that.
课程的目标，但以前参加过我的课程的人会知道我不喜欢这样做。

13
00:00:35,440 --> 00:00:36,360
Let's not do that.
我们不要那样做。

14
00:00:36,360 --> 00:00:38,200
Let's get straight to action.
让我们直接开始行动吧。

15
00:00:38,200 --> 00:00:44,200
Let's go and see some autonomous AI agents in practice, and we'll come back and do that other stuff
让我们去看看一些自主人工智能代理的实践，然后我们回来做其他的事情

16
00:00:44,200 --> 00:00:44,640
later.
之后。

17
00:00:45,560 --> 00:00:51,720
So I've taken us now to the app N810, which is an exciting app that is definitely generating interest.
现在我将带我们了解 N810 应用程序，这是一款令人兴奋的应用程序，肯定会引起人们的兴趣。

18
00:00:51,720 --> 00:00:58,680
This is an example of one of these low code or no code workflow apps that allows you to construct a
这是这些低代码或无代码工作流程应用程序之一的示例，可让您构建

19
00:00:58,680 --> 00:01:04,090
workflow of orchestrating between different applications and build it without necessarily needing to
在不同应用程序之间编排并构建它的工作流程，而无需

20
00:01:04,090 --> 00:01:05,410
write any code yourself.
自己编写任何代码。

21
00:01:05,730 --> 00:01:11,650
The difference with some of the other workflow tools like this is that it has generative AI built into
与其他一些类似的工作流程工具的区别在于，它内置了生成式人工智能

22
00:01:11,650 --> 00:01:15,330
it, and that's why people are so excited about N810.
这就是人们对 N810 如此兴奋的原因。

23
00:01:15,610 --> 00:01:21,530
So if you come to N810, which is the cloud version of it, you can also download it and run it locally.
所以如果你来到N810，它是它的云版本，你也可以下载并在本地运行。

24
00:01:21,530 --> 00:01:23,210
But here we're using it in the cloud.
但这里我们在云中使用它。

25
00:01:23,210 --> 00:01:26,850
You can press Get Started and set up an account if you want to do this yourself.
如果您想自己执行此操作，可以按开始并设置帐户。

26
00:01:26,850 --> 00:01:28,010
Or you can just watch me.
或者你可以看着我。

27
00:01:28,010 --> 00:01:31,170
But it might be fun to try this out yourself if you haven't used it before.
但如果您以前没有使用过，那么亲自尝试一下可能会很有趣。

28
00:01:31,490 --> 00:01:37,050
So I've set up an account, I've done that, and once I've signed in, I get this beginning screen to
所以我已经设置了一个帐户，我已经完成了该操作，一旦我登录，我就会看到这个开始屏幕

29
00:01:37,090 --> 00:01:38,810
add my first step.
添加我的第一步。

30
00:01:38,810 --> 00:01:42,490
You can also use one of their templates right off the bat if you want to, but we're going to build
如果您愿意，您也可以立即使用他们的模板之一，但我们将构建

31
00:01:42,490 --> 00:01:44,210
something ourselves right now.
我们现在的一些事情。

32
00:01:44,490 --> 00:01:46,170
So we're going to add a first step.
所以我们要添加第一步。

33
00:01:46,170 --> 00:01:51,010
And what we're going to do is we're going to begin by starting with a chat message.
我们要做的是从聊天消息开始。

34
00:01:51,290 --> 00:01:57,130
So this if I go back to the canvas here, you press back to canvas on the top left.
所以如果我回到这里的画布，你按回到左上角的画布。

35
00:01:57,130 --> 00:02:03,130
We can now see this canvas which is showing that we have a chat box here that's represented by this
我们现在可以看到这个画布，它显示我们这里有一个聊天框，用这个表示

36
00:02:03,130 --> 00:02:04,770
chat window down here.
聊天窗口在下面。

37
00:02:05,070 --> 00:02:09,030
and we can chat and do something as a result of that chat.
我们可以聊天并通过聊天做一些事情。

38
00:02:09,070 --> 00:02:10,430
So what do we want to do?
那么我们想要做什么呢？

39
00:02:10,870 --> 00:02:16,430
Well, we press the plus button right here and we come over to the right and we decide that we want
好吧，我们按下这里的加号按钮，我们走到右边，我们决定我们想要

40
00:02:16,430 --> 00:02:18,710
to have advanced AI.
拥有先进的人工智能。

41
00:02:19,270 --> 00:02:22,950
And we're going to create an AI agent right here.
我们将在这里创建一个人工智能代理。

42
00:02:23,150 --> 00:02:28,230
And now, if I go back to canvas, I'll show you that what we have in our canvas now is a chat message
现在，如果我回到画布，我会向您展示画布中现在有一条聊天消息

43
00:02:28,230 --> 00:02:31,430
going into an AI agent representing by this box.
进入由该框代表的人工智能代理。

44
00:02:31,750 --> 00:02:34,350
And then something can come out at the back of that.
然后后面就会出现一些东西。

45
00:02:34,630 --> 00:02:36,190
And you don't need to know all of the details here.
您无需了解此处的所有详细信息。

46
00:02:36,190 --> 00:02:37,550
This is more to give you an idea.
这更多的是给你一个想法。

47
00:02:37,590 --> 00:02:39,270
And by all means you can play with this yourself.
无论如何，你可以自己玩这个。

48
00:02:39,270 --> 00:02:42,110
But most of this course is going to be about building things like this.
但本课程的大部分内容都是关于构建这样的东西。

49
00:02:42,430 --> 00:02:43,910
But let's give this a shot.
但让我们试一试。

50
00:02:43,910 --> 00:02:46,990
So the next thing we can do is add a chat model.
所以我们接下来要做的就是添加聊天模型。

51
00:02:46,990 --> 00:02:50,870
And this is a large language model that's going to sit behind this AI agent.
这是一个大型语言模型，将位于该人工智能代理的后面。

52
00:02:51,030 --> 00:02:54,270
And I'm going to pick open AI chat model.
我将选择开放式人工智能聊天模型。

53
00:02:54,390 --> 00:02:58,270
Now that's because I have an open AI key which will be setting up for you if you don't have one already
那是因为我有一个开放的 AI 密钥，如果您还没有，它会为您设置

54
00:02:58,270 --> 00:02:58,990
quite soon.
很快。

55
00:02:59,030 --> 00:03:04,790
And alternatively, if you don't want to do this, you can use Olama instead and run for free, but
或者，如果您不想这样做，您可以使用 Olama 代替并免费运行，但是

56
00:03:04,790 --> 00:03:10,960
you would then have to install it Locally, but I've set up my OpenAI account and you can do this yourself.
然后你必须在本地安装它，但我已经设置了我的 OpenAI 帐户，你可以自己安装。

57
00:03:11,120 --> 00:03:16,800
All you do is you come down here and you press create New credential and you type in your API key.
您所要做的就是来到这里，按下“创建新凭证”，然后输入您的 API 密钥。

58
00:03:16,920 --> 00:03:18,000
But I've done that already.
但我已经这么做了。

59
00:03:18,000 --> 00:03:20,440
So my OpenAI account is linked.
这样我的 OpenAI 帐户就被链接了。

60
00:03:20,480 --> 00:03:21,720
It's as simple as that.
就这么简单。

61
00:03:21,760 --> 00:03:22,760
And here it is.
就是这样。

62
00:03:22,800 --> 00:03:28,280
It looks here OpenAI chat is connected to my chat model.
看起来 OpenAI 聊天已连接到我的聊天模型。

63
00:03:28,280 --> 00:03:29,280
So far so good.
到目前为止，一切都很好。

64
00:03:29,480 --> 00:03:30,680
Let's keep moving.
让我们继续前进吧。

65
00:03:30,720 --> 00:03:32,680
We're now going to add in a tool.
我们现在要添加一个工具。

66
00:03:32,800 --> 00:03:38,160
Now, tools are one of the most fundamental building blocks of a gigantic AI.
现在，工具是庞大人工智能最基本的构建模块之一。

67
00:03:38,360 --> 00:03:41,120
And this week is going to be a lot about building tools.
本周将有很多关于构建工具的内容。

68
00:03:41,520 --> 00:03:46,160
So I pressed the plus button to open up the list of tools that I could connect with the AI agent.
因此，我按下加号按钮打开可以与人工智能代理连接的工具列表。

69
00:03:46,160 --> 00:03:50,520
And you can see there's a large number of tools, a lot of different things that this agent could,
你可以看到有大量的工具，这个代理可以做很多不同的事情，

70
00:03:50,520 --> 00:03:52,560
could use, could take advantage of.
可以利用，可以利用。

71
00:03:52,600 --> 00:03:54,920
It could do calculations with a calculator.
它可以用计算器进行计算。

72
00:03:54,920 --> 00:04:01,640
It can book meetings using my Google calendar or read my emails, look at my Facebook timeline, lots
它可以使用我的 Google 日历预订会议或阅读我的电子邮件、查看我的 Facebook 时间线等等

73
00:04:01,640 --> 00:04:04,600
of things that it can do, as you will see here, read Hacker News for me.
正如您将在这里看到的，它可以做的事情，请为我阅读《黑客新闻》。

74
00:04:04,600 --> 00:04:05,800
I would like that.
我愿意。

75
00:04:05,800 --> 00:04:10,220
Okay, but we're going to go all the way down and we're going to find something here that I just want
好吧，但我们要一直往下走，我们会在这里找到我想要的东西

76
00:04:10,260 --> 00:04:13,620
to show off, which is the Philips Hue tool.
炫耀一下，这就是飞利浦Hue工具。

77
00:04:13,700 --> 00:04:15,140
I don't know if you know about Philips Hue.
不知道你是否了解飞利浦Hue。

78
00:04:15,180 --> 00:04:17,660
It's something which is, uh, gives you light bulbs.
它是，呃，给你电灯泡的东西。

79
00:04:17,660 --> 00:04:22,620
And I have a lot of light bulbs in my apartment here, and we're just going to pick a light bulb.
我的公寓里有很多灯泡，我们只需要挑选一个灯泡即可。

80
00:04:22,620 --> 00:04:24,660
This one here called the bed strip.
这里称为床条。

81
00:04:24,900 --> 00:04:26,580
And we can add a field.
我们可以添加一个字段。

82
00:04:26,580 --> 00:04:27,900
We'll say brightness.
我们会说亮度。

83
00:04:28,700 --> 00:04:33,140
We'll let the AI automatically choose what it wants to do with brightness.
我们会让人工智能自动选择它想要对亮度做什么。

84
00:04:33,340 --> 00:04:36,540
We'll add a field hue which is like the color.
我们将添加一个类似于颜色的场色调。

85
00:04:36,780 --> 00:04:38,460
And we'll let that do that too.
我们也会让它这样做。

86
00:04:38,460 --> 00:04:39,740
And that's all there is to it.
这就是全部内容。

87
00:04:39,780 --> 00:04:45,700
We've now when I go back to the canvas, you'll see that we have given a tool to this agent that you
现在，当我回到画布时，您会看到我们已经为该代理提供了一个工具，您可以使用它

88
00:04:45,700 --> 00:04:50,860
can see visually here, that it is able to control the Philips Hue light bulb.
在这里可以直观地看到，它能够控制飞利浦 Hue 灯泡。

89
00:04:51,260 --> 00:04:56,860
So here we are looking at our chat, our agent, the LM and the tool.
所以在这里我们关注的是我们的聊天、我们的代理、LM 和工具。

90
00:04:56,900 --> 00:05:01,300
Let's get going with bringing up the chat message that's associated with this input.
让我们开始显示与此输入关联的聊天消息。

91
00:05:01,460 --> 00:05:04,020
And let's say well hi there.
让我们打个招呼吧。

92
00:05:04,740 --> 00:05:08,220
And you can see it working and thinking hello, how may I assist you today.
您可以看到它正在工作并思考“你好，今天我可以为您提供什么帮助”。

93
00:05:08,420 --> 00:05:13,150
Let's say please Turn the lights on.
假设请把灯打开。

94
00:05:13,550 --> 00:05:15,350
Bright white.
亮白色。

95
00:05:16,630 --> 00:05:17,230
And let's see.
让我们看看。

96
00:05:17,270 --> 00:05:18,270
And bam!
砰！

97
00:05:18,790 --> 00:05:19,870
Did you see that coming?
你看到了吗？

98
00:05:20,110 --> 00:05:24,230
On come the lights that I am, in fact, wearing my light strip.
事实上，我戴着灯带，灯亮了。

99
00:05:24,510 --> 00:05:25,990
Uh, so here we go.
呃，所以我们开始吧。

100
00:05:26,150 --> 00:05:28,150
Now, you may say to me, okay, that's cool.
现在，你可能会对我说，好吧，那很酷。

101
00:05:28,150 --> 00:05:29,870
I see tools in action.
我看到工具正在发挥作用。

102
00:05:29,870 --> 00:05:31,950
I see an LM that I'm chatting with.
我看到一个 LM 正在跟我聊天。

103
00:05:31,990 --> 00:05:34,150
It's controlling my lights in my apartment.
它控制着我公寓里的灯。

104
00:05:34,190 --> 00:05:34,910
Great.
伟大的。

105
00:05:34,910 --> 00:05:36,910
But it's not really showing me autonomy.
但这并没有真正向我展示自主权。

106
00:05:36,910 --> 00:05:39,830
I'm not seeing something where it's making its own decision.
我没有看到它自己做出决定的事情。

107
00:05:39,830 --> 00:05:41,510
Well, then let me show you that.
好吧，那么让我告诉你。

108
00:05:41,510 --> 00:05:46,350
So to make it autonomous, we need to give this agent some agency.
因此，为了使其自治，我们需要给这个代理一些代理权。

109
00:05:46,350 --> 00:05:49,630
So let's say please pick a color.
所以假设请选择一种颜色。

110
00:05:50,590 --> 00:06:00,190
Let's say, uh, either deep red or deep blue and change the lights to that color.
假设，呃，深红色或深蓝色，然后将灯光更改为该颜色。

111
00:06:01,030 --> 00:06:02,430
Let's see how it does with that.
让我们看看它是如何做到的。

112
00:06:03,030 --> 00:06:05,910
And there we go a lovely red comes out.
就这样，一种可爱的红色出现了。

113
00:06:05,950 --> 00:06:07,230
Fantastic.
极好的。

114
00:06:07,230 --> 00:06:08,590
So there you have it.
这样你就得到了。

115
00:06:08,630 --> 00:06:10,470
We have an autonomous agent.
我们有一个自主代理。

116
00:06:10,510 --> 00:06:16,330
Maybe it's a simple task, but nonetheless, you just saw it making its own decision, picking red over
也许这是一个简单的任务，但尽管如此，你只是看到它做出自己的决定，选择红色

117
00:06:16,330 --> 00:06:21,610
blue and changing the light bulb all through Nathan's web app.
蓝色并通过 Nathan 的网络应用程序更换灯泡。

118
00:06:22,370 --> 00:06:27,970
So look, that was a bit small and superficial, but nonetheless, it was our first foray into the world
所以看，这有点小和肤浅，但尽管如此，这是我们第一次涉足这个世界

119
00:06:27,970 --> 00:06:29,010
of Agentic AI.
代理人工智能。

120
00:06:29,290 --> 00:06:32,770
And I strongly encourage you to go and take a look at N810.
我强烈建议您去看看N810。

121
00:06:32,890 --> 00:06:34,650
It's so easy to use.
它非常容易使用。

122
00:06:34,650 --> 00:06:40,610
It's so quick to set up an account, to hook up a web form to your Google Calendar, and lots of other
设置帐户、将网络表单连接到 Google 日历以及许多其他功能都非常快捷

123
00:06:40,610 --> 00:06:46,690
things to try out, and it gives you a nice hands on sense of what it's like to work with agents.
可以尝试的事情，它可以让您很好地了解与代理商合作的感觉。

124
00:06:46,930 --> 00:06:52,970
But I should say, this is the last time that we'll be using a tool, a low code, no code tool like
但我应该说，这是我们最后一次使用工具，低代码，无代码工具，如

125
00:06:52,970 --> 00:06:53,250
this.
这。

126
00:06:53,250 --> 00:06:58,210
As a user of AI, for the next six weeks, we're going to be rolling up our sleeves and we're going
作为人工智能的用户，在接下来的六周里，我们将卷起袖子，我们将

127
00:06:58,210 --> 00:06:59,810
to be coding agents.
成为编码剂。

128
00:06:59,810 --> 00:07:05,570
We're going to be building them ourselves and working with frameworks that allow us to build and have
我们将自己构建它们，并使用允许我们构建和拥有的框架

129
00:07:05,570 --> 00:07:10,250
different agents interact, be orchestrated to solve problems.
不同的代理相互作用，被协调来解决问题。

130
00:07:10,730 --> 00:07:11,290
Okay.
好的。

131
00:07:11,570 --> 00:07:14,890
So in the next lecture, I will tell you more about what I have in store for you.
因此，在下一堂课中，我将向您详细介绍我为您准备的内容。

132
00:07:14,930 --> 00:07:15,570
See you then.
到时候见。