Shadowing Practice: How To Use Claude Better Than 99% Of People - Learn English Speaking with Video

Choose a practice mode

Each mode opens a full-screen practice room.

257 sentences
If sentences are too short or too long, click Edit to adjust them.
1
Give Claude to two people.
2
One will use it to build a better email.
3
The other will use it to help build a $100 million company.
4
Same tool.
5
different users.
6
And that gap between people who use AI
7
and people who wield it is about to reshape careers and companies and families and lives over the next decade.
8
If you're new here, I've been a CEO, board member, investor in technology companies worth billions.
9
And today I want to share with you how to use Claude better than 99 % of people from beginner to advanced.
10
And it's way easier than you think.
11
Cloud is not just one app.
12
It's a whole stack of tools built for a very different kind of work environment for businesses.
13
There's chat for thinking, Cloud Cowork to get work done, Cloud Code to build things, Cloud Chrome to browse with a brain,
14
Cloud Skills to make it all repeatable, lots of tools.
15
dramatically.
16
The best way to visualize it is this: five activities: think, remember, execute, build, and browse.
17
Let's go through each one of them.
18
First is think.
19
You go to Cloud Chat.
20
And this is what most of us do when we think about chat bots.
21
We input a prompt, we get a response, you bring a messy problem, a fuzzy idea, or a rough draft, and work through it.
22
But many of us just use AI to do all the work We've all seen those LinkedIn posts.
23
So if you go to Claw Chat and type,
24
"Write me a LinkedIn post about leadership," you'll get a very polished paragraph that says nothing.
25
And we've talked about how to prompt better with things like aim before actor input mission.
26
Try this prompt instead.
27
You are a business school professor.
28
I am trying to explain why some leaders sound credible and others sound.
29
I'm attaching my notion page with a rough idea that talks about leadership and authenticity, leadership and humility.
30
Your job is to push back on what's weak and sharpen what's real.
31
Find me research that helps me create a strong insight.
32
And then we can write and write.
33
a LinkedIn post you may clawed your thinking partner now.
34
Of course, like all AI, it will not do what you tell it to do, not the first time around at least.
35
And sometimes it's going to be super frustrating because you'll give this detail prompt and just crap will come back.
36
So there are three things that you can do that can become your power moves when that happens.
37
calendar, your Notion app, anything else you can.
38
That way you can attach files to that chat session.
39
It will read it, it'll get context from it.
40
Second, ground your insights with research.
41
You can ask Claude to go out on the web and do deep research.
42
It has already learned the entire internet during its training, so why not use it?
43
But when you get the research back, always ask one more time,
44
build your AI skill in real time.
45
If you're patient and curious, you can literally build your engine while you're flying the plane.
46
For instance, let's say you have no background in corporate finance and you're building a financial model.
47
You get stuck on how to use a specific spreadsheet feature or even a financial concept like IRR or free cash flow.
48
No problem.
49
Just start another chat in another tab and ask away so you can learn and do.
50
Do and learn.
51
The cycle just continues.
52
Now let's go meet our second member of your team.
53
This one helps you remember and it's called Claude projects.
54
We all know when we're creating something new or solving a complicated problem,
55
the work doesn't end in one session or even in one chat.
56
And that's why all three AI platforms nowadays have gotten better at maintaining memory across different chat sessions.
57
Claude remembers your world through projects.
58
A project is where you give the chatbot your files, your instructions, tone, your ongoing work,
59
you're not starting from zero, every time you open it.
60
And of course, I would be careful about sharing confidential documents from your office.
61
But let's say you're actively or passively looking for a career change or a new job opportunity.
62
You can create a project.
63
You drop in your resume, your LinkedIn profile, the two or three job descriptions that you like or the company you're targeting,
64
your writing samples, your professional bio, the other resumes that you like.
65
with exactly what you need.
66
So you can add something like,
67
you're the world's most badass recruiter and resume writer who has placed candidates in top companies in my industry.
68
I am a brand marketer with five years of experience at a large agency called WPP.
69
Your job is to help me create a great story for my next adventure, for my next company, and make me desirable for the next role.
70
I write in a direct, confident tone.
71
I don't like corporate fillers.
72
I hate buzzwords.
73
When I ask you to tailor something, mash the job descriptions language without losing my voice.
74
When I ask you to do deep research, make sure you deliver only the relevant and verified data.
75
Don't make it up.
76
And when I ask you for feedback, be honest.
77
Tell me what's weak and what I need to work on.
78
strengthen those areas.
79
This is one way to provide instructions, but you can see that there are a hundred ways to do it.
80
And that's the kind of instruction that makes any project your own.
81
Not a prompt that you're copying from some YouTuber,
82
but a brief that you write for someone you actually know very well: yourself.
83
From that point on, Every time you come back Claude already knows what you want and who you are.
84
You can ask it to tailor a cover letter, craft a specific bullet of your resume for a specific role,
85
a project, turns Claude from a one -off conversation into an ongoing relationship between you and your AI.
86
This is also why I don't customize Claude at the account level.
87
I like customizing it at the project level because that way I can give it specific context.
88
Because using AI to plan your vacation is very different from using it to plan your retirement.
89
Now let's go to execute and for that we have our third team member Claude Cowork.
90
Chat is where the work begins.
91
Cowork is where it gets done.
92
You start in a prompt window, but finish it on your desktop.
93
Cowork is a desktop application for Mac or Windows.
94
Unfortunately, it's available only on Claude's paid plans right now.
95
But with Cowork, instead of asking a question, you give it a task.
96
When do you use Cowork versus chat?
97
Well, you use Cowork when you have a lot of assets already on your computer's hard drive.
98
When the task needs multiple steps steps and when you need
99
that output to be on your local drive as a local file.
100
So for example, you can tell cowork to do the following, take all of these customer interview transcripts from this folder,
101
these spreadsheets of accounts and notes from last week's product meeting, find top three reasons on why the customers are churning.
102
Why are they leaving?
103
provide all the supporting data, create a very clean slide deck that I can use tomorrow, put that slide deck in this folder.
104
And here's what makes Cowork even more interesting.
105
It can reach out to other AI tools through a connector called MCP, the model context protocol.
106
Think of MCP as giving Claude a set of keys
107
to other ai tools it can knock on their door unlock
108
the capabilities of those tools act with them act through them to give you results let me show you what
109
that means in a real example imagine you run a business
110
selling handcrafted candles you have a small business you have a terrific product
111
but you're bootstrapping your business right and you don't have a huge marketing budget in the old super polished or professional.
112
But now look at what you can do when you can plug Claude into a creative AI tool called Hicksfield.
113
They are the sponsor for this video.
114
Now Hicksfield is used by 18 million creators backed by tier one VCs like Excel
115
and Menlo Ventures and they've already crossed the billion dollar valuation
116
and they were the first creative platform to ship an official
117
And that's it go to settings connectors plus button paste the hicksfield url
118
and you're done that's it now you can go into co -work
119
and you tell it to do whatever you need to sell
120
more products for instance you could say generate 20 beautiful ad
121
creatives for my new lavender candle line three ideas for instagram three editorial close -ups for the website
122
and a vertical video for the launch you it just runs.
123
Claude Cowork writes the prompt and passes it on to Hicksfield.
124
Hicksfield generates the images and the video
125
and the entire set of files land in your local folder without you needing to hire a creative agency
126
and pay them thousands of dollars.
127
That would have taken you three weeks of a professional shoot,
128
a photographer, a stylist, and weeks of post -production and of session with Claude and Hicks field.
129
This is how AI is leveling the playing field.
130
A solo founder with the right set of tools today can now produce the kind of creative output
131
that used to require a large team and a large budget.
132
There is a link in the description below.
133
They have a free tier.
134
Take it for a spin, try it, and you could build something very cool and interesting this weekend two things to keep in mind.
135
First, the output will be a starting point.
136
You'll still have to go through each and every slide and make sure it's good.
137
But a lot of heavy lifting is done by Claude Cowork already.
138
Second, give explicit permission for Claude Cowork to access only specific directory and specific files.
139
Claude is very conscious about security, but please be very mindful about what you give access to.
140
And I usually create a subfolder and move all the files and data into that folder.
141
And that's all Claude has access to.
142
It's called sandboxing.
143
So the rest of your hard drive remains secure, Claude can't get to it.
144
Fourth is build.
145
And this is where Claude Code comes into play.
146
This is the part that makes a lot of us nervous.
147
It made me nervous.
148
The moment we hear code, We're like, "Ah, I don't know." We assume that all that stuff is only for engineers.
149
But that assumption is one of the biggest missed opportunities in AI right now.
150
If you can type in English, you don't need a computer science background to code and build something cool and useful.
151
Let's say you have a consulting business or a side hustle.
152
Simple example.
153
Just go to Claude Code and prompt.
154
I want a dashboard where I can drop in my sales pipeline
155
and meeting nodes and instantly see which deals are at risk, what's stuck, and what my next move should be.
156
That's all you need.
157
You don't need to think like an engineer to start using clot code.
158
You just need to be clear about the problem you want to solve.
159
the thing you want to build.
160
And of course you have to have the right data so that dashboard you build is useful.
161
And finally the fifth team member is for browsing the internet.
162
And for that you can use Claude Chrome.
163
And you're gonna go, wait what?
164
Don't worry.
165
Claude has this little extension that you can install in your Chrome browser.
166
can let Claude see what you're looking at as well, help you process it and act inside your workflow in real time.
167
And I think about this a lot nowadays because most of my work happens inside the browser, right?
168
My files are on Google Drive or Microsoft OneDrive, my emails, my scheduling, my team meetings, my research, filling out forms,
169
making purchases, And now Claude is right there with you for all of it.
170
You're on a job listing site, Claude can read it and help you tailor your outreach.
171
You're reading a 40 page industry report, Claude can pull the three insights that matter the most, in real time.
172
So that is your team.
173
There are other team members, but these five are the most interesting and useful.
174
This is your stack.
175
But even with the full team working with you, make all the difference between the average and the elite mode.
176
That's where we go next.
177
Any AI's results depend on you.
178
Even with the full team of agents working for you, Claude is only as good as the input you give it.
179
But the super users who get exceptional output from Claude, they direct Claude the way they would direct a smart person they've just hired.
180
And the easiest way to do that is a framework I call Prime.
181
P is purpose.
182
When you prompt Claude, give it a precise goal.
183
Tell it what you need it to do.
184
Like, help me turn this messy proposal into a five -part organized document that looks like a sharp client memo.
185
R is research.
186
We talked about it before.
187
In many cases, you may need external research, to ground the response.
188
Ask it to go out and fetch it for you.
189
Ask it to verify it.
190
And sometimes the raw material may come from you.
191
Your notes, transcripts, files, examples, background, constraints.
192
Anything that Claude needs so that it can stop hallucinating or guessing.
193
"I" is for interview.
194
This is the hidden gem.
195
I really like how Claude does it.
196
In a lot of cases, choice questions and you pick the right choice
197
and based on what you clicked and It refines its approach to a specific way of responding to you.
198
M is for mechanics.
199
Here you tell Claude, how the output should look like.
200
Do you want bullets or a paragraph?
201
Do you want a document or a table?
202
Do you want it concise or you want detail?
203
strategic or conversational, anything you choose.
204
And finally E is for examples: Show Claude what good looks like a format you liked, or a tone reference.
205
or an outline that worked before.
206
Examples are one of the fastest ways to quality.
207
Let's go through an example.
208
You have an important presentation coming up tomorrow.
209
run it through Prime purpose.
210
What is this meeting really for?
211
Do you need an approval?
212
Alignment?
213
Are you asking for resources?
214
What is the outcome you really want?
215
Research.
216
Give Claude the context.
217
What's the audience like?
218
The risks?
219
The data?
220
What your team cares about?
221
external resources, internal docs, anything you can give.
222
Interview.
223
So tell Claude, interview me before you respond.
224
Now it will ask you questions that sharpen its own scope and your thinking.
225
Mechanics.
226
Now you know the output of that deliverable.
227
You want a 10 slide deck and talking points.
228
And finally, examples.
229
Give it a past deck that you liked or style you admire.
230
So that is prime.
231
Once you start doing that, AI stops being a true and starts becoming your edge.
232
And by the way, if you want the frameworks like these in your inbox, subscribe to my newsletter.
233
The link is below somewhere and it's free.
234
The real edge is the human using it.
235
Everyone watching this feels like someone else is getting ahead faster.
236
that they are smarter or they're richer or they have better resources.
237
I know I feel like that sometimes.
238
That is the default condition of ambition.
239
The question is not whether you are outgunned.
240
The question is how you outshine when you are.
241
You have been carrying labels for years.
242
I am not technical.
243
I'm not a designer, I don't have an MBA, but Those are just labels.
244
For $20 a month, you can hire something that is already better than most MBAs and PhDs now.
245
You can think more sharply with it.
246
You can design better.
247
You can code.
248
You can build.
249
But do you have the curiosity to keep learning?
250
the tenacity to get through that machine friction.
251
the patience to build real capabilities,
252
or will you slowly replace real effort with convenience and lose your instinct to wonder.
253
AI will give you a lot of things.
254
But what AI can't give you is that innate curiosity that made you press play on this video.
255
And you already have it.
256
As one of my mentors used to say, "You're the one you've been waiting for." Thank you.
257
And I love you.

Download App

Everything you need to speak fluently

AI PronunciationScore every sentence
IPA PracticeMaster every sound
VocabularyBuild your word bank
Vocab GameLearn while playing

Same Channel

FOR YOU

Recommend Video

Vocabulary and speaking notes for this lesson

This video has 257 sentences and 2806 words to shadow. The speech runs for 19:30. The speaker talks at a steady 144 words per minute, a comfortable pace for shadowing. 82% of the words are among the 3,000 most common in English; the rest is worth studying before you start.

Key vocabulary in this video

15 words from the video worth learning, with pronunciation and meaning:

WordPronunciationMeaning
prompt verb/pɹɑmpt/To lead (someone) toward what they should say or do.
output noun/ˈaʊtpʊt/Production; quantity produced, created, or completed.
deck noun/ˈdɛk/Any raised flat surface that can be walked on: a balcony; a porch; a raised patio; a flat rooftop.
slide noun/ˈslaɪ̯d/An item of play equipment that children can climb up and then slide down again.
folder noun/ˈfoʊldɚ/An organizer that papers are kept in, usually with an index tab, to be stored as a single unit in a filing cabinet.
tone noun/ˈtəʊn/A specific pitch.
hire verb/ˈhaɪɹ/To obtain the services of in return for fixed payment.
input noun/ˈɪnpʊt/The act or process of putting in; infusion.
insight noun/ˈɪnsaɪ̯t/A sight or view of the interior of anything; a deep inspection or view; introspection; frequently used with into.
instruction noun/ɪnˈstɹʌkʃən/The act of instructing, teaching, or providing with information or knowledge.
resume verb/ˈɹɛz.ə.meɪ/To start (something) again that has been stopped or paused from the point at which it was stopped or paused; continue, carry on.
tailor noun/ˈteɪlɚ/A person who makes, repairs, or alters clothes professionally, especially suits and men's clothing.
browse verb/bɹaʊz/To scan, to casually look through in order to find items of interest, especially without knowledge of what to look for beforehand.
label noun/ˈleɪ.bəl/A small ticket or sign giving information about something to which it is attached or intended to be attached.
solve verb/sɒlv/To find an answer or solution to a problem or question; to work out.

Phrasal verbs you will hear

WordPronunciationMeaning
go through verbTo travel from one end of something to the other.
come back verbTo return to a place.
come up verbTo emerge or become known, especially unexpectedly.
fill out verb/fɪl ˈaʊt/To complete a form or questionnaire with requested information.
get ahead verbTo advance toward success.
get through verb/ɡɛt ˈθɹu/To overcome; to endure.
go out verbTo leave, especially a building.
work through verbTo get past a difficult or stressful situation by thinking or talking about it.

Pronunciation to watch

The speaker uses 44 contractions and reduced forms, such as you're, don't, you'll. Say them the short way, as you hear them.

  • The “th” sounds: strengthen /ˈstɹɛŋ(k)θən/, authenticity /ɑθɛnˈtɪsɪti/
  • The “sh” and “zh” sounds: instruction /ɪnˈstɹʌkʃən/, polish /ˈpɑ.lɪʃ/, notion /ˈnoʊʃən/, sharp /ʃɑɹp/, extension /ɪkˈstɛnʃən/
  • Long words — get the stress right: capability /ˌkeɪ.pəˈbɪl.ɪ.ti/, curiosity /ˌkjʊɹ.iˈɑ.sə.ti/, complicated /ˈkɑm.plɪˌkeɪ.tɪd/, photographer /fəˈtɑ.ɡɹə.fɚ/, editorial /ˌɛdɪˈtɔːɹɪəl/

How to practise with this video

  1. Listen to the whole video once without speaking and note the words you do not know.
  2. Shadow it sentence by sentence at normal speed, repeating each one until your rhythm matches the speaker.
  3. Record yourself and compare with the original, paying attention to words like prompt, output, deck.

Grammar in this video

The structures the speaker uses most, with the exact words from the video:

StructureIn the video
Present perfect continuous have/has been + -ing — an action that started earlier and is still going onhave been carrying · you've been waiting
“Used to” used to + verb — a past habit or state that is no longer trueused to require · used to say
Present perfect have/has + past participle — a past action that still matters nowI've been · we've talked · has already learned
Passive voice be + past participle — the focus is on what happens, not who does itis done · are outgunned

What is the Shadowing Technique?

Shadowing is a science-backed language learning technique originally developed for professional interpreter training and popularized by polyglot Dr. Alexander Arguelles. The method is simple but powerful: you listen to native English audio and immediately repeat it out loud — like a shadow following the speaker with just a 1–2 second delay. Unlike passive listening or grammar drills, shadowing forces your brain and mouth muscles to simultaneously process and reproduce real speech patterns. Research shows it significantly improves pronunciation accuracy, intonation, rhythm, connected speech, listening comprehension, and speaking fluency — making it one of the most effective methods for IELTS Speaking preparation and real-world English communication.

Shadowing technique: read the full step-by-step guide →