
10 Incredible Things ChatGPT Browser Use Can Do (Automate Everything) transcript
Paul J Lipsky · @PaulJLipsky
Words
3,926
Runtime
19:42
Speaking pace
199wpm
Reading time
16min
199 words per minute, between the 181 median and the 201 75th percentile of 349 measured videos. That distribution comes from the 349-video hook study.
Opening (first 30 seconds)
You probably know that the Chat GPT desktop app has a built-in browser, but most people don't realize just how powerful it really is. In fact, it's probably one of the most slept-on features inside of Chat GPT. The more I use it, the more I find automations and workflows that were previously either impossible or extremely difficult to set up. In this video, I'm going to show you everything you need to know about the Chat GPT browser to master yourself. And then I'll share 10 use cases ranging from the simple to the mind-blowing. Let's start out by
100 words, the words spoken in the first 30 seconds at 199 words per minute.
Sentence shape
| Measure | This transcript |
|---|---|
| Sentences | 209 |
| Average words per sentence | 18.8 |
| Longest sentence | 59 words |
| Questions asked | 3 |
| Sentences containing a number | 5 |
Most used terms
- chatgpt54
- browser52
- open26
- chat21
- click20
- ask15
- app14
- chat gpt12
- gpt12
- notion11
- chatgpt browser9
- start9
Filler phrases
36 in total: like 21 · actually 7 · you know 3 · basically 2 · I mean 1 · kind of 1 · right? 1.
A literal whole-word count of the same phrase list the Prepublish browser extension uses, so a phrase inside another word is not counted and a phrase used in its ordinary sense still is. It is a count and not a judgement.
What this transcript is
Every word below is the caption track YouTube publishes for this video, pulled from the video itself and reproduced unchanged. It is not Prepublish's writing, not a summary, and not a re-transcription: it is the video's own published captions. English captions, generated automatically by YouTube, in the video’s original language. Source: the video on YouTube. A channel that would rather this page did not exist can ask for its removal through the contact page, and it is removed.
Transcript
You probably know that the Chat GPT desktop app has a built-in browser, but most people don't realize just how powerful it really is. In fact, it's probably one of the most slept-on features inside of Chat GPT. The more I use it, the more I find automations and workflows that were previously either impossible or extremely difficult to set up. In this video, I'm going to show you everything you need to know about the Chat GPT browser to master yourself.
And then I'll share 10 use cases ranging from the simple to the mind-blowing. Let's start out by opening up the Chat GPT desktop app. I want to start by showing you how the browser works and all of its features. If you feel like you've already got that down, I encourage you to stick around anyway because I may surprise you with something new. But if you're confident you know everything about the browser and you just want the use cases, you can skip around using the timestamps down below.
Once you have the Chat GPT desktop app open, click on this icon on the top right to toggle open the side panel. And you may see two choices in here. You may see files and browser, or you may just see browser. Obviously, we are going to click on browser to open the browser. And this is it. I'm going to click on this button right here to expand it to make it larger and easier to look at. And this is pretty much a standard browser.
So up here, you can enter in any URL. You can open up multiple tabs, and you can use the URL up here as a search bar. And just like with a regular browser, there's a back button, there's a forward button, and there's a refresh. If this is your first time using the browser, one thing you may want to do is click on these three dots over here on the right, and then click on import cookies and passwords. And this can bring in your browsing history, your cookies, and your saved passwords from the browser that you were using before like Chrome.
You can just select the correct Chrome profile, and then click on import. So yeah, it's a browser, but unlike a traditional browser, this has Chat GPT built in. So at any point, you You click down here where it says work with ChatGPT. That will expand it and you can ask ChatGPT questions about the tab that you have open, about all the tabs you have open, or you can even ask it to take over your browser for you and start clicking around.
There's also an annotation button up here. So, if you click on this, you can now select elements on the page and ask ChatGPT questions about those elements. And you'll understand more what this feature does and why it's useful when we run through some of those use cases in a second. But before we do that, we have to look at the browser settings and change some things there. So, to unselect the annotation, you can click up here where it says annotating.
That will unselect it. And now we can come into the settings by clicking on our name on the bottom left and then click on settings. And then on the left, under integrations, select where it says browser. Now, there are a lot of settings here, but there are only a couple that I suggest that you change. So, first, make sure you have this toggled on where it says let ChatGPT control the built-in browser. Then, if you want, under general, I have where it says web URL and link open destination, I chose ChatGPT.
Because what that will do is if ChatGPT in the chat sends you a link and you click on it, it will open it up in the ChatGPT browser. If you don't want that, you can select your default browser and then it will open Safari or Chrome or Firefox, whatever you use. But I like using the ChatGPT browser for that. That way I don't have too many windows open. I also do the same thing for the next option, which is local URL open destination.
Down here is an option for annotation screenshots. I just showed you annotations, but if you have this enabled, this gives ChatGPT more context when answering your questions. It does say that it increases your plan usage. However, I found it to be very useful, so I leave that one on. Scrolling down, we have some settings for auto fill and passwords and downloads. if you want to change the download location. But, the really important thing is down here under permissions.
First, look at approval. This is where you can choose whether ChatGPT can open websites on its own without asking for permission, or if it should always ask for permission before opening a website. You can make that choice for yourself, and we have a similar choice for browsing history. You can choose if ChatGPT can always look at your browsing history, or if it first has to ask permission to access your history. But, there are always these specific site permissions that override those defaults.
So, let's say you're not yet comfortable giving ChatGPT full access to the web without it asking you for permission. So, you would select right here where it says always ask. But, let's say there are a couple of sites where you do feel comfortable, all you have to do is click on add here, put in the name of the website, and then choose the rule for it. So, for this one, I want ChatGPT to always have access to facebook.com.
Let's say I have a schedule set up where every day it's going through my Facebook feed and looking for potential leads. I want that to be done automatically on its own, so I need to give it permission to access Facebook all the time. So, that's why I'm doing that here, and then I can click on add. And so, even though ChatGPT normally under these settings has to always ask for permission before opening websites, if the website is facebook.com, it no longer has to ask me for permission.
So, what's great about this is that you can get very granular with the controls. I'm going to delete this one and switch this back to always allow though, cuz those are the settings I prefer. Okay, so now that your browser is set up and you have a general idea of how it works, let's dive into some of the use cases so you can get a better idea of what you can do with ChatGPT browser use. This first use case is pretty simple, but it's worth mentioning.
You can use the ChatGPT browser as a browser. And because you can open multiple tabs and it stays logged in for you between sessions, it's a pretty capable browser, especially because it has Chat GPT built in. So, when you come across something like an article that you want AI to summarize for you, all you have to do is click down here where it says work with Chat GPT and type in your question like, "Summarize this article." Now, usually when I'm using the Chat GPT browser, I like to switch which the model slider down so it's a little bit faster because I don't want a slow model when I'm browsing the web or doing things.
I want it to work a little bit quicker. When you have it in this mode where it's full screen like this, you'll be able to see your thinking and sorry, the model's thinking and the answer by clicking on this chevron right here and that will open it up. You can see right here it is reading the article and pulling out the main points. So, this is all of its thinking and then here is the summary. But, if you don't like this where you have to expand this up and down, you can always click on the top right here where it says restore panel width and then you'll have the browser over here on the right and the chat over here on the left.
And you can hover over the split right here and hold it down to make either side as big or small as you want. Now, for this second use case, what I'm not going to do is I'm not going to show you how Chat GPT can fill out forms for you because that's what everyone else on YouTube demos. And I don't think it's a very good demo because browsers already have autofill built in and that's much faster. But, there was a similar situation that came up for me recently where Chat GPT really was helpful.
Every year for my business, I have to file an annual report with my state and every year I forget how to do that. There's some website I have to go to and I never remember where it is. This year, I just told Chat GPT to start the process for me and to get me as far as it could before I had to take over. And because ChatGPT already knows a lot of information about my business, it was able to get me pretty far. Of course, I didn't just sit and watch it do this.
I had this running in the background while I was working on another task. So, that taught me that if there's a task that needs to be done online and I would ordinarily ask ChatGPT how to do it, what I really should be doing is just asking ChatGPT to do it for me. Then, while it's working, I can spend time on a task that I actually do know how to do. For this third use case, I'm going to show you another task that you can offload to ChatGPT.
Talking to customer support. So, let's say I purchased a drill recently from Home Depot that I want to return. What I'm going to do is just ask ChatGPT to do that return for me. Can you use your browser to open up homedepot.com and open up the live chat and return the drill that I recently purchased, the email information, the information about it's in my email, I mean. And while it's working, you may have noticed that I specifically told it to open up the browser.
I find that that often helps to either say that or to say use browser use because sometimes it tries to do everything through plugins and it doesn't realize or remember that it has access to a browser. So, sometimes using that language can help. Now, as we are talking, you will see right here that this little window pops up. This is a preview of what it's doing. So, even if you have the side panel closed and you're not able to see the browser, you always see a preview of it right here.
If you wanted to, you can hide it, but to see the full thing, you can expand the side panel right here. And then, here is the Home Depot tab, which it has opened. So, it already accurately founded found the chat right here and it clicked on start a return. And now, Home Depot's asking for the order number. It correctly pulled that and pasted it in. It got that from my email, and now it's off to you actually do the return.
So, that's again something I can have running in the background while I'm working on something else, and if a problem comes up, ChatGPT will let me know, and then I can take over the browser and fix any issues. But, I've used this already, and it's already been able to return a bunch of stuff for me, which is really nice because, you know, that's something I could sit and just watch and do myself, but it's nice when it's just automated and running for me.
For this use case, I'm going to show you two cool things that I use ChatGPT browser for. First, you can have it open multiple tabs for you, and with that, it's really good at helping you compare different products when you're shopping for something. So, let's give it a test right here. Hey, I have a Starlink a Starlink Mini that I want to attach to the top of my truck camper. Can you find like four or five different products that would do that?
I want ones that have good ratings and that would be easy for me to mount. Pull all of them up as separate tabs in the browser. And here we go, it's getting to work opening up all five of these or four of these four or five of these different tabs with the different products. And hope you're seeing like a little bit of a theme here, right? Because in the past, we used to ask ChatGPT how to do things, and then we would follow those instructions, but as long as you can do it on the web, you should just be asking ChatGPT to do all of it for you.
And here, it's not only gone out and done research like in the past, we would just have a list like this where we would have to click and open all of them. We don't have to do that anymore. It now opens up all the tabs for us, and we can see all of those right here. But, of course, it works the other way as well. So, if you were doing research on your own, let's say you didn't want to ask ChatGPT to do the research, and you just on your own found all of these different options, you can then come into ChatGPT here and say something like, "Create a table comparing the features of all of these mounts." And it can look at all the tabs that you have open when it's writing its response.
And there we go. I mentioned before how ChatGPT will usually try to use a plugin before it uses browser use. And that makes sense. It really should do that. But there are some situations where it can actually use both together in a way that's very beneficial. Here, for example, on the left I have opened ChatGPT, and on the right I have opened the Notion app. This is not inside of ChatGPT. This is a separate app. And if you're not familiar with Notion, it's basically a note-taking app, and you can see one of my notes right here.
So, ordinarily what most people do is they use the Notion app and they work inside of here. And then, when they want ChatGPT to work on a document or page that they've created, they use the Notion plugin, which you can find just by doing the at symbol and typing in the name of the plugin, which is Notion. And then, they have to describe what the page is that they want ChatGPT to help them with. So, I may say, "Can you find the page called ChatGPT versus Claude in my video database and edit it to make it shorter?" But there's an easier way to do this.
So, let's full-screen the ChatGPT app, and I will come over to Notion on my browser. So, now I have the same page open in the ChatGPT browser instead of inside the Notion app. And I can use this the exact same way. I can come in here and make edits. And so, instead of using the Notion app, I'll start using Notion inside the ChatGPT browser. That way, if I want ChatGPT's help, all I have to do now is come down to ChatGPT down here and say to it, "Edit this to make it shorter." I don't have to tell it to use the Notion plugin.
I don't have to tell it which page I want it to edit. It has all of that context because it's able to see what I have open in the browser. And what's great about this is that it's going to use the browser for context, but it's going to use the plugin to actually take action because that's more efficient. And you can see that happening right here. It's editing the Notion page using the plugin. And then over here on the right, you can see it made those changes.
Use case number six is one of my favorite little hacks. You can have AI use AI. So here in the browser, I have opened grok.com and I'm signed in. I don't use Grok all that often, but I do find that it's helpful when I'm researching trending topics because it has real-time access to Twitter. So what I do, you know, is I've set up a skill called Ask Grok. So anytime I ask ChatGPT to do some research for me on a topic, it knows that in addition to doing its own research, it will open up the browser and also ask Grok to do research and pull in the results from that and include that in its full analysis and the report that it makes for me.
It just makes it a lot more comprehensive. Now, Twitter has an official API, which I could probably set up, but this was just a lot easier for me to set up. I didn't want to have to learn how to set up the API for Twitter or pay for it either. So I just use this and it seems to work. This seventh use case is kind of similar. Let's say you want to use ChatGPT with a certain app or tool, but when you come over to plugins, they're not available here or they're not available on the free plan of whatever app you want to connect with ChatGPT.
A lot of times, you can just use browser use instead. So for instance, I'm going to come over to LinkedIn. Here we go. And even though LinkedIn has a plugin, it's quite limited in what it can do. And it can't do what I need it to do, which is to really look through LinkedIn and look through my feed and find new leads because I'm thinking about starting an AI agency. But, with browser use, ChatGPT can do that. So, if I send that along, it will start that task and it will take over this browser and start looking around for me.
And there we go, it's starting to scroll. So, basically, this works for any website where you need to be logged in to really access the information that you want to see and that you want ChatGPT to be able to use. So, for example, I've seen other people use this for online support forums. So, ChatGPT could compile a list of all the biggest complaints for the software that the the online support forum is for. Be aware, though, that doing something like this does sometimes violate the terms of service for certain websites.
So, I just wanted to give you that warning. Use case number eight, I haven't actually heard anyone else talk about this before, but you can give ChatGPT its own email address, its own VoIP if you wanted, or really any chat service that you can access online. So, in addition to having its own email address, it also has its own Google Chat reminders, and I have it often send me messages on here. So, I will sometimes tell it, "Hey, start a task for me, and then when you're done, message me." And it knows that message me means open up the browser, open up Google Chat, and send me a message on there letting me know that you're done.
And the reason I do this is because even though I sometimes get notifications on my phone from the ChatGPT app when it's done with the task, I don't always get them. So, this makes sure that if it finishes something, I actually get alerted about it. So, really useful, so I'm not sitting in front of my computer all day waiting for it to finish. I can walk away, get a Google Chat message when it's done, and I can come back and see the completed task.
Again, there are other ways to do this, but this is fast, it's free, and it's easy. This ninth use case is really helpful if you like to use ChatGPT to vibe code websites or apps because you can open it up in the browser, look at it, and tell ChatGPT what changes you want to make using the annotation tool. So, let me expand this and let's say I don't like some of the graphics here like how I hover over this and it changes to orange.
So, what I'll do is I'll click on the annotate tool and I will select those elements. So, that's that one. And if I hold down shift, I can actually select multiple elements. Most people don't know that. And then you can add the comment right here. So, I'll say, "I don't like that this switches from blue to orange." Then if you click on enter, that will be added to the chat, but if you hold down command and click enter, that will just be sent to ChatGPT.
You can see it's working down here and working on those changes. And as it's working, what it can also do is on its own after it fixes those changes, it can take over the browser and look at it itself to make sure that it worked properly. If it hovers over these elements and they still turn orange, it'll know that it didn't fix it properly and it'll go back and fix it. And finally, ChatGPT's browser use is excellent for timing online bookings.
For example, I want to reserve a campsite at Rocky Mountain National Park. Some of these more ideal campsites though can be pretty hard to get. So, I'll just have ChatGPT take care of it for me. Find out when Rocky Mountain National Park opens up reservations for their campsites. Then schedule a task so right when the availability right when the campsite becomes available for the weekend of September 18th, you come into the website and reserve a campsite for me.
And now, instead of sitting at the computer waiting for those campsites to become available myself, ChatGPT is just going to handle it for me. So, there you go. That's how to get the most out of ChatGPT browser use and 10 mind-blowing things you can do with it. If you enjoyed this video, do me a quick favor. Give it a thumbs up and subscribe to the channel because I make content like this all the time showing you the best ways to use AI tools.
In fact, I have another video just like that right here for you. This one goes over the 10 concepts that you need to master to get the most out of the ChatGPT desktop app. So, if that interests you, click on this video right here and I'll see you over there in 1 second. Bye for now.
The words are the caption track's own and nothing is reworded or re-transcribed. Paragraph breaks are placed between sentences so the text reads as prose.
Use this transcript
Three free tools that work on the material around a video like this one. No signup, no login.
Hook Analyzer
Paste the first 30 seconds of your own draft for a hook score and rewrites.
Policy Pre-Flight
Check your draft against YouTube's advertiser-friendly guidelines before you record it.
Channel Skill Generator
Read this channel's public videos and transcripts, and download a writing brief for it.