Luyện nói tiếng Anh bằng Shadowing qua video: Google Antigravity 2.0 Beginner's Guide

Chọn chế độ luyện tập

Mỗi chế độ mở một phòng luyện tập toàn màn hình.

248 câu

Nếu các câu quá ngắn hoặc quá dài, hãy bấm Edit để chỉnh sửa.

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.

Tải Ứng Dụng

Mọi thứ bạn cần để nói trôi chảy

Chấm điểm AIChấm từng câu nói

Luyện IPAThành thạo mọi âm

Từ vựngMở rộng vốn từ

Game Từ vựngHọc qua chơi

Quét QR

Download on theApp Store Get it onGoogle Play

FOR YOU

Video gợi ý

9 câu

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

Business EnglishUniversity StudentsWorking Adults

309 câu

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

Business EnglishUniversity StudentsWorking Adults

42 câu

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

Business EnglishUniversity StudentsWorking Adults

51 câu

Từ vựng và ghi chú luyện nói cho bài học này

Bài luyện nói trình độ C1 này dựa trên video “Google Antigravity 2.0 Beginner's Guide”. Những từ được nhắc lại nhiều nhất trong bài: agent, ahead, sub. Video này có 247 câu và 3465 từ để luyện shadowing. Phần lời nói dài 16:07. Người nói nói nhanh, khoảng 215 từ mỗi phút, nên sẽ có nhiều chỗ nối âm và nuốt âm. 85% số từ nằm trong 3.000 từ tiếng Anh thông dụng nhất; phần còn lại nên xem trước khi luyện.

Từ vựng quan trọng trong video

15 từ khó nhất trong video, kèm phiên âm và nghĩa:

Từ	Phiên âm	Nghĩa
confetti danh từ	/kənˈfɛ.ti/	công-phét-ti, hoa giấy
folder danh từ	/ˈfoʊldɚ/	bìa hồ sơ
streak danh từ	/stɹiːk/	vệt
approve động từ	/əˈpɹuːv/	phê duyệt
dashboard danh từ	/ˈdæʃˌboɹd/	bảng đồng hồ, bảng điều khiển
verify động từ	/ˈvɛɹɪfaɪ/	xác minh, xác thực
stack danh từ	/stæk/	chồng
cheat động từ	/ˈt͡ʃiːt/	gian lận, bịp
surrender động từ	/səˈɹɛndə(ɹ)/	đầu hàng
carousel danh từ	/ˌkæɹəˈsɛl/	đu quay, trò kéo quân
toolbar danh từ	/ˈtul.bɑɹ/	thanh công cụ
whitelist danh từ		danh sách trắng, danh sách cho phép
accelerate động từ	/ɪkˈsɛl.əˌɹeɪt/	tăng tốc
diagram danh từ	/ˈdaɪ.ə.ɡɹæm/	giản đồ, biểu đồ
pasta danh từ	/ˈpɑ.stə/	mì ống

Cụm động từ bạn sẽ nghe

Từ	Nghĩa
open up động từ	mở
check out động từ	tính tiền, trả phòng
come back động từ	trở lại, trở về

Những câu đáng luyện lại

Các câu ngắn, trọn ý trong video mà bạn có thể dùng lại khi giao tiếp hằng ngày:

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.

Ngữ pháp trong video

Những cấu trúc người nói dùng nhiều nhất, kèm đúng cụm từ trong video:

Cấu trúc	Trong video
Câu điều kiện if + mệnh đề, will/would + động từ — điều kiện và kết quả	if it ran at 5am, so I'll go · if I reopen, I'll see
Thì hiện tại hoàn thành have/has + quá khứ phân từ — việc đã xảy ra nhưng còn liên quan đến hiện tại	We've heard · has already finished · has now run
Câu bị động be + quá khứ phân từ — nhấn vào việc xảy ra, không phải người làm	is centered · can be built · is now set

Phát âm cần chú ý

Người nói dùng 96 dạng rút gọn, ví dụ we'll, I'll, I'm. Hãy nói theo dạng ngắn đúng như bạn nghe.

Âm “th”: walkthrough /ˈwɔːk.θɹuː/, aesthetic /ɛsˈθɛ.tɪk/, smoothly /ˈsmuːðli/
Âm “sh” và “zh”: dashboard /ˈdæʃˌboɹd/, gosh /ɡɑːʃ/
Từ dài — đặt trọng âm cho đúng: configurable /kənˈfɪ.ɡə.ɹə.bəl/, repository /ɹɪˈpɒz.ɪ.t(ə.)ɹɪ/, synchronously /ˈsɪŋkɹənəsli/, dependency /dɪˈpɛndənsi/, honorary /ˈɑn.əˌɹɛɹ.i/

Những âm người Việt thường gặp khó:

Cụm phụ âm cuối — đọc đủ từng âm, đừng nuốt âm cuối: artifact /ˈɑɹtɪfækt/, prompt /pɹɑmpt/, dashboard /ˈdæʃˌboɹd/, instruct /ɪnˈstɹʌkt/, subagent /ˌsʌbˈeɪ̯.d͡ʒənt/
Âm /tʃ/, /dʒ/ và /ʒ/ — tiếng Việt không có, đừng đọc thành “ch” hay “gi”: cheat /ˈt͡ʃiːt/, subagent /ˌsʌbˈeɪ̯.d͡ʒənt/, badge /bæd͡ʒ/
Âm /æ/ — mở miệng rộng hơn âm “e”: artifact /ˈɑɹtɪfækt/, dashboard /ˈdæʃˌboɹd/, stack /stæk/, carousel /ˌkæɹəˈsɛl/, navigate /ˈnæv.ɪ.ɡeɪt/

Cách luyện với video này

Nghe hết video một lần, chưa cần nói, và ghi lại những từ bạn chưa biết.
Bắt đầu ở tốc độ 0,75×, nói đuổi từng câu, rồi quay lại tốc độ bình thường khi đã quen.
Ghi âm giọng mình rồi so với bản gốc, chú ý các từ như confetti, folder, streak.

Phương Pháp Shadowing Là Gì?

Shadowing là kỹ thuật học ngôn ngữ có cơ sở khoa học, ban đầu được phát triển cho chương trình đào tạo phiên dịch viên chuyên nghiệp và được phổ biến rộng rãi bởi nhà đa ngôn ngữ học Dr. Alexander Arguelles. Nguyên lý cốt lõi đơn giản nhưng cực kỳ hiệu quả: bạn nghe tiếng Anh của người bản xứ và lặp lại to ngay lập tức — như một "cái bóng" (shadow) đuổi theo người nói với độ trễ chỉ 1–2 giây. Khác với luyện ngữ pháp hay học từ vựng bị động, Shadowing buộc não bộ và cơ miệng phải đồng thời xử lý và tái tạo ngôn ngữ thực tế. Các nghiên cứu khoa học xác nhận phương pháp này cải thiện đáng kể phát âm, ngữ điệu, nhịp điệu, nối âm, kỹ năng nghe và độ lưu loát khi nói — đặc biệt hiệu quả cho người luyện IELTS Speaking và muốn giao tiếp tiếng Anh tự nhiên như người bản ngữ.

Phương pháp shadowing: đọc hướng dẫn từng bước đầy đủ →

Luyện nói tiếng Anh bằng Shadowing qua video: Google Antigravity 2.0 Beginner's Guide

Chọn chế độ luyện tập

Tải Ứng Dụng

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

Từ vựng và ghi chú luyện nói cho bài học này

Từ vựng quan trọng trong video

Cụm động từ bạn sẽ nghe

Những câu đáng luyện lại

Ngữ pháp trong video

Phát âm cần chú ý

Cách luyện với video này

Phương Pháp Shadowing Là Gì?