[MUSIC PLAYING] Hi, everyone. I'm so excited to be part of this conference

【音樂播放】大家好。我很興奮能參加這個會議。

and share with you five practical steps from software developer to AI engineer. And if anyone is wondering here, this avatar on the slide,

並與您分享從軟體開發者到AI工程師的五個實用步驟。如果有人在這裡感到疑惑，這張投影片上的頭像，

this is what happens if you ask AI to make you

這就是當你請 AI 幫你做時會發生的事情

look a little bit more agentic. All right, let's get started. So I'm pretty sure everyone is familiar with this image here. And the post from SWIX that defines the new role of the AI

看起來有點更有代理性。好的，讓我們開始吧。所以我相信大家對這張圖片都很熟悉。還有 SWIX 的這篇文章，定義了人工智慧的新角色。

engineer. And as you've experienced probably daily in your jobs, you don't need to be a full ML researcher anymore or data

工程師。而且，就像您在工作中可能每天都會經歷的那樣，您不再需要成為一個完整的ML研究員或數據科學家。

scientist. Things that took months or years before to get AI projects

科學家。以前需要幾個月或幾年的時間才能完成的AI專案

into production is now able to being just a couple of API

進入生產現在可以開始只需幾個API

calls.

呼叫。

Super exciting. But still, if you're working with AI,

超級刺激。但是，如果你正在和人工智慧合作，

it still makes sense to understand the basics of the technology.

它仍然有意義了解技術的基礎。

And this involves a couple of things, right?

這涉及到一些事情，對吧？

So you have to understand at a basic level how foundation models work. Why they're sometimes producing output that you don't expect in your application code, right? You have to understand how you can customize the models,

所以你必須基本了解基礎模型是如何運作的。為什麼有時候會在應用程式碼中產生你意想不到的輸出呢？你必須了解如何自訂這些模型。

how you can, for example, sometimes fine tune models to adapt them to your specific use cases

如何可以，例如，有時微調模型以適應您的特定使用情境

and data sets, how to include functions in your application

和數據集，如何在您的應用程式中包含函數

code to give them access to additional systems. The good news is if you're just starting on this journey to become an AI engineer, there's plenty of resources now these days available to you to learn. And I wanted to call out one specific course here, which is called Generative AI with Large Language Models. A few colleagues of mine, we actually collaborated with Andrew Ng and the team at deeplearning.ai

代碼以讓他們存取其他系統。好消息是，如果您剛開始踏上成為 AI 工程師的旅程，現在有很多資源可供您學習。我想在這裡特別提到一門課程，名為「使用大型語言模型進行生成式 AI」。我和幾位同事實際上與 Andrew Ng 和 deeplearning.ai 團隊合作。

to put this course together and help you understand the fundamentals of generative AI to help you build real world applications.

將這門課程組合在一起，幫助您了解生成式人工智慧的基礎，以幫助您建立真實世界的應用程式。

If you're curious, it's available on deeplearning.ai and on Coursera.

如果您感到好奇，可以在 deeplearning.ai 和 Coursera 上找到。

Now, the second step in this journey

現在，這段旅程的第二步

is to start get hands on with the AI developer tools to help you increase your productivity.

開始親自使用人工智慧開發工具，幫助您提高生產力。

And I think we're all seeing this quote here, and we experienced it in our daily jobs that how we do work, how we develop applications

我想我們都看到這裡的引述，並且在我們日常工作中體驗到，我們如何工作，如何開發應用程式

has changed a lot. These days, we can literally use natural language inputs

已經改變了很多。這些天，我們可以真正使用自然語言輸入

to interact with applications, and really, English

與應用程式互動，而實際上，英文

has become one of the most popular and hottest

已成為最受歡迎和最熱門的之一

programming languages. I think we can see this happening.

程式語言。我認為我們可以看到這種情況發生。

For example, you can go these days from English to code

例如，您可以從英文轉換為程式碼。

by asking AI to, for example, rewrite a README file. We can also do code to English.

透過要求 AI 來，例如，重新撰寫 README 檔案。我們也可以將程式碼轉換成英文。

For example, asking AI to document functions in our code. But this is not all.

例如，要求人工智慧記錄我們程式碼中的功能。但這還不是全部。

If we look at the software development lifecycle, I think many of us can agree that the majority of time,

如果我們看軟體開發生命週期，我認為很多人都會同意，大部分的時間，

we usually spend not writing valuable code, but all the other things around it. So sometimes up to 70% of unvaluable tasks,

通常我們花費的時間不是在寫有價值的程式碼，而是在其周圍的其他事情上。因此有時高達 70% 的無價值任務。

which is writing boilerplate code, writing documentation,

撰寫樣板代碼、編寫文件。

trying to maintain old code bases. And sometimes we only have a fraction of the time,

嘗試維護舊代碼庫。有時我們只有一小部分的時間，

maybe 30%, that we're spending on actually what

也許30%，我們實際花在什麼上面

creates joy and the creative tasks in software development.

創造了喜悅和軟體開發中的創意任務。

And this is what led us at AWS, this inspired us, to create Amazon Q. Amazon Q is a generative AI-powered

這就是 AWS 鼓舞我們創造 Amazon Q 的原因。Amazon Q 是一個由生成式人工智慧驅動的

assistant specifically developed for software development. And this is much more than just a coding assistant. Q developer actually uses agents to perform much more complex

專為軟體開發而開發的助理。這不僅僅是一個編碼助理。Q開發者實際上使用代理來執行更複雜的操作。

tasks and help you automate those. For example, feature development and also code transformation.

任務並協助您自動化這些。例如，功能開發以及程式碼轉換。

Think about working with old Java-based code bases

考慮與舊的基於Java的代碼庫一起工作

that you need to migrate maybe to your newer Java version.

您可能需要遷移到您更新的Java版本。

And to show you how this works, I asked my colleague Mike Chambers to put together a quick demo.

為了向您展示這是如何運作的，我請我的同事 Mike Chambers 組裝了一個快速示範。

Let's have a look.

讓我們來看看。

With Amazon Q installed inside of my IDE, I can go to New Tab,

搭載 Amazon Q 在我的 IDE 內，我可以前往 New Tab。

and I can start a conversation with Amazon Q developer. I can do the kinds of things that maybe you'd expect,

我可以開始與 Amazon Q 開發者對話。我可以做一些你可能期待的事情，

such as, how can I create a serverless application?

例如，我該如何建立一個無伺服器應用程式？

How do I get started? And the chat session brings back a list of instructions

我該如何開始？而聊天會話會帶回一份指示清單

of what I should do, starting off by installing AWS SAM CLI,

我應該做什麼，首先是安裝 AWS SAM CLI。

how to do that, where to get that from, and how to step through the creation of a project.

如何做到這一點，從哪裡獲取，以及如何逐步完成項目的創建。

Now, if I've done that, then serverless SAM, for example,

現在，如果我已經這樣做了，那麼無伺服器 SAM，例如，

might actually come back with some generated code. And here is that code.

可能實際上會回來帶有一些生成的程式碼。這裡是那段程式碼。

Maybe I don't quite know what this code does. So I can right-click on the code and send it to Amazon Q,

也許我不太清楚這段程式碼是做什麼。所以我可以右鍵點擊程式碼，並將它發送到Amazon Q。

asking Amazon Q to explain.

要求 Amazon Q 解釋。

And the code then will go into a prompt along with explain

然後代碼將會進入提示符號，並解釋

and generate an answer. And this is great for code that's been generated for us. But also, imagine code for legacy systems,

並生成一個答案。這對於為我們生成的代碼來說是很棒的。但同時，想像一下為遺留系統生成代碼，

something that was worked on years ago by somebody else,

多年前由別人完成的事情。

where you can get Amazon Q to help explain it.

您可以在這裡獲得Amazon Q來幫助解釋。

We can also get Amazon Q to generate code. Now, this is, again, probably the kind of thing

我們也可以讓 Amazon Q 生成程式碼。現在，這可能又是那種事情。

you'd expect. I can put in a comment line inside of my code. In this case, I want to create an input checking function.

你會預期的。我可以在我的程式碼中加入一行註解。在這種情況下，我想要建立一個輸入檢查函數。

I'm going to give it some more definition here

我打算在這裡給它更多的定義

that I actually want it to trim any string that's being sent into this function. And yes, Amazon Q can generate this small function.

我實際上希望它修剪傳送到此函數的任何字符串。是的，Amazon Q可以生成這個小函數。

Well, that's great.

那太棒了。

But what about if I've got more code that I need to have generated? Well, I can go to the chat and put in /dev.

但如果我有更多需要生成的代碼呢？嗯，我可以去聊天室輸入/dev。

And I can put in a much more comprehensive description

而且我可以提供更全面的描述

of something that I would like. In this particular case, I'm going to ask for it to write a function to search by category

我想要的東西。在這個特定情況下，我要求它寫一個按類別搜索的功能

in DynamoDB with a bunch of details about the way

在 DynamoDB 中有關該方式的大量細節

that I want the output to be formatted.

我希望輸出格式化。

So this is much more than just a single or a few lines of code.

所以這不僅僅是單一或幾行程式碼。

And in this particular case, what's going to happen is it will come back, again, with a step-by-step list

在這個特定案例中，將會再次回來，並附有一個逐步清單

of what's required. So I need to add in template.yaml.

所需的內容。所以我需要在 template.yaml 中添加。

It's recommending that I create search by category.mjs

建議我建立 search by category.mjs

and many more things. But this isn't just a big shopping list of things

和許多其他東西。但這不僅僅是一個很長的物品清單

that I need to do. This is actually a plan.

我需要做的事情。這實際上是一個計畫。

And it's a plan that Amazon Q can actually follow for us. So it generates some code as a change set, something

這是亞馬遜 Q 可以為我們實際執行的計畫。因此，它會產生一些程式碼作為一個變更集，某種變動。

that we can look at the difference

我們可以看看差異

between our current code and what it suggests. And if we like that, we can actually

在我們目前的程式碼和它所建議的之間。如果我們喜歡這樣，我們實際上可以

click on the Insert Code button. And it will add all of that code into our project,

點擊「插入程式碼」按鈕。然後它會將所有程式碼添加到我們的專案中。

way more than just a couple of lines. So Amazon Q Developer is much more than just code completion.

遠不止幾行代碼。所以 Amazon Q Developer 遠不止於代碼補全。

All right.

好的。

If you're curious to learn more about Amazon Q, Amazon Q

如果您對Amazon Q想要了解更多，Amazon Q

Developer, we have a couple of more sessions throughout this day.

開發者，我們今天還有幾個場次。

So make sure you're checking those Expo sessions. And we also do have a session at our AWS booth here.

所以請確保您查看那些博覽會的場次。我們在這裡的 AWS 展位也有一個場次。

You can also visit our Amazon Q Developer Center for much more examples what you can do with it.

您也可以造訪我們的 Amazon Q 開發者中心，了解更多您可以使用它做的例子。

All right, let's come to step three.

好的，讓我們來到第三步。

And this is where the fun starts. Start prototyping and building with AI.

這就是樂趣開始的地方。開始用人工智慧進行原型設計和建造。

And the fun includes a couple of steps, right?

而且樂趣包括了一些步驟，對吧？

Everyone developing with AI knows this. It starts all with defining your use case. And then really, you're on this road trying to choose from different models. You're trying to customize them to your use case, decide whether it's prompt engineering,

每個與人工智慧一起發展的人都知道這一點。一切都始於定義您的使用案例。然後，您真的正在嘗試從不同的模型中進行選擇。您試圖將它們定制為您的使用案例，決定它是否是提示工程。

whether you do REG, whether you need to do a little bit of fine tuning there with your data.

無論您進行 REG，還是需要對您的數據進行一點微調。

And of course, across the whole development workflow,

當然，在整個開發工作流程中，

you have to incorporate responsible AI policies, making sure data is private and secure,

你必須納入負責任的人工智慧政策，確保數據是私密且安全的。

and also implementing guardrails into your application.

並將護欄納入您的應用程式。

And then when you're integrated, another fun part, obviously, working with the agents,

然後當你被整合後，另一個有趣的部分，顯然是與代理人合作。

what we're hearing a lot here throughout this conference, and the fun topic of how to keep them up to date, GNI Ops.

我們在這次會議中聽到很多關於如何讓他們保持最新狀態的有趣話題，GNI Ops。

I think there's a lot of terms for that, MFM Ops, LLM Ops.

我認為有很多術語可以用來描述，MFM Ops，LLM Ops。

So really, a lot of things to consider here. I want to dive in briefly into the topic of models to choose. And this is really an important topic. When you're evaluating models, you have to really evaluate them thoroughly,

所以，這裡有很多事情要考慮。我想簡要探討一下要選擇的模型這個主題。這真的是一個重要的主題。當你在評估模型時，你必須要徹底評估它們。

because most likely, there's not just going to be one size fits all for you.

因為很可能，對你來說並不只有一種尺寸適合所有人。

In fact, if you look at all your use cases

事實上，如果您看所有您的使用案例

you want to implement, there's likely no one model

你想要實施的話，可能沒有一個模型

to rule them all. And this is why we developed Amazon Bedrock.

統治它們所有。這就是為什麼我們開發了 Amazon Bedrock。

Bedrock is a fully managed service

基石是一個完全管理的服務

that gives you access to a wide range of leading foundation models that you can start experimenting with,

提供您存取廣泛的領先基礎模型，您可以開始進行實驗。

implementing into your applications.

將其實施到您的應用程式中。

It also integrates the tooling you need to customize your model, whether it's fine tuning,

它還整合了您需要自定義模型的工具，無論是微調。

also to include reg workflows to build agents,

也包括了reg workflows 來建立agents,

and of course, everything in a secure environment

當然，一切都在一個安全的環境中。

where you are in full control of your data. And speaking of choice, just to give you a quick overview,

在這裡，您完全掌控您的數據。說到選擇，讓我為您快速概述一下，

as of today, this is the selection

截至今日，這是選擇。

of models you can choose from. We're working with leading companies such as AI21 Labs,

您可以選擇的模型。我們與AI21實驗室等領先公司合作。

Entropic, Cohere, Meta, Mistral AI, Stability AI.

Entropic, Cohere, Meta, Mistral AI, Stability AI.

And we also offer our own Amazon Titan models

而且我們也提供我們自己的Amazon Titan模型

for you to choose from. And I'm super excited just to call this out.

供您選擇。我非常興奮地喊出這個。

Last week, together with Entropic's launch, we integrated Cloud 3.5 Sonnet on Amazon Bedrock as well.

上週，我們與Entropic的推出一起，在Amazon Bedrock上也整合了Cloud 3.5 Sonnet。

So you can also, since last week, use this model.

所以您也可以，自上週開始，使用這個模型。

Super exciting.

超級刺激。

Now, with choice also comes responsibility, right? And we continuously innovate and trying to make it easier for you to build applications across the different model types. And just a few weeks ago, we introduced a new unified Converse API in Amazon Bedrock. What does this do? The unified Converse API helps you with a new unified method structured invocation, meaning you can use the same parameters and bodies

現在，有選擇就有責任，對吧？我們不斷創新，並努力讓您更輕鬆地在不同的模型類型上建立應用程式。就在幾週前，我們在 Amazon Bedrock 推出了一個新的統一 Converse API。這是做什麼用的？統一的 Converse API 幫助您使用一種新的統一方法結構化調用，這意味著您可以使用相同的參數和主體。

regardless of which model you choose. And we are on the platform side. We're handling this translation if parameters are called different for the different models, handling the system user assistant prompts for you,

無論您選擇哪個模型。而我們在平台端。如果不同模型的參數被稱為不同，我們將為您處理系統使用者助理提示。

and also giving you a consistent output format. And as well, having native function calling support

同時也提供您一致的輸出格式。同時，也具備本地函數調用支援

in here. But let me show you how this looks in code.

在這裡。但讓我向您展示這在程式碼中是如何呈現的。

So here's the Python example that shows how you can use the new API. This is Python, so we're starting by just integrating the Python SDK client here. And then you can define this list of messages. And here's, for example, where you put in your user message prompts. You can put in system prompts as well.

所以這裡是展示如何使用新 API 的 Python 範例。這是 Python，所以我們首先在這裡只是整合 Python SDK 客戶端。然後你可以定義這個訊息清單。這裡，舉例來說，你可以輸入你的使用者訊息提示。你也可以輸入系統提示。

And then this message list, you can just pass in this single API call using the Converse API here.

然後這個訊息清單，你可以直接通過這個單一的 API 呼叫，使用這裡的 Converse API。

In the model ID, you can choose which model you want to test. Here, I'm using an entropic model. And then pass the messages and also the inference parameters. And again, in this API, all those parameters are standardized. And we're going to make the work behind the covers to convert this to the specific format that the model is expecting.

在模型 ID 中，您可以選擇要測試的模型。在這裡，我使用的是一個熵模型。然後傳遞訊息和推論參數。再次，在這個 API 中，所有這些參數都是標準化的。我們將在幕後進行工作，將其轉換為模型期望的特定格式。

So you have an easy way to work across different models.

所以您有一種輕鬆的方式可以在不同的模型之間工作。

Similarly here for function calling, we do have the support built in with the models that support it. So how we implement this is by defining a tool list.

同樣地，在這裡對於函數的呼叫，我們有內建支援的模型來支援它。因此，我們實現這個的方式是通過定義一個工具清單。

So tool here equivalent to the functions

所以這裡的工具相當於功能

you want to give access to. And then when you're doing the Converse API call,

您想要提供存取權限。然後當您執行 Converse API 呼叫時，

you can pass this list of tools. All right, if you want to find out more about Converse API, here's a link to our generative AI space on community.aws, which has a lot more tutorials, code examples, not just for Python, but across different languages as well. So check it out.

你可以傳遞這個工具清單。好的，如果你想要更多關於 Converse API 的資訊，這裡有一個連結到我們在 community.aws 上的生成式 AI 空間，裡面有更多教學、程式碼範例，不僅僅是針對 Python，還有其他不同語言的範例。所以去看看吧。

The author here, Dennis Traub, is also somewhere here in the audience here this week. So if you want to connect with him,

這裡的作者 Dennis Traub 這週也在觀眾席中。所以如果你想要與他聯繫，

talk about different code examples and how to use the API, feel free to reach out.

談論不同的程式碼範例以及如何使用API，歡迎隨時聯絡。

All right, now let's integrate AI into our applications.

好的，現在讓我們將人工智慧整合到我們的應用程式中。

And this can be a whole session in its own. But I want to focus on one of the hottest topics

這可以是一個完整的課程。但我想專注於其中一個最熱門的話題。

right now that we're discussing during the conference, which is, of course, agents.

我們現在正在討論的是在會議中，當然是代理商。

And I have one more demo here. And I asked my colleague Mike last time

我這裡還有一個範例。上次我問了我的同事 Mike。

to put together an exciting demo to show you what you can do with agents.

組裝一個令人興奮的示範，展示您可以如何利用代理。

Mike?

麥克？

And we need sound. --be able to create agentic workflows right

我們需要聲音。--能夠創建主動性工作流程。

inside of the AWS console and inside of the service. It works fully serverless. And I've used it to create an agent that plays Minecraft.

在 AWS 控制台內部和服務內部。它完全無伺服器。我已使用它來創建一個玩 Minecraft 的代理。

Let me show you how I did it.

讓我來展示給你看我是如何做到的。

If we jump into the AWS console, go down the menu on the left-hand side to Agents, you

如果我們進入 AWS 控制台，往左側選單滑動到代理人，

can see the Agent screen here. And I can open up my agent, my Minecraft agent.

可以在這裡看到代理人畫面。而且我可以打開我的代理人，我的Minecraft代理人。

Now, if I just go into Agent Builder and just expand the screen out a little bit,

現在，如果我只是進入代理程式建立工具，並稍微擴大螢幕，

you get to see some of the parameters that I used to create this agent. So you can see the large language model I used,

你可以看到我用來創建這個代理人的一些參數。所以你可以看到我使用的大型語言模型，

in this case, Cloud 3 Haiku. And you can also see this, the instructions for the agent.

在這個案例中，Cloud 3 Haiku。而且您也可以看到這個，代理人的指示。

Now, this is not some notes for myself. This is actually prompt engineering

現在，這不是給自己的一些筆記。這實際上是提示工程。

that we're doing to explain how we want the agent, in this case, the Minecraft bot, to play the game.

我們正在解釋我們希望代理人，也就是這個情況下的《Minecraft》機器人，如何玩遊戲。

And then we also have to add some tools in, some Minecraft tools.

然後我們還必須加入一些工具，一些 Minecraft 工具。

So we do that through Actions and inside of Action Groups. So I've got a couple of different Action Groups.

所以我們透過行動和行動組來做到這一點。所以我有幾個不同的行動組。

We've got Minecraft Actions and Minecraft Experimental. Let's have a look at Actions.

我們有 Minecraft 行動和 Minecraft 實驗。讓我們來看看行動。

And inside of here, we can see some really simple things, some actions that the bot will be able to do.

在這裡面，我們可以看到一些非常簡單的事情，一些機器人能夠執行的動作。

And these are all linked up to code. So we've got the action to jump.

這些都與程式碼相連。所以我們有跳躍的動作。

We've got the action to dig. And you can see the description here for action to dig.

我們已經有挖掘的動作。你可以在這裡看到挖掘的描述。

It's got some instructions. Again, this is prompt engineering. And then we've got some parameters

這裡有一些指示。再次強調，這是提示工程。然後我們有一些參數。

that we can collect. In fact, we require these parameters. So the bot needs to get these for us.

我們可以收集的資料。事實上，我們需要這些參數。所以機器人需要為我們取得這些資料。

If I scroll down a little further, there's a couple of really simple actions in here.

如果我再往下滾動一點，這裡有幾個非常簡單的操作。

Action to get a player location and action to move to a location.

獲取玩家位置的動作和移動到一個位置的動作。

I want to show you those in Action because the bot can actually problem solve

我想要展示給你看這些在行動中，因為機器人實際上可以解決問題

and reason its way to be able to use these tools to solve

並理由其方式能夠使用這些工具來解決

simple problems. Let's jump into the game. And so it is nighttime.

簡單的問題。讓我們開始遊戲吧。現在是晚上。

So let's set it to be the daytime so that we can see what's going on.

所以讓我們設定為白天，這樣我們就可以看到發生了什麼。

So it's set time to day. OK. And there in the middle of the screen, you can see Rocky.

所以現在是設定時間。好的。在螢幕中央，你可以看到 Rocky。

Rocky is the bedrock agent running inside of the game. And we can talk to it.

Rocky是遊戲內運行的基石代理，我們可以與它交談。

We can have a chat session. But what about if we want it to come to us? Now, there is no tool to come to us.

我們可以進行一次聊天。但如果我們希望它來找我們呢？現在，沒有工具可以來找我們。

So if I-- I'm just going to back up a little bit further,

所以如果我--我只是要再往後退一點點，

make it a little bit more of a challenge. And I'm going to say, come to me in chat. And what's going to happen now is

讓它變得更有挑戰性一點。我要說，來找我聊天。現在會發生的是

that the agent's going to reason through a whole set of actions. It's going to look to see who requested that.

代理人將會推理整套行動。它將會查看是誰提出了要求。

It's then going to take that name, and that's my name.

它會採用那個名字，那就是我的名字。

And it's going to find the location of that player. And then it's going to map a path from where

它將找到該玩家的位置。然後它將從那裡繪製一條路徑。

it currently was to me. All of those things happened all in that blink of an eye.

它目前對我來說就是這樣。所有這些事情都發生在一眨眼之間。

And there's agentic workflows making all of that happen. This is super exciting.

而且有代理工作流程讓所有這些發生。這真是令人興奮。

I'm discovering new things that this bot can do every day. But with that, it's back to you.

我每天都在發現這個機器人可以做的新事情。但隨之而來的，又回到你身上。

All right. Thank you, Mike. If you're curious to know how we did this,

好的。謝謝，Mike。如果你想知道我們是如何做到這一點的話，

check out our booth session. We're running the demo there as well.

查看我們的攤位活動。我們也在那裡進行示範。

And we have another session in the agents track later today. So make sure you're popping in there

我們今天晚些時候還有一個在代理商軌道上的場次。所以請確保你會去參加。

if you want to know more. And of course, you can find the project code for this on GitHub.

如果你想要知道更多。當然，你可以在 GitHub 上找到這個專案的程式碼。

So if you want to play, play it on your own in how you can integrate agents into a fun thing,

所以如果你想玩，就自己玩，看看你如何將代理商融入一個有趣的事情中，

check out this project. All right. We're almost there. So the last step I really want to call out is stay up to date.

檢查這個專案。好的。我們快完成了。所以我特別想提醒的最後一步是保持最新。

There's so much happening in this space, as you all know. And a really good way to do that is to engage with the community.

這個領域發生了很多事情，大家都知道。而與社群互動是一個非常好的方法。

Speaking of community, I have one last announcement to make.

說到社區，我有最後一個公告要宣布。

And I'm super excited to announce that we're transforming our AWS loft here in San Francisco into the AI engineering hub for the community. So we're super excited to host workshops, events, and meetups

我非常興奮地宣布，我們將把我們在舊金山的 AWS loft 轉變為社區的人工智慧工程中心。所以我們非常興奮地舉辦工作坊、活動和聚會。

there.

那裡。

If you want to suggest a couple of topics you're most interested in to make those events most valuable to you, fill out this quick survey here.

如果你想要提出幾個你最感興趣的主題，讓這些活動對你更有價值，請在這裡填寫這份快速調查。

Also, if you're interested in speaking or hosting a meetup yourself, you can let us know. And also, we do have another event tonight,

此外，如果您有興趣演講或主持一個聚會，您可以告訴我們。而且，今晚我們還有另一個活動。

which I think we're reaching capacity or just half-reached capacity.

我認為我們已經達到容量的上限，或者只是達到了一半的容量。

But we do have a happy hour with Entropic tonight at the loft.

但我們今晚在閣樓有一個與Entropic的歡樂時光。

In case you didn't make it anymore and we're at capacity, don't worry.

如果你沒有再來，而我們已經滿了，不用擔心。

We're working on putting together much more events like this in the upcoming weeks and month.

我們正在努力籌備未來幾週和幾個月內舉辦更多這樣的活動。

So keep an eye out for those. And with that, I'm coming to the end of my presentation.

所以請留意這些。接下來，我要結束我的簡報。

This wraps it up, the five practical steps

這就是結論，這五個實用步驟

to become an AI engineer. And let's innovate together.

成為一名人工智慧工程師。一起來創新。

And I'm looking forward and I'm excited to see what you build with AI.

我很期待，也很興奮地期待看到你用人工智慧建立的東西。

Thanks so much. Make sure you're checking out the rest of the sessions here and also pop by our booth outside.

非常感謝。請務必查看這裡的其餘場次，也別忘了來我們攤位外頭走走。