Shadowing Practice: Learn 95% of ChatGPT Work in Under 20 Minutes - Learn English Speaking with Video

Kies een oefenmodus

Elke modus opent een volledig scherm oefenruimte.

239 zinnen

Als zinnen te kort of te lang zijn, klik op Bewerken om ze aan te passen.

You're in the right place if you use ChatGPT every day.

Know that ChatGPT Work is a major upgrade, but you're still using it like a normal chatbot because no one,

not even OpenAI, can explain what you're supposed to do differently.

Now ChatGPT goes from just answering questions to doing work for you by connecting to all of your tools.

Okay, Dominic, but what does that mean?

I guess I'll take a stab at this.

Here in ChatGPT Work, I've asked it to create a Google Calendar reminder for my brother's birthday.

A simple enough task that regular ChatGPT can do as well.

But watch what happens next.

In my next prompt, I tell ChatGPT Work to add a cake emoji to the event title, put reminder to buy gift in the calendar description,

and I also say to carry these rules forward for every birthday event.

And after fast forwarding, We can see the AI has saved both defaults for every future birthday event.

But what exactly does that mean?

To answer that, let's open a brand new session within ChatGPT Work and say, create a birthday reminder for Sam Elman on April 22nd.

And let's fast forward to see what happens.

And we see the cake emoji in the title and the gift reminder in the description, even though I never asked for either one in this session,

which illustrates ChatGPT Work's biggest advantage over regular ChatGPT.

ChatGPT work remembers the rules you want it to follow and carries them into future tasks.

So the more you teach it about how you work, the more useful it becomes.

And that's just the tip of the iceberg.

So let's get started.

Before diving in, let's first take a quick look at all the products you have access to.

On one end of the spectrum is good old ChatGPT chat.

I'm not gonna waste your time with this today.

On the other end, we have Codex, which is designed for coders and programmers.

So we're not touching this today either.

The middle is where it gets confusing because there are two versions of ChatGPT Work.

ChatGPT Work Web lives inside the web version of ChatGPT.

It has a few unique advantages, but it's a lot less capable than the desktop version.

ChatGPT Work Desktop is the one I recommend using for everyone who's not technical.

So that's what we'll be focusing on for the rest of this video.

Good job, OpenAI for making this so simple.

As an ex-Googler, I can tell you, we never made our product lineup so confusing for our consumers.

And something like this never ever bit us in the ass.

Once you've downloaded the desktop version of ChatGPT Work, you only need one other thing to unlock its full capabilities, a Google Doc.

Think of this document as the master rule book for ChatGPT Work, written entirely in plain English.

The purpose section explains how this document works, The global rule section contains the instructions ChatGPT Work follows for all tasks.

Voice principles controls how the AI writes and maintenance explains how ChatGPT Work should keep the file organized as it grows.

Taking a closer look at the Google Doc, we see that ChatGPT Work added the Google Calendar birthday rule from earlier as a subsection under global rules.

The voice principle section is thin on purpose because you'll learn how to teach it to sound like you later on.

And the same goes for the routing map.

I've linked the starter template for you down below.

And when you download this, make sure you go to files, download, and download as a markdown file, okay?

And you're gonna need to rename this exactly, all right?

You're not gonna rename this to like agent.

You're not gonna rename this to agent one.

You're gonna rename this to agents.md.

Exactly like that, okay?

Or ChatGPT work is not gonna recognize it.

Next, create a folder anywhere on your desktop, call it whatever you want.

For me, I'll just say Jeff Work OS.

And then we're gonna move the agents.md file into that folder, all right?

And then back in the ChatGPT desktop app, make sure the work toggle is selected.

And then under choose project, we're gonna pick that folder we just created, all right?

And once your folder has been added or mounted,

ChatGPT work will now automatically read your agents.md file before it performs any task.

And the best part is, you don't even need to manually maintain this file.

You can just tell ChatGPT work.

Remember this rule.

Whenever I ask you to rename image files, use a short but descriptive name so I know what each image is without opening it.

And let's just fast forward here.

Clicking into the agents.md file opens it up in the preview pane.

And we can see that ChatGPT work added a subsection under global rules with our file name convention.

Now I can drop a folder of photos into my WorkOS folder.

And in a new chat, I can say, rename the photos in the images folder.

And after about a minute, we're just gonna skip ahead here.

We can see the images have been renamed according to our new rule.

So just to be clear, ChatGPT Work could already analyze and rename images, but without rules in place,

it'll rename the photos differently every time, giving you inconsistent results which leads us to the most important takeaway from this video.

If you use ChatGPT Work without mounting a folder, you're basically using regular ChatGPT.

Once you mount a folder with an agents.md file inside,

ChatGPT Work reads that file before every task and follows your preferences so you get consistent results.

One thing I'm choosing not to cover today is the three ChatGPT models because that's a whole separate rabbit hole.

But luckily for us, today's sponsor HubSpot has a free guide that breaks it down.

It's one of the clearest explanations of which model is good for what.

And honestly, I've been making the mistake of defaulting to the most powerful model, SOL, for everything, wasting like a bunch of tokens.

But now I know better.

For a recent presentation, I started off using SOL to build the narrative

and to analyze a bunch of earnings call transcripts and financial statements.

Then I actually jumped to Luna to pull thousands of numbers from the financials into a spreadsheet.

And it was surprisingly fast and accurate.

Then finally, I used Terra to actually build out the slide titles and speaker notes.

Inside, you also get nine ready to run workflows from just getting started all the way to connecting Gmail, Slack and Drive for recurring automations.

So check out the free guide by clicking the link down below.

Thank you HubSpot for sponsoring this video.

Next up, let's see how we can supercharge plugins with our agents.md file.

As a quick reminder, plugins connect ChatGPT Work to tools you already use like Notion, Gmail, and Slack.

In Claude, this is called connectors.

And in Gemini, this is called connected apps.

And connecting to an app within ChatGPT Work is very easy.

You just go to plugins and then search for a tool like Google Calendar, and you simply follow the instructions.

But just giving access by itself isn't that useful.

teaching ChatGPT work how you like to use that app is another thing entirely.

And that's where the agents.md file comes in.

For example, with your folder mounted, start a new chat and say,

remember this, meetings default to 45 minutes and format Google calendar descriptions so they're easy to scan.

Start with bottom line up front, followed by three short bullets with relevant context.

And we're just gonna skip ahead here.

Opening up the agents.md file, we see ChatGPT Work added the new rule under Google Calendar rules directly, which is a great example of us,

100

the user, setting the rules and the AI doing the grunt work.

101

Now, in a fresh ChatGPT session, I can upload my apartment lease and say,

102

create a Google Calendar event for a call I have with my real estate agent tomorrow at 10 a.m.

103

I've attached my lease for your reference.

104

And let's fast forward.

105

And again, we see ChatGPT Work has created the event following the instructions saved inside our agents.md file.

106

45 minute event, bottom line up front with three bullets, even though we didn't repeat those instructions in the prompt.

107

But there's a problem.

108

Google Calendar is only one app.

109

And as you connect more, Notion, Gmail, Google Calendar, Teams, Granola, Spotify, so on and so forth,

110

adding all those rules for all those apps in one agents.md file will get very messy.

111

So here's a pro tip.

112

We can tell ChatGPT Work, create a tool conventions.md file that will house all rules governing tools moving forward.

113

Move every tool or plugin specific rule from agents.md into it.

114

Replace the moved content in agents.md with a link.

115

And we're just gonna send this off.

116

While that's working, let me quickly explain why we just did that.

117

ChatGPT Work loads agents.md before every single task.

118

So a bloated file means worse outputs and wasted tokens.

119

And since we're not using tools like calendar in every task,

120

moving those app specific rules into a separate file keeps agents.md lean and organized.

121

Opening up the newly created tool conventions file, we see that both the image file and Google Calendar rules got moved over.

122

And over in our agents.md file,

123

that entire section got replaced by a pointer to the newly created tool conventions file.

124

Now that you understand how plugins work together with agents.md, here are three useful plugin rules that you can add today.

125

For Gmail, never include a sign off in my Gmail replies because I already have a default signature set up.

126

For Notion, always use the existing templates in my Notion databases instead of creating pages from scratch.

127

For Slack, when summarizing Slack threads, always separate the output into decisions, action items, and open questions.

128

As a quick recap, plugins let you connect ChatGPT work to your apps.

129

And although by itself, this is nothing new, you can use agents.md to teach the AI how you use those apps.

130

By the way, my free cowork toolkit includes all the templates you need to organize your rules, folders, and workflows in one week.

131

Yes, it is built for Cloud Cowork, but the exact same logic and frameworks apply to ChatGPT Work, link down below.

132

Moving on to my favorite feature, the side panel.

133

So basically, the side panel in ChatGPT Work has three completely different functions.

134

First, it lets you preview and edit files as you've seen already.

135

Second, it's a fully functional browser, and we're gonna get into the benefits of that in a bit.

136

And third, I can use the side chat function to hide stuff from the main chat.

137

And this is not to be confused with a side chick.

138

Okay, that was really bad.

139

I'm kind of struggling today.

140

Hang on, hang on, hang on.

141

Starting with the preview pane, let's go through an example.

142

If we open up our tool conventions.md file in the side panel, we can highlight the entire Google Calendar section,

143

click Edit, and we can say, add a section for Gmail, Notion, and Slack using the same structure,

144

H2 headers, with clearly labeled placeholder rules under each one.

145

And let's fast forward, just a few seconds later, the same file has matching sections for all four tools.

146

And if you made a mistake, you can just click the undo button here.

147

I'm just gonna click redo.

148

Simple enough, right?

149

Pro tip, whenever you see a hyperlinked file or folder,

150

you can right click and choose show in finder or the windows equivalent to quickly locate it within your workspace,

151

letting you easily drag the file or folder into another location.

152

Next up, the in-app browser can be opened by pressing command and control T, right?

153

Just like opening up a new tab and typing in the URL.

154

And you should know that we could technically ask ChatGPT to open up the in-app browser in a prompt, but obviously that's super slow.

155

Why would we ever do this though?

156

Let's go through two real use cases.

157

Here, I'm on my partnerships page and instead of taking screenshots or copy pasting the URL, I can click the annotate icon,

158

select this specific section of the page and say, hey, create a preview of this section in dark mode.

159

And let's see what happens.

160

Think of annotation mode like leaving a comment directly on a website.

161

Instead of describing where something's on the page, I can point to the exact element and explain the change I want in plain English.

162

First, we see that ChatGPT Work gives us a mockup of how the dark mode would look, right?

163

Light mode, dark mode, which is already pretty cool.

164

Better yet, because ChatGPT Work is connected to my website hosted on Ghost,

165

I can actually ask ChatGPT Work to implement this change, which I did off camera.

166

Meaning, if you go to my website right now, You will see there is now a dark toggle and it looks pretty incredible.

167

To be clear, those were two separate steps.

168

Anyone can open a public webpage and ask for a mock-up,

169

but actually pushing the change live requires ChatGPT work to be connected to that platform.

170

A lot of you are gonna be horrified by this next example, but technically you can log into your accounts within the in-app browser.

171

So if you trust OpenAI and Scam Outlet, I mean, Sam Altman, you can hand off a lot of tedious work.

172

For example, I recently launched a course

173

and I had ChatGPT work test every single link within the lesson descriptions to check for dead links

174

and to confirm they all open up in a new tab so the learning experience isn't interrupted, which would have been super annoying to do manually.

175

Lastly, we can type forward slash side to open up a

176

temporary side chat I can see everything in the main conversation without interrupting anything.

177

So as an example, here I have an active task where ChatGPT work is reviewing a dense PDF.

178

And I have a question, but I don't want to interrupt the task.

179

And so I open side chat and ask, based on the uploaded PDF, what does personal assessment mean in plain English versus salaries tax?

180

And fast forwarding a little bit here, we see it answers my question without interfering with the main task.

181

A few things to know when using side chat.

182

It already has the context from the main task, so you don't need to re-explain or re-upload anything.

183

And second, nothing inside the side chat flows back into the main chat.

184

And third, closing it deletes the side chat, so you need to copy anything you want to keep.

185

As a quick recap of the side panel, here's the mental model to carry forward.

186

Use the preview pane to quickly review and or edit a file ChatGPT work surfaced in chat.

187

Use the in-app browser when the context you want to share with ChatGPT lives on a website.

188

189

You side chat when the question or tangent needs the same context as the main task, but shouldn't change the deliverable.

190

Now, let's move on to skills in the context of ChatGPT work.

191

As a quick reminder, a skill basically takes some sort of input, like messy notes, processes that against a checklist of rules you create,

192

and gives you an output, like a structured briefing.

193

Diving right into an example, here I'm in the middle of a working session where ChatGPT work gave me the first draft of my next newsletter.

194

and after making some edits, I've pasted the final draft I'm actually going to send out.

195

What I'm about to do next will teach ChatGPT work to sound like me for every newsletter moving forward.

196

In the same chat, I say, compare this final newsletter against your original draft earlier in this chat.

197

Identify the repeatable differences in my writing style, then create an improved skill I can run whenever I give you a draft and my final version.

198

Show me the proposed learnings before updating the voice principal section of agents.md.

199

Just to be super clear, we're doing two things here.

200

One, we're creating a skill called improve.

201

And second, the input we're giving it contains both the initial V1 draft and my final draft.

202

Then the skill compares the two to extract patterns and the output are the writing rules to carry forward.

203

Here we can see that ChatGPT work identified seven repeatable learnings, ignored changes not related to our tone of voice

204

and proposed updates to the voice principle section and created an improved skill that I can use in the future.

205

And after approving those updates, fast forwarding a little bit, we can then open the agents.md file to see all the changes.

206

And that's the key takeaway when it comes to using skills in ChatGPT work.

207

You are going to make those edits and corrections anyway.

208

So why not create skills that teach ChatGPT work your preferences so you re-explain yourself less and less over time.

209

All right, that covers the basics.

210

So let me share the next logical step on your way to building your own AI system.

211

Here in my Work OS folder, it looks a little empty, but what if I dragged another folder with my travel preferences in here?

212

And then in a new ChatGPT work session, I say, review the new travel folder I just added to this workspace.

213

Add a travel entry to the routing map So future travel related requests are routed to this folder.

214

Finish by showing me the exact entry you added and explain why.

215

And we're just gonna fast forward here.

216

I'm actually gonna ignore the output on purpose because it's not gonna make any sense to you right now.

217

Instead, I'm gonna start a new chat and say, I wanna plan a trip to Iceland.

218

How will this workspace handle that?

219

And after just a few seconds,

220

we see that, whoa, ChatGPT Work knows that this ask is related to like traveling and stuff,

221

and therefore should be managed within the travel folder we just added.

222

So what's going on?

223

How did it know?

224

Well, if I open up the agents.md file, we see that a new entry has been added to the routing map section, telling ChatGPT work that all travel

225

and trip related tasks should be routed to the travel folder since the travel folder holds all context related to planning trips,

226

like my Marriott membership, my seat preferences on flights, and what happened on previous trips.

227

In plain English, instead of maintaining one giant messy folder, the routing map lets us break our work into smaller subfolders,

228

one for each recurring part of our job or life.

229

And because I know a lot of you will ask, I use both ChatGPT Work and Claude Co-Work since I can just mount the same folder to both, right?

230

And you'll see in my actual like Jeff OS workspace, I have more than like 30 areas or like what I call workstations.

231

And I have agents.md that ChatGPT recognizes and a Claude.md that Claude recognizes.

232

And if you want something like this, but you don't want to build from scratch, my cowork Academy starts you off with the whole structure already built.

233

The folders, the routing map and the rule files.

234

It's taught in Claude cowork, yes.

235

But as you just saw, the same folder works in both.

236

Link down below.

237

If you found this useful, check out this tutorial next on how to give your AI system perfect memory.

238

See you on the next video.

239

In the meantime, have a great one.

App downloaden

Alles wat je nodig hebt om vloeiend te spreken

AI UitspraakScoor elke zin

IPA OefeningBeheers elk geluid

WoordenschatBouw je woordenschat op

WoordenspelLeren terwijl je speelt

Scan QR

Download on theApp Store Get it onGoogle Play

Zelfde Kanaal

FOR YOU

Aanbevolen Video

337 zinnen

Ultimate Guide To ChatGPT Codex for Everyday People

Business EnglishUniversity StudentsWorking Adults

17 zinnen

Did someone say... SecondBrain?

Business EnglishUniversity StudentsWorking Adults

46 zinnen

OpenAI’s new browser feels familiar…

Business EnglishUniversity StudentsWorking Adults

268 zinnen

Learn 97% of Claude in Under 16 Minutes

Business EnglishWorking Adults

78 zinnen

5 Things You Should Never Ask ChatGPT | Vantage with Palki Sharma

Business EnglishDaily ConversationUniversity Students

59 zinnen

An ex-OpenAI researcher just deleted language from the LLM...

Business EnglishUniversity StudentsWorking Adults

28 zinnen

Daily Stand-Up: Sharing Your Progress

Business EnglishWorking Adults

270 zinnen

Transformers, the tech behind LLMs | Deep Learning Chapter 5

Business EnglishUniversity StudentsWorking Adults

542 zinnen

The Future Of Work (& The New High-Income Skill Stack)

Business EnglishUniversity StudentsWorking Adults

The Art of Learning Like a Genius (even if you're not one)

307

34 zinnen

The Art of Learning Like a Genius (even if you're not one)

Business EnglishUniversity StudentsWorking Adults

Woordenschat en spreektips bij deze les

Deze video bevat 239 zinnen en 3385 woorden om na te spreken. Het gesproken deel duurt 19:29. De spreker praat in een natuurlijk tempo van ongeveer 174 woorden per minuut, dicht bij een alledaags gesprek. Slechts 79% van de woorden hoort bij de 3.000 meest gebruikte Engelse woorden, dus de woordenschat is pittig.

Belangrijke woorden in deze video

15 woorden uit de video die het leren waard zijn, met uitspraak en betekenis:

Woord	Uitspraak	Betekenis
folder zelfstandig naamwoord	/ˈfoʊldɚ/	hechtmap, map
calendar zelfstandig naamwoord	/ˈkæl.ən.də/	kalender
connect werkwoord	/kəˈnɛkt/	verbinden
reminder zelfstandig naamwoord	/ɹɪˈmaɪndə(ɹ)/	geheugensteuntje
mount werkwoord	/maʊnt/	beklimmen
skill zelfstandig naamwoord	/skɪl/	bekwaamheid, vaardigheid
edit werkwoord	/ˈɛdɪt/	bewerken, wijzigen
preview zelfstandig naamwoord	/ˈpɹiːvjuː/	voorsmaak, voorsmaakje
desktop zelfstandig naamwoord	/ˈdɛsktɒp/	desktop
output zelfstandig naamwoord	/ˈaʊtpʊt/	productie
plain zelfstandig naamwoord	/pleɪn/	vlakte
instruction zelfstandig naamwoord	/ɪnˈstɹʌkʃən/	onderwijs
preference zelfstandig naamwoord	/ˈpɹɛf(ə)ɹ(ə)ns/	voorkeur, preferentie
principle zelfstandig naamwoord	/ˈpɹɪn.sɪ.pəl/	principe, beginsel
upload werkwoord	/ˈʌpˌloʊd/	uploaden

Phrasal verbs die je zult horen

Woord	Uitspraak	Betekenis
check out werkwoord		onderzoeken
set up werkwoord	/ˌsɛt ˈʌp/	bereiden, voorbereiden

Grammatica in deze video

De structuren die de spreker het meest gebruikt, met de exacte woorden uit de video:

Structuur	In de video
Present perfect have/has + voltooid deelwoord — iets uit het verleden dat nu nog telt	I've asked · has saved · you've downloaded
Lijdende vorm be + voltooid deelwoord — het gaat om wat er gebeurt, niet om wie het doet	is designed · is selected · has been added
Betrekkelijke bijzinnen who / which + zin — extra informatie over een persoon of ding	Codex, which is · mode, which is

Uitspraak om op te letten

De spreker gebruikt 71 samentrekkingen en verkorte vormen, zoals gonna, we're, I'm. Spreek ze kort uit, zoals je ze hoort.

De “th”-klanken: thin /ˈθɪn/, thread /ˈθɹɛd/
De klanken “sh” en “zh”: instruction /ɪnˈstɹʌkʃən/, partnership /ˈpɑɹtnɚʃɪp/, explanation /ˌɛkspləˈneɪʃən/, establishment /ɪˈstæb.lɪʃ.mənt/, presentation /ˌpɹɛzn̩ˈteɪʃn̩/
Lange woorden — let op de klemtoon: differently /ˈdɪf.ə.ɹənt.li/, technically /ˈtɛk.nɪˌkəl.i/, manually /ˈmænj(u)əliː/, temporary /ˈtɛmp(əˌɹ)ɛɹi/, explanation /ˌɛkspləˈneɪʃən/

Zo oefen je met deze video

Luister de hele video één keer zonder te spreken en noteer de woorden die je niet kent.
Begin op 0,75× snelheid, spreek zin voor zin na en ga terug naar normale snelheid zodra het makkelijk gaat.
Neem jezelf op en vergelijk met het origineel; let daarbij op woorden als folder, calendar, connect.

Wat is de Shadowing-techniek?

Shadowing is een wetenschappelijk onderbouwde taalleermethode die oorspronkelijk is ontwikkeld voor professionele tolkentraining en gepopulariseerd door polyglot Dr. Alexander Arguelles. De methode is eenvoudig maar krachtig: je luistert naar native Engelse audio en herhaalt het onmiddellijk hardop — als een schaduw die de spreker volgt met slechts 1–2 seconden vertraging. In tegenstelling tot passief luisteren of grammaticadrills, dwingt shadowing je hersenen en mondspieren om echte spraakpatronen tegelijkertijd te verwerken en te reproduceren. Onderzoek toont aan dat het de uitspraaknauwkeurigheid, intonatie, ritme, verbonden spraak, luisterbegrip en spreekvaardigheid aanzienlijk verbetert — waardoor het een van de meest effectieve methoden is voor IELTS Speaking-voorbereiding en echte Engelse communicatie.

Shadowing-techniek: lees de volledige stap-voor-stap-gids →

Shadowing Practice: Learn 95% of ChatGPT Work in Under 20 Minutes - Learn English Speaking with Video

Kies een oefenmodus

App downloaden

Write a Killer Résumé in the AI Era: 5 New Rules!

How I'd Learn AI From Scratch in 2026 (skip the useless 80%)

Tell Me About Yourself (The BEST Way to Answer this Interview Question)

Why Are You a Good Fit for this Role - How to Answer

What is Your Biggest Weakness? (Ace this Interview Question!)

Claude Design is Insanely Easy (even for beginners)

Tell Me About Yourself - Structure a Strong Answer

7 Job Interview Questions to Prepare For!

AI Agents, Clearly Explained

How to Get Started with Notion (without losing your mind)

Google’s AI Course for Beginners (in 10 minutes)!

Tell me a time You Handled a Difficult Situation (Interview Question)

Ultimate Guide To ChatGPT Codex for Everyday People

Did someone say... SecondBrain?

OpenAI’s new browser feels familiar…

Learn 97% of Claude in Under 16 Minutes

5 Things You Should Never Ask ChatGPT | Vantage with Palki Sharma

An ex-OpenAI researcher just deleted language from the LLM...

Daily Stand-Up: Sharing Your Progress

Transformers, the tech behind LLMs | Deep Learning Chapter 5

The Future Of Work (& The New High-Income Skill Stack)

The Art of Learning Like a Genius (even if you're not one)

Woordenschat en spreektips bij deze les

Belangrijke woorden in deze video

Phrasal verbs die je zult horen

Grammatica in deze video

Uitspraak om op te letten

Zo oefen je met deze video

Wat is de Shadowing-techniek?