跟读练习: Google Antigravity 2.0 Beginner's Guide - 通过视频学习英语口语

选择练习模式

每种模式都会打开全屏练习室。

248 句

如果句子过短或过长，请点击 Edit 进行调整。

Introducing Antigravity 2 .0, a new standalone desktop app for orchestrating agents.

Less than a year ago, we launched the Google Antigravity IDE, which included the Agent Manager, one of the world's first agent -first GUIs on the market.

Millions of users loved working in the Agent Manager, accelerating both their work as developers and non -developers.

We've heard your feedback and built a bunch of new features.

Combined with the recent Leaps and Gemini model capabilities, We're excited to release Antigravity 2 .0 and take a bold next step towards an agent -first world.

Let me show you how you can get started.

So let's go ahead and open up Antigravity.

We're going to start by onboarding.

First, I'm going to sign in with my Google account.

And if you're an Antigravity IDE user, your next update will bring you exactly into this application.

So we'll go through onboarding.

I'm a light mode kind of guy.

Next, you'll see the Build with Google page.

This allows you to install skills and plugins that hook into your favorite Google products.

So in this case, we're going to install the Modern Web Guidance, which helps your agent navigate the web and build the best possible web products.

We're going to install the Chrome DevTools, and there's a bunch of other options that you can choose from.

By the way, if you're already an anti -gravity IDE user, you'll see a screen like this, and you can go ahead and leave that keep anti -gravity IDE checked

so that you can transition smoothly into anti -gravity 2 .0.

We'll start by creating a new project Antigravity 2 .0 is centered around this idea of a project.

You can add folders, add Git repositories, And this really serves as the launchpad for your agent.

So in this case, we're starting a brand new project.

So I'll go ahead and create a new folder, and we're going to be building a game.

It's called StreetGuessr.

So, we're going to add that folder as a project and dive right in.

So first I'm just going to ask it a quick question.

Let's just warm up.

What can you help me with?

And it's a coding agent, it's also just a general assistant.

It'll tell me some of the things

that it can do as well as some of the new commands and new features that are available in ATGravity 2 .0.

One of my favorite features is using my voice to tell the agent what to do.

Here I'm going to press the mic.

give it mic access, and tell it what kind of game we want to build.

So I'll press the button and say, how would I build a video game web app that lets users put in a city name, or draw a bounding box around a map,

then let the user guess all the street names in that particular region?

I'm open to using any API, but ideally keep it pretty cheap.

And you can give me a couple of options on how this can be built.

You don't actually need to build it yet, but I do want to see a pretty comprehensive plan for what my options here are.

And why don't we add that we want this to be an artifact implementation plan.

So we'll go ahead and send that.

And we're using Gemini 3 .5 Flash, which you can see it's really, really fast at putting together a pretty comprehensive plan for how to build a game like this.

We'll open up the implementation plan.

You'll see there is now an architecture diagram of what we can expect.

I noticed

that Gemini had a couple of open questions for me to answer before I can actually put together a comprehensive plan.

So I'll go ahead and answer those questions just like I would in anti -gravity So,

I'm pretty comfortable with the user allowing picking any part of the world.

I really like its idea about making a classic paper map style game, and I think we're going to need a server, so let's choose a full stack framework for this.

And I'm going to ask it to update my plan just to be sure

that I know exactly what the model is going to go off the build.

All right, it's already gone ahead and updated my plan, so I think I'm ready to start building.

I'll go ahead and click proceed.

Thank you.

Antigravity likes to keep you in control, both from a safety perspective and it's just good for you to know when it's running commands on your computer.

Now, of course, this is configurable, but in the beginning, I want to get a feel for what sorts of commands the agent is running for me.

So here it's asking me to accept, reject, and whitelist particular commands that it wants to run.

In this case, I want it to create this sort of app, and I want to install these dependencies, so I'm going to go ahead and press yes.

But all of this is configurable, complete control over which types of commands you always want to run, and maybe some commands that you want it to ask you every single time.

that can get your agent dialed to exactly what you want.

And just like that, Gemini 3 .5 Flash has already finished the first version of our game, and it's telling me exactly what it built via a walkthrough artifact,

and now it's suggesting that it can actually run my project for me so that I can open it up.

So let's take it up on that suggestion.

I'll say run it for me so I can check it out.

The agent has now run npm run dev, which we can see right above our toolbar.

And to view these sorts of background commands or background subagents, we can go ahead and click it, and you'll see the output directly on the right.

And now I can see that my server is running at localhost 3000.

And by clicking on localhost 3000, I can open up Chrome and see a pretty cool, pretty nifty version of this classic map where we can go ahead and guess.

So let's go ahead and pick one of the coolest locations in San Francisco, North Beach.

Let's go ahead and just try and play this game.

It's kind of cheating because it did put a couple of the street names in the placeholders.

So we'll go ahead and start with those first.

All right.

I think those are all the streets that I can name.

for the purposes of this demo.

So we'll go ahead and surrender, and it looks like we got 14 out of 128.

So that was pretty cool for a first pass.

Gemini 3 .5 put together a very, very good game here.

But now comes the fun part.

I have a bunch of ideas on various features and some of the design elements I want to add to my game.

And this really is where Antigravity 2 .0 starts to shine.

We can introduce parallel conversations and sub -agents, and our agents are capable of a lot of sophisticated work.

So here we'll start, add a confetti animation.

When you get a street right multiple times in a row, a streak counter and show confetti with increasing intensity the more you get it right in a row.

The first one should not have confetti, but should light up the street counter.

And here I'm going to go down and select instead "New Work Tree".

And what this will do is spin up a new folder with a copy of the code, so the agent can run in parallel without interrupting my main flow.

I'll go ahead and send that, and I'll start a new conversation and we'll do something similar.

"Design me a trophy for when a user gets more than 50 % of the street names correct.

"Use image generation to give me something that matches the app's aesthetic." So while that's going, it looks like my first conversation is actually ready and giving me a plan.

So I'll go ahead and review this plan.

It looks like it's going to add an external library.

This generally looks good, so I'll press "Proceed." And we'll start a third conversation, because I have a lot of ideas of things that I actually want to build.

This time, I'm going to work inside of my main conversation, just so that I can work on this one a little bit more synchronously.

regions.

Let's do San Francisco North Beach area, West Village, New York, Treasure Island in the SF Bay, and downtown Dallas.

What's really nice about using a fast and intelligent model like Gemini 3 .5 Flash, our agents are already waiting for us to give feedback.

So here it put together a pretty nice looking shield trophy for when someone gets more than 50 % correct.

And this looks pretty good, but I have some other ideas.

I like this aesthetic.

100

Let's actually have three tiers of trophies.

101

We can do one for really, really good achievement, and then one for 50%, and then one for 10%.

102

Let's do three sub -agents so that generating these is faster.

103

We'll go ahead and send that.

104

So it looks like adding presets to our homepage is complete, and it's given me a walkthrough, and I can also see all the files the agent changed.

105

I can click on a particular file, in this case app page .tsx, and I can leave comments directly inside of this artifact pane.

106

And I want to move this into a constants directory, there are some things that I want to change, but I can just leave comments just like any other artifact.

107

And now I'll tell the agent what to do differently.

108

So while that's working, I have another one.

109

It looks like the streak is done.

110

So this will be fun to check out.

111

So it looks like my image generation is finished and I have a carousel of three different options.

112

Those look pretty good to me.

113

And it's actually modifying some of the code to make it

114

so that these trophies pop up at the end of our game.

115

So I'll go ahead and reload my app.

116

And as you can see, I now have presets for North Beach, West Village, Treasure Island, and Dallas.

117

Going ahead and clicking around things look pretty good.

118

And why don't we go ahead and play one of these games?

119

So let's test my knowledge of West Village, New York.

120

Perry Street, that's a thing, I do know that.

121

Hudson.

122

I guess we could do all the numbers, starting with 7th.

123

We'll try 5, 4.

124

Okay, 4 looks good, 3, and now we have a bunch of confetti coming on the screen.

125

It's actually kind of fun, and we're on a streak of 5.

126

That is awesome.

127

Okay, for the purposes of demo, let's go ahead and stop and try and evaluate what we should build next.

128

So we'll go ahead and press surrender and reveal, and it looks like our badges and trophies are showing up, so I'm a novice explorer of West Village, New York.

129

some of those gnarly technical problems.

130

So to start, we'll go back into voice mode and let's ask it to do something.

131

Let's add a backend to this that connects to a SQL database.

132

You can use SQLite.

133

For this web app, have it store the user's favorite maps so they can access them later, as well as their history of games and their scores for each.

134

And let them see their game history and see their progress over time and compete against their own high score.

135

So this is a pretty complex task because it involves refactoring a bunch of things throughout our application.

136

So you'll see it doing a lot of research, both in the front end and in the back end, in order to put together a comprehensive plan.

137

I'll go ahead and review this.

138

It looks like it's putting together an entire database schema.

139

It'll do some three factors on both the client and the server.

140

And generally this looks pretty good.

141

So let's go ahead and build it.

142

But this time I want to show you a new part of Antigravity 2 .0, which is sub -agents.

143

So I'll ask it to spin up a bunch of sub -agents to get this work done in parallel, Then let me know when you're done.

144

I'm excited to play this game when you're finished.

145

And I actually had a second idea, which is why don't you test yourself?

146

So we'll use /browser, and we know a lot of people really loved seeing the agent use a browser in order to verify

147

that it completed its task correctly.

148

So, I'm going to use /browser and ask it to test itself.

149

So this is my first time setting up the browser.

150

So I'm going to go ahead and go back to Chrome and follow these instructions.

151

Go ahead and press remote debugging, have it check again, and looks like we're good to go.

152

Just like that, a couple clicks, our browser is now set up.

153

Cool, so the agents are now working for me and it kicked off three different sub -agents.

154

It has one to test end -to -end with the browser.

155

It has another one that I guess is a UI /UX designer, and then we have another database and API engineer.

156

So roughly, QA, front end, and back end.

157

And it also added a timer for itself to check in on all the sub -agent progress 90 seconds later.

158

And if you head over to your Artifact pane and click Overview, You can see a list of all the sub -agents and what they're doing.

159

And if an agent gets stuck, you can easily see action buttons for you to one -click approve.

160

In this case, the browser wants to go to /dashboard.

161

So I'll go ahead and press approve there.

162

This is one of my favorite features in anti -gravity.

163

Not only can you manage many main agents, but your own agents can actually manage their own teams of sub -agents.

164

It's really common for some of my more technical, more complex engineering tasks for my agent to spin off five, ten, if not twenty different sub -agents to go ahead

165

and check each other's work or just parallelize the work so that it gets done faster and more correctly.

166

So, with so many agents running, now is probably the time where I can go get a snack

167

or grab a coffee and come back when things are done.

168

Antigravity will notify me and let me know when my attention is required either to approve a command

169

or just unblock some sub agents.

170

All right.

171

I'm back and it looks like our sub agents have finished

172

and it's gone ahead and tested itself and verified that everything works correctly.

173

So let's go ahead and play this new version of our game that is now full stack.

174

So it looks pretty familiar.

175

I guess now we have looks like favorite maps that we can put in.

176

We'll go ahead and select a section.

177

Let's try this part of San Francisco and.

178

I can name it now.

179

We'll call it North SF.

180

And we'll go ahead and play North SF.

181

276 roads.

182

Let's get started.

183

We did this earlier, so we'll speed through a couple ones that we remember.

184

Broadway, Market, Lombard, Union, Stockton, Polk.

185

you Great, 3%.

186

And we see it's now a personal high score, very cool.

187

And I can go over to my archives and it's saving my progress just as we instructed it to.

188

Alright, let's just see if it works in other parts of the world, like London or New York.

189

Bye.

190

Bye.

191

Bye.

192

So wouldn't it be fun to actually use the agent to play the game that it just created?

193

So let's add /browser.

194

Can you play the game for me and get all the streets on Treasure Island, San Francisco?

195

And I'll let it cheat.

196

You can do web search research to make sure you get at least 90 % accuracy.

197

and we'll see how the agent does.

198

So here it's utilizing a sub -agent to actually go ahead and play the game.

199

And you can see how it's deciding it to get 90 % or probably it will probably just get 100%.

200

It's actually going ahead and querying an API to get a list of all the streets on Treasure Island.

201

That's obviously not something that a human would do if they were playing this game, but it's an agent so it can do whatever it wants.

202

Looks like it's putting in a bunch of street names.

203

Interestingly, none of them are registering, and let's see if it decides if this is a bug in the game or a bug in its logic.

204

Looking at the thought traces, it seems like the model has figured out

205

that it was not pressing the enter key after putting in each Street name

206

and maybe that's why it wasn't able to get a hundred percent And just like that, now it's putting in all the names.

207

Oh my gosh.

208

So much confetti.

209

15, 17.

210

Oh, it actually missed one.

211

Interestingly, its streak got reset.

212

We're now at 30 out of 45.

213

There we go.

214

Personal high score, 100 % of the streets on Treasure Island.

215

done by an agent.

216

Now that's going to be a really hard score to beat.

217

but it got that top score.

218

Honorary decree, Grand Master Cartographer.

219

Now that we've played our game, I want to set up something called a scheduled task.

220

This is something brand new to Antigravity 2 .0, and it lets you run prompts on the loop.

221

So I'll go ahead and start a new scheduled task, and I really actually enjoy this game, so I want it to tell me every morning a new random location in the world

222

that I can play and maybe have it tie back to historical facts or something interesting about that particular region, and while I want it to be random, I don't want it to be a completely

223

where there is no famous street that I just have absolutely no hope of guessing.

224

So I'll add in the prompt that it should be something with at least one or two famous streets.

225

So we'll go ahead and call this Morning Street Guesser.

226

We'll have it run at 5 a .m every morning and I'll put in my prompt.

227

Choose a random big city in the world that uses English street names, pick a sub -region of that city with famous street names

228

and give me a local host link to play my game every morning to start my day.

229

Give me a famous landmark or historical reference point for that particular bounding box.

230

We'll add that scheduled task, and within a couple of seconds we'll now see it on our dashboard.

231

Now, It is not currently 5am, but I do want to show you what this would look like if it ran at 5am, so I'll go ahead and copy -paste that prompt

232

and just run it right now and I'll show you exactly what that would look like if it was.

233

very, very early in the morning.

234

But what's really cool is Antigravity 2 .0 can run in the background even when all the windows are closed.

235

So I'll go ahead and X out this window and as you can see in the top menu bar, there is a little icon, it's the anti -gravity icon, that is telling me how many agents I have running,

236

and a quick button to reopen that interface.

237

So if I reopen, I'll see that my agent has now finished.

238

And just like that, the agent has decided to take me back to London and I guess Today, I will play Street Guesser in London.

239

And what's really cool here is that those scheduled tasks will continue to run in the background, and you can set up as many of those as you want.

240

So you might have a task that checks the status of a PR

241

or puts together a daily brief of tasks that you have to get done today.

242

The possibilities really are endless.

243

And as long as you see that anti -gravity icon in your menu bar, you'll have confidence knowing that those tasks are executing behind the scenes and that your agents are working for you.

244

And just like that, there's your first look at anti -gravity 2 .0.

245

You just saw sub -agents working in parallel, you saw work trees, scheduled tasks, image generation, the list goes on and on.

246

On behalf of the anti -gravity team, thank you for watching.

247

And we hope you love what we've built.

248

Check it out at antigravity .google.

下载应用

流利口语所需的一切

AI 发音评分逐句打分

音标练习掌握每个音

词汇学习建立你的词库

词汇游戏边玩边学

扫码

Download on theApp Store Get it onGoogle Play

FOR YOU

本课的词汇与口语要点

这节 C1 级别的口语课以视频“Google Antigravity 2.0 Beginner's Guide”为素材。视频中反复出现的词有：agent, ahead, sub。这段视频共有 247 个句子、3465 个单词可供跟读。讲话部分时长为 16:07。说话人语速较快，每分钟约 215 个词，会出现较多连读和弱读。 85% 的单词属于英语最常用的 3,000 词，其余的词建议在练习前先学一下。

视频中的重点词汇

视频中最难的 15 个单词，附发音和释义：

单词	发音	释义
artifact 名词	/ˈɑɹtɪfækt/	人工製品 /人工制品
confetti 名词	/kənˈfɛ.ti/	五彩紙屑 /五彩纸屑
folder 名词	/ˈfoʊldɚ/	卷宗, 文件夾 /文件夹
streak 名词	/stɹiːk/	痕迹
approve 动词	/əˈpɹuːv/	批准, 贊成 /赞成
dashboard 名词	/ˈdæʃˌboɹd/	汽車儀表 /汽车仪表, 儀表盤 /仪表盘
walkthrough 名词	/ˈwɔːk.θɹuː/	攻略
verify 动词	/ˈvɛɹɪfaɪ/	校驗 /校验, 驗證 /验证
aesthetic 形容词	/ɛsˈθɛ.tɪk/	審美的 /审美的
stack 名词	/stæk/	堆
demo 名词	/ˈdɛm.oʊ/	示範 /示范
cheat 动词	/ˈt͡ʃiːt/	作弊, 使诈
surrender 动词	/səˈɹɛndə(ɹ)/	投降
carousel 名词	/ˌkæɹəˈsɛl/	行李傳送帶 /行李传送带
instruct 动词	/ɪnˈstɹʌkt/	教, 教育

视频中出现的短语动词

单词	发音	释义
go ahead 动词	/ˌɡoʊ əˈhɛd/	請便 /请便
put together 动词		拼合, 組合 /组合
check out 动词		退房
come back 动词		回來 /回来, 返回
figure out 动词		弄清楚
go down 动词		下降, 下去
go through 动词		通過 /通过
show up 动词		露面

值得反复跟读的句子

视频中简短而完整的句子，可以直接用在日常对话里：

We're going to start by onboarding.
I'm a light mode kind of guy.
What can you help me with?
Here I'm going to press the mic.
We'll open up the implementation plan.

视频中的语法

说话人最常用的结构，并附上视频中的原话：

结构	视频中的用法
条件句 if + 从句，will/would + 动词 — 条件及其结果	if it ran at 5am, so I'll go · if I reopen, I'll see
现在完成时 have/has + 过去分词 — 过去发生但与现在仍有关联的事	We've heard · has already finished · has now run
被动语态 be + 过去分词 — 强调发生了什么，而不是谁做的	is centered · can be built · is now set

需要注意的发音

说话人用了 96 次缩略和弱读形式，例如 we'll, I'll, I'm。请按听到的简短形式来说。

“th” 音: walkthrough /ˈwɔːk.θɹuː/, aesthetic /ɛsˈθɛ.tɪk/, smoothly /ˈsmuːðli/
“sh” 和 “zh” 音: dashboard /ˈdæʃˌboɹd/, gosh /ɡɑːʃ/
长单词——注意重音位置: configurable /kənˈfɪ.ɡə.ɹə.bəl/, repository /ɹɪˈpɒz.ɪ.t(ə.)ɹɪ/, synchronously /ˈsɪŋkɹənəsli/, dependency /dɪˈpɛndənsi/, honorary /ˈɑn.əˌɹɛɹ.i/

中文母语者容易读错的音：

/v/ — 不要读成 /w/，上齿轻触下唇: approve /əˈpɹuːv/, verify /ˈvɛɹɪfaɪ/, novice /ˈnɑvɪs/, navigate /ˈnæv.ɪ.ɡeɪt/, archive /ˈɑɹˌkaɪv/
词尾辅音 — 要读清楚，后面不要加元音: artifact /ˈɑɹtɪfækt/, prompt /pɹɑmpt/, streak /stɹiːk/, approve /əˈpɹuːv/, dashboard /ˈdæʃˌboɹd/
/r/ 和 /l/ 的区别: configurable /kənˈfɪ.ɡə.ɹə.bəl/, carousel /ˌkæɹəˈsɛl/, gnarly /ˈnɑɹli/, reload /ɹiːˈləʊd/, synchronously /ˈsɪŋkɹənəsli/

如何用这段视频练习

先完整听一遍视频，不要开口，记下不认识的单词。
先用 0.75 倍速逐句跟读，熟练之后再回到正常速度。
录下自己的声音并与原声对比，特别注意 artifact, confetti, folder 这类单词。

什么是跟读法？

跟读法 (Shadowing) 是一种有科学依据的语言学习技巧，最初开发用于专业口译员的培训，并由多语言者Alexander Arguelles博士普及。这个方法简单而强大：您在听英语母语原声的同时立即大声重复——就像是一个延迟1-2秒紧跟说话者的影子。与被动听力或语法练习不同，跟读法强迫您的大脑和口腔肌肉同时处理并模仿真实的讲话模式。研究表明它能显着提高发音准确性，语调，节奏，连读，听力理解和口语流利度——使其成为雅思口语备考和真实英语交流最有效的方法之一。

影子跟读法: 阅读完整分步指南 →

跟读练习: Google Antigravity 2.0 Beginner's Guide - 通过视频学习英语口语

选择练习模式

下载应用

推荐视频

What’s new in Gemini API, Google AI Studio and Google Antigravity (Google I/O 2026 recap)

Claude Code: The Advanced Guide (99% of Devs Skip These Features)

1.2 How Google Analytics collects and processes data - Analytics Academy on Skillshop

Business Partner C1. Unit 1. Video 1.1.1.

ngày 26 tháng 5, 2026

Easy Migration from Postgres to Databricks Lakebase

Godot in 100 Seconds

What's new in Google Cloud in less than 1 minute

The Multi-Agent Architecture That Actually Ships — Luke Alvoeiro, Factory

Why 95% of Android Developers Get Use Cases Wrong

Introducing GPT-6 Astra: the most intelligent and aligned model in the world.

Start building Shopify apps, FAST

本课的词汇与口语要点

视频中的重点词汇

视频中出现的短语动词

值得反复跟读的句子

视频中的语法

需要注意的发音

如何用这段视频练习

什么是跟读法？