Codex's Browser Agent Automates Literally Anything

Codex's browser use is probably the best Codex's browser use is probably the best that I've ever tried before. It can that I've ever tried before. It can that I've ever tried before. It can literally do anything on a browser or on literally do anything on a browser or on literally do anything on a browser or on your actual local computer. And if you your actual local computer. And if you your actual local computer. And if you need to be signed in for something, you need to be signed in for something, you need to be signed in for something, you just sign in once and Codex will save just sign in once and Codex will save just sign in once and Codex will save it. So, the possibilities are endless. it. So, the possibilities are endless. it. So, the possibilities are endless. You can actually automate anything now. You can actually automate anything now. You can actually automate anything now. Let me show you guys how to set it up, Let me show you guys how to set it up, Let me show you guys how to set it up, how easy it is, and a few good use how easy it is, and a few good use how easy it is, and a few good use cases. All right. So, I'm using the cases. All right. So, I'm using the cases. All right. So, I'm using the Codex desktop app, which is just Codex desktop app, which is just Codex desktop app, which is just honestly the main way that I like to honestly the main way that I like to honestly the main way that I like to drive Codex. It's super, super slick. drive Codex. It's super, super slick. drive Codex. It's super, super slick. And we get the browser to pop up on the And we get the browser to pop up on the And we get the browser to pop up on the right-hand side, which I'll show you right-hand side, which I'll show you right-hand side, which I'll show you guys in a sec. So, luckily we live in a guys in a sec. So, luckily we live in a guys in a sec. So, luckily we live in a world now where most tools that we need world now where most tools that we need world now where most tools that we need to use have an API guy. So, it's much to use have an API guy. So, it's much to use have an API guy. So, it's much easier to just connect Codex through the easier to just connect Codex through the easier to just connect Codex through the API. Or, if we just go to the plugins, API. Or, if we just go to the plugins, API. Or, if we just go to the plugins, there's hundreds of plugins in here. there's hundreds of plugins in here. there's hundreds of plugins in here. But, every once in a while we don't have But, every once in a while we don't have But, every once in a while we don't have an API, and you can do that with browser an API, and you can do that with browser an API, and you can do that with browser use. But, before I show you an use. But, before I show you an use. But, before I show you an automation like that, let's just take a automation like that, let's just take a automation like that, let's just take a look at this example where you might be look at this example where you might be look at this example where you might be building a website. You might be building a website. You might be building a website. You might be building some sort of app. And you need building some sort of app. And you need building some sort of app. And you need a browser, an agent, to actually test a browser, an agent, to actually test a browser, an agent, to actually test through things. If you guys watched a through things. If you guys watched a through things. If you guys watched a recent video I did on like building an recent video I did on like building an recent video I did on like building an AI SaaS in one day, then this was AI SaaS in one day, then this was AI SaaS in one day, then this was actually from that demo where I had a actually from that demo where I had a actually from that demo where I had a browser agent get spun up and test the browser agent get spun up and test the browser agent get spun up and test the heck out of our app. And it did 85 heck out of our app. And it did 85 heck out of our app. And it did 85 focused auto- mation checks with real focused auto- mation checks with real focused auto- mation checks with real browser workflow testing, which means it browser workflow testing, which means it browser workflow testing, which means it was clicking around, it was typing was clicking around, it was typing was clicking around, it was typing things, it was hitting buttons, and it things, it was hitting buttons, and it things, it was hitting buttons, and it was trying to break the app. And it was trying to break the app. And it was trying to break the app. And it found a ton of bugs, and then we were found a ton of bugs, and then we were found a ton of bugs, and then we were able to just fix them. So, in this able to just fix them. So, in this able to just fix them. So, in this example, I have a super simple website example, I have a super simple website example, I have a super simple website spun up here on the localhost. It's a spun up here on the localhost. It's a spun up here on the localhost. It's a form submission, as you can see. And form submission, as you can see. And form submission, as you can see. And there's a few issues before we actually there's a few issues before we actually there's a few issues before we actually go ahead and start testing this thing.

go ahead and start testing this thing. go ahead and start testing this thing. You can see like this spacing is weird. You can see like this spacing is weird. You can see like this spacing is weird. This thing is overlapping. And so, what This thing is overlapping. And so, what This thing is overlapping. And so, what you can do is you can click on this you can do is you can click on this you can do is you can click on this annotate button, and that lets you annotate button, and that lets you annotate button, and that lets you choose very specific elements to choose very specific elements to choose very specific elements to actually change. So, I can click right actually change. So, I can click right actually change. So, I can click right here on this phone number box, and I can here on this phone number box, and I can here on this phone number box, and I can describe, "Hey, this is kind of like describe, "Hey, this is kind of like describe, "Hey, this is kind of like overlapping. It's out of bounds. It's overlapping. It's out of bounds. It's overlapping. It's out of bounds. It's covering up the company box. So, I need covering up the company box. So, I need covering up the company box. So, I need you to fix this." And then, when you you to fix this." And then, when you you to fix this." And then, when you shoot that off, it actually goes over shoot that off, it actually goes over shoot that off, it actually goes over here into your chat. And then, you can here into your chat. And then, you can here into your chat. And then, you can make another annotation like, "Okay. So, make another annotation like, "Okay. So, make another annotation like, "Okay. So, this whole box isn't really aligned on this whole box isn't really aligned on this whole box isn't really aligned on the same Y axis as number one and number the same Y axis as number one and number the same Y axis as number one and number three. So, you need to fix that as three. So, you need to fix that as three. So, you need to fix that as well." And then, those annotations are well." And then, those annotations are well." And then, those annotations are saved over here, and we can just go saved over here, and we can just go saved over here, and we can just go ahead and shoot them off. So, that's ahead and shoot them off. So, that's ahead and shoot them off. So, that's kind of like a lovable style or like a kind of like a lovable style or like a kind of like a lovable style or like a cloud design style thing that you can do cloud design style thing that you can do cloud design style thing that you can do with the in-app browser in Codex. What with the in-app browser in Codex. What with the in-app browser in Codex. What else is really cool about this is that else is really cool about this is that else is really cool about this is that you can actually just drive this thing. you can actually just drive this thing. you can actually just drive this thing. So, you can go to Google, you can search So, you can go to Google, you can search So, you can go to Google, you can search for Grand Canyon images, you can go to for Grand Canyon images, you can go to for Grand Canyon images, you can go to all, you can go to different links if all, you can go to different links if all, you can go to different links if you want. You can use the browser right you want. You can use the browser right you want. You can use the browser right here while you have Codex open. But, of here while you have Codex open. But, of here while you have Codex open. But, of course, Codex can also just take control course, Codex can also just take control course, Codex can also just take control of it. Now, we can see right here is my of it. Now, we can see right here is my of it. Now, we can see right here is my mouse, but also this is what Codex's mouse, but also this is what Codex's mouse, but also this is what Codex's mouse looks like. And that's how you mouse looks like. And that's how you mouse looks like. And that's how you know it's now sort of getting ready to know it's now sort of getting ready to know it's now sort of getting ready to take control of the browser. Okay, so take control of the browser. Okay, so take control of the browser. Okay, so now that those changes have been made, now that those changes have been made, now that those changes have been made, let's actually start testing out our UI.

let's actually start testing out our UI. let's actually start testing out our UI. I want to see things that maybe me as a I want to see things that maybe me as a I want to see things that maybe me as a human, I would maybe go through here and human, I would maybe go through here and human, I would maybe go through here and test like five or six edge cases, but we test like five or six edge cases, but we test like five or six edge cases, but we can see how Codex can do it way quicker can see how Codex can do it way quicker can see how Codex can do it way quicker and way more. Okay, so you have the UI and way more. Okay, so you have the UI and way more. Okay, so you have the UI open. I want to make sure that there are open. I want to make sure that there are open. I want to make sure that there are no bugs. I want to make sure that this no bugs. I want to make sure that this no bugs. I want to make sure that this thing can't break. So, what I want you thing can't break. So, what I want you thing can't break. So, what I want you to do is use your browser use and just to do is use your browser use and just to do is use your browser use and just test the heck out of this thing. Try test the heck out of this thing. Try test the heck out of this thing. Try different things, try your best to break different things, try your best to break different things, try your best to break it, and let me know what bugs you find it, and let me know what bugs you find it, and let me know what bugs you find and what things we need to fix. And so, and what things we need to fix. And so, and what things we need to fix. And so, by the way, while this is running, by the way, while this is running, by the way, while this is running, there's a difference between browser use there's a difference between browser use there's a difference between browser use being headless or headed. Headless means being headless or headed. Headless means being headless or headed. Headless means it's running in the background, so you it's running in the background, so you it's running in the background, so you can keep working in the foreground, and can keep working in the foreground, and can keep working in the foreground, and you won't actually see it going on, but you won't actually see it going on, but you won't actually see it going on, but it can run a lot of things in the it can run a lot of things in the it can run a lot of things in the background. But, if you want it to be background. But, if you want it to be background. But, if you want it to be headed, that's basically where you're headed, that's basically where you're headed, that's basically where you're able to see it. So, we're probably going able to see it. So, we're probably going able to see it. So, we're probably going to be able to see some things right to be able to see some things right to be able to see some things right here, but if you wanted this to just here, but if you wanted this to just here, but if you wanted this to just work for a few hours for you headless in work for a few hours for you headless in work for a few hours for you headless in the background, you could ask it to do the background, you could ask it to do the background, you could ask it to do so, and then it wouldn't disturb so, and then it wouldn't disturb so, and then it wouldn't disturb whatever work you're doing. So, if you whatever work you're doing. So, if you whatever work you're doing. So, if you ever hear that terminology, that's what ever hear that terminology, that's what ever hear that terminology, that's what it means. So, there you go. You can see it means. So, there you go. You can see it means. So, there you go. You can see that the mouse is moving around right that the mouse is moving around right that the mouse is moving around right now. It tried to click continue, and now. It tried to click continue, and now. It tried to click continue, and then it says first name is required, then it says first name is required, then it says first name is required, enter a valid email address, and enter a enter a valid email address, and enter a enter a valid email address, and enter a 10-digit phone number. 10-digit phone number. 10-digit phone number. And now you can see it just entered in And now you can see it just entered in And now you can see it just entered in some information and it was able to hit some information and it was able to hit some information and it was able to hit continue. And it's just going to keep continue. And it's just going to keep continue. And it's just going to keep going through this QA check. We're going through this QA check. We're going through this QA check. We're validating that some of these fields are validating that some of these fields are validating that some of these fields are required options and that the continue required options and that the continue required options and that the continue button won't actually let it move on button won't actually let it move on button won't actually let it move on without without without filling those in. And by the way, the filling those in. And by the way, the filling those in. And by the way, the reason you're seeing some of these UI reason you're seeing some of these UI reason you're seeing some of these UI bugs is because I asked this chat to bugs is because I asked this chat to bugs is because I asked this chat to like make there be a few UI things to like make there be a few UI things to like make there be a few UI things to fix because I wanted to show you guys fix because I wanted to show you guys fix because I wanted to show you guys the annotations. So, just ignore that.

the annotations. So, just ignore that. the annotations. So, just ignore that. Mainly, what I'm trying to show you guys Mainly, what I'm trying to show you guys Mainly, what I'm trying to show you guys now is the actual browser use QA now is the actual browser use QA now is the actual browser use QA function. So, here you can see as it's function. So, here you can see as it's function. So, here you can see as it's clicking around, as it's trying to clicking around, as it's trying to clicking around, as it's trying to navigate this UI, it already said the navigate this UI, it already said the navigate this UI, it already said the core click path mostly works, but I've core click path mostly works, but I've core click path mostly works, but I've confirmed two real data integrity confirmed two real data integrity confirmed two real data integrity problems already, which is that problems already, which is that problems already, which is that obviously invalid contact data does get obviously invalid contact data does get obviously invalid contact data does get through, and changing the country code through, and changing the country code through, and changing the country code to UK resets to US when you return to to UK resets to US when you return to to UK resets to US when you return to edit. I'm now testing keyboard edit. I'm now testing keyboard edit. I'm now testing keyboard submission and restart behavior, which submission and restart behavior, which submission and restart behavior, which often exposes bypasses the click path often exposes bypasses the click path often exposes bypasses the click path misses. So, think about it like this, no misses. So, think about it like this, no misses. So, think about it like this, no matter what you get, you're going to matter what you get, you're going to matter what you get, you're going to want to test it, but would you rather want to test it, but would you rather want to test it, but would you rather have something that has been not tested have something that has been not tested have something that has been not tested at all, or would you rather have at all, or would you rather have at all, or would you rather have something that has been tested 100 times something that has been tested 100 times something that has been tested 100 times already by an AI agent? Especially if already by an AI agent? Especially if already by an AI agent? Especially if you tell the agent to try to break it, you tell the agent to try to break it, you tell the agent to try to break it, it's going to find some things that need it's going to find some things that need it's going to find some things that need to be fixed. No matter how good you are to be fixed. No matter how good you are to be fixed. No matter how good you are at trying to predict edge cases, when at trying to predict edge cases, when at trying to predict edge cases, when you push an app into production and you push an app into production and you push an app into production and users start using it, people are weird, users start using it, people are weird, users start using it, people are weird, people are unpredictable, so they're people are unpredictable, so they're people are unpredictable, so they're going to do things. And so, this agent going to do things. And so, this agent going to do things. And so, this agent is able to hopefully simulate weird is able to hopefully simulate weird is able to hopefully simulate weird humans and just find things that you humans and just find things that you humans and just find things that you might not have thought of. You can see might not have thought of. You can see might not have thought of. You can see here, it even switched this to mobile here, it even switched this to mobile here, it even switched this to mobile view to still make sure that view to still make sure that view to still make sure that everything's working. And look at this, everything's working. And look at this, everything's working. And look at this, in mobile it found a few failures in in mobile it found a few failures in in mobile it found a few failures in responsiveness. So, that isn't something responsiveness. So, that isn't something responsiveness. So, that isn't something that I yet had tested. Okay, so this that I yet had tested. Okay, so this that I yet had tested. Okay, so this thing finished up now, and you can see thing finished up now, and you can see thing finished up now, and you can see that we have a bunch of things that that we have a bunch of things that that we have a bunch of things that passed, but a bunch of things that also passed, but a bunch of things that also passed, but a bunch of things that also failed. So, it was able to find all of failed. So, it was able to find all of failed. So, it was able to find all of these bugs because it was testing the these bugs because it was testing the these bugs because it was testing the UI, and it didn't even do it that long.

UI, and it didn't even do it that long. UI, and it didn't even do it that long. If we wanted to make this even harder, If we wanted to make this even harder, If we wanted to make this even harder, we could do a slash goal, and we could we could do a slash goal, and we could we could do a slash goal, and we could say, "Hey, don't stop until you've tried say, "Hey, don't stop until you've tried say, "Hey, don't stop until you've tried 100 different unique scenarios of, you 100 different unique scenarios of, you 100 different unique scenarios of, you know, UI edge cases, and then come back know, UI edge cases, and then come back know, UI edge cases, and then come back to me." But, it still found a lot of to me." But, it still found a lot of to me." But, it still found a lot of things that were broken, and now all things that were broken, and now all things that were broken, and now all we'd have to do is say, "Okay, cool, go we'd have to do is say, "Okay, cool, go we'd have to do is say, "Okay, cool, go implement those changes. Go fix all implement those changes. Go fix all implement those changes. Go fix all those bugs." Okay, so let me show you those bugs." Okay, so let me show you those bugs." Okay, so let me show you guys another example. This is when you guys another example. This is when you guys another example. This is when you maybe have some sort of platform where maybe have some sort of platform where maybe have some sort of platform where you want to be able to like download you want to be able to like download you want to be able to like download statements or something, but they don't statements or something, but they don't statements or something, but they don't have an API. So, you can actually have an API. So, you can actually have an API. So, you can actually interact with it with Codex's browser interact with it with Codex's browser interact with it with Codex's browser use because it basically uses vision and use because it basically uses vision and use because it basically uses vision and then AI to analyze like what it's then AI to analyze like what it's then AI to analyze like what it's looking at and where to click. And I looking at and where to click. And I looking at and where to click. And I would I just want to show you how easy would I just want to show you how easy would I just want to show you how easy it actually is to build these. All I it actually is to build these. All I it actually is to build these. All I said was, "Hey, you know, I want to said was, "Hey, you know, I want to said was, "Hey, you know, I want to build the skill, blah blah blah, what build the skill, blah blah blah, what build the skill, blah blah blah, what would be helpful?" And you could record would be helpful?" And you could record would be helpful?" And you could record a quick Loom, you could send screenshots a quick Loom, you could send screenshots a quick Loom, you could send screenshots with arrows, but you actually don't have with arrows, but you actually don't have with arrows, but you actually don't have to. You can basically just describe to. You can basically just describe to. You can basically just describe pretty clearly what you need to do. So, pretty clearly what you need to do. So, pretty clearly what you need to do. So, what happened here is it opened up what happened here is it opened up what happened here is it opened up Relay, I signed in, and it saved that Relay, I signed in, and it saved that Relay, I signed in, and it saved that session. Now, I said, "Okay, in the session. Now, I said, "Okay, in the session. Now, I said, "Okay, in the Relay dashboard, you're signed in. What Relay dashboard, you're signed in. What Relay dashboard, you're signed in. What I need you to do is go to the dashboard, I need you to do is go to the dashboard, I need you to do is go to the dashboard, click on accounts, find the statements, click on accounts, find the statements, click on accounts, find the statements, um, click on these two accounts, um, click on these two accounts, um, click on these two accounts, download them as CSVs, and then put them download them as CSVs, and then put them download them as CSVs, and then put them into this folder. And it was able to do into this folder. And it was able to do into this folder. And it was able to do that on one shot. I didn't have to give that on one shot. I didn't have to give that on one shot. I didn't have to give it any feedback, and it downloaded them it any feedback, and it downloaded them it any feedback, and it downloaded them and saved that whole flow as a skill.

and saved that whole flow as a skill. and saved that whole flow as a skill. Now, this is super helpful because now I Now, this is super helpful because now I Now, this is super helpful because now I could, at the end of the month, just set could, at the end of the month, just set could, at the end of the month, just set this up as a scheduled routine because I this up as a scheduled routine because I this up as a scheduled routine because I could set a scheduled routine here and could set a scheduled routine here and could set a scheduled routine here and say, "Hey, use this skill on the most say, "Hey, use this skill on the most say, "Hey, use this skill on the most recent, you know, month statement in recent, you know, month statement in recent, you know, month statement in Relay." And for the most part, Codex is Relay." And for the most part, Codex is Relay." And for the most part, Codex is going to save your sessions when you're going to save your sessions when you're going to save your sessions when you're logged in. However, there are some logged in. However, there are some logged in. However, there are some limitations like the fact that Relay is limitations like the fact that Relay is limitations like the fact that Relay is going to pretty much boot you out going to pretty much boot you out going to pretty much boot you out because it's, you know, it's a banking because it's, you know, it's a banking because it's, you know, it's a banking platform. It's going to be secure and platform. It's going to be secure and platform. It's going to be secure and boot you out. So, look at this here. I boot you out. So, look at this here. I boot you out. So, look at this here. I asked it to do this again, and it said, asked it to do this again, and it said, asked it to do this again, and it said, "Hey, Relay is open at the login screen, "Hey, Relay is open at the login screen, "Hey, Relay is open at the login screen, but you have to sign in again." Now, but you have to sign in again." Now, but you have to sign in again." Now, what's really interesting that you can what's really interesting that you can what's really interesting that you can do is you can actually open up your do is you can actually open up your do is you can actually open up your settings. You can have a password settings. You can have a password settings. You can have a password manager inside of Codex. And you can see manager inside of Codex. And you can see manager inside of Codex. And you can see this goes to your browser, and now you this goes to your browser, and now you this goes to your browser, and now you can go to import them so that Codex can can go to import them so that Codex can can go to import them so that Codex can actually fill that out for you. And that actually fill that out for you. And that actually fill that out for you. And that way you're not putting it into the chat way you're not putting it into the chat way you're not putting it into the chat history or anything like that. You're history or anything like that. You're history or anything like that. You're saving it more securely. So, all you saving it more securely. So, all you saving it more securely. So, all you have to do for that is create a CSV file have to do for that is create a CSV file have to do for that is create a CSV file that looks like this. I've got the name, that looks like this. I've got the name, that looks like this. I've got the name, the URL, the username, the password, and the URL, the username, the password, and the URL, the username, the password, and any notes, which in this case are empty. any notes, which in this case are empty. any notes, which in this case are empty. I imported that here, right here as a I imported that here, right here as a I imported that here, right here as a file, a CSV file, and now we have file, a CSV file, and now we have file, a CSV file, and now we have relay.com password. Go ahead and try relay.com password. Go ahead and try relay.com password. Go ahead and try this again in the password manager for this again in the password manager for this again in the password manager for the in-app Codex browser. You should be the in-app Codex browser. You should be the in-app Codex browser. You should be able to log in now. And then run the able to log in now. And then run the able to log in now. And then run the skill on June. All right, so over here skill on June. All right, so over here skill on June. All right, so over here now you can see the browser has taken now you can see the browser has taken now you can see the browser has taken control, and it is going to put in my control, and it is going to put in my control, and it is going to put in my email and my password. Now, if this asks email and my password. Now, if this asks email and my password. Now, if this asks me for a two-factor authentication code me for a two-factor authentication code me for a two-factor authentication code from my phone or something, then I'm from my phone or something, then I'm from my phone or something, then I'm obviously not going to be able to do obviously not going to be able to do obviously not going to be able to do that. I'd have to do that manually. But that. I'd have to do that manually. But that. I'd have to do that manually. But hey, if I was on a Mac and my text went hey, if I was on a Mac and my text went hey, if I was on a Mac and my text went there and I used computer use to do there and I used computer use to do there and I used computer use to do that, technically you would be able to that, technically you would be able to that, technically you would be able to automate that whole thing, but I would automate that whole thing, but I would automate that whole thing, but I would say you probably want to be careful say you probably want to be careful say you probably want to be careful about stuff like that. But as you can about stuff like that. But as you can about stuff like that. But as you can see, it was able to pull the passwords see, it was able to pull the passwords see, it was able to pull the passwords from my password manager, paste those

from my password manager, paste those from my password manager, paste those in, and now it should be able to log in in, and now it should be able to log in in, and now it should be able to log in to Relay for me. You can see here that to Relay for me. You can see here that to Relay for me. You can see here that the mouse has moved over to accounts. the mouse has moved over to accounts. the mouse has moved over to accounts. It's then going over to statements, and It's then going over to statements, and It's then going over to statements, and it's going to be able to download these it's going to be able to download these it's going to be able to download these two statements for us. So, you can see two statements for us. So, you can see two statements for us. So, you can see it's pretty cool that it was able to it's pretty cool that it was able to it's pretty cool that it was able to figure all this out. Remember, I've only figure all this out. Remember, I've only figure all this out. Remember, I've only ran this skill once and all I did was ran this skill once and all I did was ran this skill once and all I did was instruct it with natural language to do instruct it with natural language to do instruct it with natural language to do this. Now, realistically, is that the this. Now, realistically, is that the this. Now, realistically, is that the way you should do it, especially with way you should do it, especially with way you should do it, especially with something like a bank account? No. What something like a bank account? No. What something like a bank account? No. What you should do is you should do is you should do is have it do the skill, you sit here and have it do the skill, you sit here and have it do the skill, you sit here and watch it, and have it do that like watch it, and have it do that like watch it, and have it do that like at least 10 times where you're very at least 10 times where you're very at least 10 times where you're very closely watching it to make sure nothing closely watching it to make sure nothing closely watching it to make sure nothing goes wrong, and you're making sure the goes wrong, and you're making sure the goes wrong, and you're making sure the script in the skill is super strict. script in the skill is super strict. script in the skill is super strict. Because at the end of the day, it's Because at the end of the day, it's Because at the end of the day, it's using vision, it's using AI, and that's using vision, it's using AI, and that's using vision, it's using AI, and that's how it's deciding what to click and what how it's deciding what to click and what how it's deciding what to click and what to do. So, really the way that I think to do. So, really the way that I think to do. So, really the way that I think about it is when you want to automate about it is when you want to automate about it is when you want to automate something, your first call should always something, your first call should always something, your first call should always be to go for an API. Like, that's what be to go for an API. Like, that's what be to go for an API. Like, that's what you want to do. It's the fastest, it's you want to do. It's the fastest, it's you want to do. It's the fastest, it's usually the cheapest, it's usually just usually the cheapest, it's usually just usually the cheapest, it's usually just the most consistent. Now, if there's no the most consistent. Now, if there's no the most consistent. Now, if there's no API, that's where you would maybe say, API, that's where you would maybe say, API, that's where you would maybe say, "Okay, cool. Well, now let me see if I "Okay, cool. Well, now let me see if I "Okay, cool. Well, now let me see if I could use like a deterministic, you could use like a deterministic, you could use like a deterministic, you know, like a macro script, right?" And know, like a macro script, right?" And know, like a macro script, right?" And that's where you'd basically be able to that's where you'd basically be able to that's where you'd basically be able to have, yes, you know, it'd be more of a have, yes, you know, it'd be more of a have, yes, you know, it'd be more of a browser use because you have a mouse browser use because you have a mouse browser use because you have a mouse that's clicking around, but it's not that's clicking around, but it's not that's clicking around, but it's not like your mouse needs reasoning. Your like your mouse needs reasoning. Your like your mouse needs reasoning. Your mouse doesn't need to look at the mouse doesn't need to look at the mouse doesn't need to look at the screen, figure out where to click, and screen, figure out where to click, and screen, figure out where to click, and based on the next UI that pops up, where based on the next UI that pops up, where based on the next UI that pops up, where do I click again? This is basically more do I click again? This is basically more do I click again? This is basically more like, "Okay, like, "Okay, like, "Okay, I have to click on this pixel, then this I have to click on this pixel, then this I have to click on this pixel, then this pixel, then this pixel every single pixel, then this pixel every single pixel, then this pixel every single time." That's something that you could time." That's something that you could time." That's something that you could do for much cheaper and much safer by do for much cheaper and much safer by do for much cheaper and much safer by just programming a macro. And that's not just programming a macro. And that's not just programming a macro. And that's not that hard either. You just ask Claude or that hard either. You just ask Claude or that hard either. You just ask Claude or Codex, "Hey, help me figure out how to Codex, "Hey, help me figure out how to Codex, "Hey, help me figure out how to make like a deterministic macro script

make like a deterministic macro script make like a deterministic macro script to just click on these pixels in that to just click on these pixels in that to just click on these pixels in that order every single time." But, if you order every single time." But, if you order every single time." But, if you can't do that every single time because can't do that every single time because can't do that every single time because there is an element of vision or there is an element of vision or there is an element of vision or reasoning, then you need to come in here reasoning, then you need to come in here reasoning, then you need to come in here and you need to do something like some and you need to do something like some and you need to do something like some browser use. And luckily, Codex has your browser use. And luckily, Codex has your browser use. And luckily, Codex has your back. I've tested a lot of different back. I've tested a lot of different back. I've tested a lot of different apps and different CLIs and different apps and different CLIs and different apps and different CLIs and different things for browser use, and so far Codex things for browser use, and so far Codex things for browser use, and so far Codex is just really solid. So, as you can see is just really solid. So, as you can see is just really solid. So, as you can see now, in my downloads, this is the now, in my downloads, this is the now, in my downloads, this is the statements that it just downloaded as a statements that it just downloaded as a statements that it just downloaded as a zip file, and it basically took these zip file, and it basically took these zip file, and it basically took these and it put it into my Hercule project. and it put it into my Hercule project. and it put it into my Hercule project. If I go in here and I scroll down to If I go in here and I scroll down to If I go in here and I scroll down to statements, and I go to probably June, statements, and I go to probably June, statements, and I go to probably June, yes, June, you can see right here it put yes, June, you can see right here it put yes, June, you can see right here it put those in here in the correct spot. Okay, those in here in the correct spot. Okay, those in here in the correct spot. Okay, so that was an example where we needed so that was an example where we needed so that was an example where we needed to save a password somewhere, right? But to save a password somewhere, right? But to save a password somewhere, right? But I've done this with things like school, I've done this with things like school, I've done this with things like school, I've done this with things like X, I've I've done this with things like X, I've I've done this with things like X, I've even done this with things like even done this with things like even done this with things like Instagram that don't make you constantly Instagram that don't make you constantly Instagram that don't make you constantly resign in because it saves that session. resign in because it saves that session. resign in because it saves that session. So let me show you another example. I'm So let me show you another example. I'm So let me show you another example. I'm going to go over here to YouTube and I'm going to go over here to YouTube and I'm going to go over here to YouTube and I'm going to grab the URL from the video going to grab the URL from the video going to grab the URL from the video that I uploaded earlier today. I'm going that I uploaded earlier today. I'm going that I uploaded earlier today. I'm going to go back into Codex, paste in that URL to go back into Codex, paste in that URL to go back into Codex, paste in that URL and say, and say, and say, "I need you to turn this YouTube video "I need you to turn this YouTube video "I need you to turn this YouTube video into an X article for me and then use into an X article for me and then use into an X article for me and then use browser use to go ahead and um format it browser use to go ahead and um format it browser use to go ahead and um format it and put it into an X article as a draft and put it into an X article as a draft and put it into an X article as a draft and then I will go ahead and review it."

and then I will go ahead and review it." and then I will go ahead and review it." So I know some of you guys are probably So I know some of you guys are probably So I know some of you guys are probably thinking, "Why don't you just use X's thinking, "Why don't you just use X's thinking, "Why don't you just use X's API for that?" You can, but it's a API for that?" You can, but it's a API for that?" You can, but it's a little bit weird with the formatting. little bit weird with the formatting. little bit weird with the formatting. It's also weird with sometimes adding It's also weird with sometimes adding It's also weird with sometimes adding things like media or thumbnails for some things like media or thumbnails for some things like media or thumbnails for some reason, at least with my testing that I reason, at least with my testing that I reason, at least with my testing that I used to do, and it's also it charges used to do, and it's also it charges used to do, and it's also it charges you, right? Because you have to pay X you, right? Because you have to pay X you, right? Because you have to pay X per usage in order to do something like per usage in order to do something like per usage in order to do something like that. And so because this is just part that. And so because this is just part that. And so because this is just part of my Codex subscription, I can just run of my Codex subscription, I can just run of my Codex subscription, I can just run this skill and it will go ahead and this skill and it will go ahead and this skill and it will go ahead and format everything for me and take care format everything for me and take care format everything for me and take care of it. I even have the skill worked out of it. I even have the skill worked out of it. I even have the skill worked out where it can go ahead and open up my where it can go ahead and open up my where it can go ahead and open up my YouTube videos and it can take YouTube videos and it can take YouTube videos and it can take screenshots of specific moments and put screenshots of specific moments and put screenshots of specific moments and put those into the article, too, where it those into the article, too, where it those into the article, too, where it makes sense. So obviously this is a bit makes sense. So obviously this is a bit makes sense. So obviously this is a bit of a loaded process because it has to do of a loaded process because it has to do of a loaded process because it has to do a few steps before it actually has the a few steps before it actually has the a few steps before it actually has the article ready to put into X. So while article ready to put into X. So while article ready to put into X. So while that's happening, let's just open up a that's happening, let's just open up a that's happening, let's just open up a new chat and let's see if our X session new chat and let's see if our X session new chat and let's see if our X session is there. is there. is there. "Can you open up a browser? I want to "Can you open up a browser? I want to "Can you open up a browser? I want to see it right here in the app and just go see it right here in the app and just go see it right here in the app and just go to X and scroll around a little bit and to X and scroll around a little bit and to X and scroll around a little bit and show me if there's anything new that has show me if there's anything new that has show me if there's anything new that has just come out um like in the AI space. just come out um like in the AI space. just come out um like in the AI space. Just scroll on my X feed." And so Just scroll on my X feed." And so Just scroll on my X feed." And so because this was a brand new session, we because this was a brand new session, we because this was a brand new session, we can actually see if X is already signed can actually see if X is already signed can actually see if X is already signed in and if it's able to interact with in and if it's able to interact with in and if it's able to interact with things.

Cool. So it just opened up X. Let me get Cool. So it just opened up X. Let me get my mouse out of here. You can see my mouse out of here. You can see my mouse out of here. You can see clearly that this is already signed in clearly that this is already signed in clearly that this is already signed in as me and my feed is visible and now it as me and my feed is visible and now it as me and my feed is visible and now it is going ahead and it's starting to is going ahead and it's starting to is going ahead and it's starting to scroll on the X page. So just start to scroll on the X page. So just start to scroll on the X page. So just start to think about already, how could you think about already, how could you think about already, how could you create some sort of skills out of this create some sort of skills out of this create some sort of skills out of this and then schedule these as tasks? So, and then schedule these as tasks? So, and then schedule these as tasks? So, maybe every morning if you wanted it to maybe every morning if you wanted it to maybe every morning if you wanted it to scroll through Instagram and things like scroll through Instagram and things like scroll through Instagram and things like that, or scroll through your own that, or scroll through your own that, or scroll through your own profile, or mark things as read or profile, or mark things as read or profile, or mark things as read or unread, you could totally go ahead and unread, you could totally go ahead and unread, you could totally go ahead and do that, no problem, because you can set do that, no problem, because you can set do that, no problem, because you can set up the schedule tasks right in here and up the schedule tasks right in here and up the schedule tasks right in here and use browser use skills that you've use browser use skills that you've use browser use skills that you've already set up. So, you can see the two already set up. So, you can see the two already set up. So, you can see the two things that it already noticed was Grok things that it already noticed was Grok things that it already noticed was Grok Bot and Grok 4.6. So, this is an Bot and Grok 4.6. So, this is an Bot and Grok 4.6. So, this is an interesting case though, because there interesting case though, because there interesting case though, because there is an API, but using the browser use is is an API, but using the browser use is is an API, but using the browser use is actually cheaper. So, that's why in this actually cheaper. So, that's why in this actually cheaper. So, that's why in this case we decided to do it and test it case we decided to do it and test it case we decided to do it and test it out. Now, what about computer use that out. Now, what about computer use that out. Now, what about computer use that you guys have also probably heard? These you guys have also probably heard? These you guys have also probably heard? These are basically the same thing. It's still are basically the same thing. It's still are basically the same thing. It's still going to use vision. It's still going to going to use vision. It's still going to going to use vision. It's still going to use AI, but the difference here is that use AI, but the difference here is that use AI, but the difference here is that the browser is basically things that are the browser is basically things that are the browser is basically things that are on the internet, or things that you on the internet, or things that you on the internet, or things that you would type into a browser like Chrome, would type into a browser like Chrome, would type into a browser like Chrome, but the computer use are things that but the computer use are things that but the computer use are things that might be on your actual computer. So, might be on your actual computer. So, might be on your actual computer. So, changing your computer settings, opening changing your computer settings, opening changing your computer settings, opening up desktop apps of things. So, let's go up desktop apps of things. So, let's go up desktop apps of things. So, let's go back into Codex. While we're waiting for back into Codex. While we're waiting for back into Codex. While we're waiting for this X article to finish up, let's see this X article to finish up, let's see this X article to finish up, let's see how this is going. It is still breaking how this is going. It is still breaking how this is going. It is still breaking down and turning it into an article.

down and turning it into an article. down and turning it into an article. Let's see if we can do some computer Let's see if we can do some computer Let's see if we can do some computer use. So, one thing you have to do though use. So, one thing you have to do though use. So, one thing you have to do though is you have to go to plugins, and you'll is you have to go to plugins, and you'll is you have to go to plugins, and you'll have to actually install computer use, have to actually install computer use, have to actually install computer use, which is just as simple as typing in which is just as simple as typing in which is just as simple as typing in computer use and hitting install, like computer use and hitting install, like computer use and hitting install, like literally 2 seconds. And then, literally 2 seconds. And then, literally 2 seconds. And then, Hey Codex, I need you to use computer Hey Codex, I need you to use computer Hey Codex, I need you to use computer use to open up my desktop app for Glydo, use to open up my desktop app for Glydo, use to open up my desktop app for Glydo, and I just want you to go to the and I just want you to go to the and I just want you to go to the settings and turn on the ability for it settings and turn on the ability for it settings and turn on the ability for it to allow and use like Bluetooth devices. to allow and use like Bluetooth devices. to allow and use like Bluetooth devices. So, just go ahead and get that set up So, just go ahead and get that set up So, just go ahead and get that set up for me. And so, this is a little bit for me. And so, this is a little bit for me. And so, this is a little bit different, right? Because it's not going different, right? Because it's not going different, right? Because it's not going to open up your in-app browser. It's to open up your in-app browser. It's to open up your in-app browser. It's going to actually kind of show your going to actually kind of show your going to actually kind of show your screen being taken over. It said, "I'll screen being taken over. It said, "I'll screen being taken over. It said, "I'll stop if Windows asks for an admin stop if Windows asks for an admin stop if Windows asks for an admin password or presents a security password or presents a security password or presents a security sensitive permission that it can't sensitive permission that it can't sensitive permission that it can't safely interpret." It shouldn't run into safely interpret." It shouldn't run into safely interpret." It shouldn't run into any of that, but it's good that it sort any of that, but it's good that it sort any of that, but it's good that it sort of has that guardrail baked in. of has that guardrail baked in. of has that guardrail baked in. Interesting. Okay, so it said, Interesting. Okay, so it said, Interesting. Okay, so it said, "Bluetooth access is a privacy "Bluetooth access is a privacy "Bluetooth access is a privacy permission, so the computer use won't permission, so the computer use won't permission, so the computer use won't let me actually do that." But, what it let me actually do that." But, what it let me actually do that." But, what it said it's going to do is open up Glydo. said it's going to do is open up Glydo. said it's going to do is open up Glydo. As you can see, I didn't open that up. As you can see, I didn't open that up. As you can see, I didn't open that up. It opened up Glydo for me. And it It opened up Glydo for me. And it It opened up Glydo for me. And it doesn't look like on my recording you doesn't look like on my recording you doesn't look like on my recording you guys can actually see this right now, guys can actually see this right now, guys can actually see this right now, but my screen kind of has like a big but my screen kind of has like a big but my screen kind of has like a big blue hue around the edges. So, you will blue hue around the edges. So, you will blue hue around the edges. So, you will clearly know if Codex is using your clearly know if Codex is using your clearly know if Codex is using your computer.

And there you go. You can see that it And there you go. You can see that it actually turned on the include Bluetooth actually turned on the include Bluetooth actually turned on the include Bluetooth devices button. Now, I think it got devices button. Now, I think it got devices button. Now, I think it got confused because I think at first it confused because I think at first it confused because I think at first it thought that I was messing with my thought that I was messing with my thought that I was messing with my actual computer settings rather than actual computer settings rather than actual computer settings rather than like an in-app setting. So, it thought like an in-app setting. So, it thought like an in-app setting. So, it thought that that was a security thing. But, it that that was a security thing. But, it that that was a security thing. But, it looks like it figured that out on the looks like it figured that out on the looks like it figured that out on the way. And I think the computer use thing way. And I think the computer use thing way. And I think the computer use thing is pretty interesting because you can is pretty interesting because you can is pretty interesting because you can remote into your Codex from your phone. remote into your Codex from your phone. remote into your Codex from your phone. So, I can control all of these sessions So, I can control all of these sessions So, I can control all of these sessions on my phone. And what I could do is on on my phone. And what I could do is on on my phone. And what I could do is on my phone I could say, "Hey, computer my phone I could say, "Hey, computer my phone I could say, "Hey, computer use, go ahead and change my settings or use, go ahead and change my settings or use, go ahead and change my settings or go ahead and do something on a desktop go ahead and do something on a desktop go ahead and do something on a desktop app that's on my PC that I'm actually app that's on my PC that I'm actually app that's on my PC that I'm actually not sitting in front of." And then you not sitting in front of." And then you not sitting in front of." And then you could control your computer from your could control your computer from your could control your computer from your phone. So, anyways, we're back in the phone. So, anyways, we're back in the phone. So, anyways, we're back in the session where it's creating that X session where it's creating that X session where it's creating that X article. You can see that it is actually article. You can see that it is actually article. You can see that it is actually creating some thumbnails for the actual creating some thumbnails for the actual creating some thumbnails for the actual article. So, hopefully we're getting article. So, hopefully we're getting article. So, hopefully we're getting close to the point where it's going to close to the point where it's going to close to the point where it's going to actually open up X and start to put actually open up X and start to put actually open up X and start to put stuff in there. But, I'll check with you stuff in there. But, I'll check with you stuff in there. But, I'll check with you guys when we get there. Okay, so it just guys when we get there. Okay, so it just guys when we get there. Okay, so it just decided to open up X. You can see that decided to open up X. You can see that decided to open up X. You can see that it's going to the drafts in my signed in it's going to the drafts in my signed in it's going to the drafts in my signed in X and then it's going to I'll go ahead X and then it's going to I'll go ahead X and then it's going to I'll go ahead and format this new article and then and format this new article and then and format this new article and then we'll take a look. It's clicking on the we'll take a look. It's clicking on the we'll take a look. It's clicking on the plus button. Man, I think it even just plus button. Man, I think it even just plus button. Man, I think it even just like resized the page a little bit. It like resized the page a little bit. It like resized the page a little bit. It was getting a little picky. In goes the was getting a little picky. In goes the was getting a little picky. In goes the title. And then it just pasted in the title. And then it just pasted in the title. And then it just pasted in the entire content of the article. Now, it's entire content of the article. Now, it's entire content of the article. Now, it's uploading this thumbnail which I don't uploading this thumbnail which I don't uploading this thumbnail which I don't think looks very good. That part of the think looks very good. That part of the think looks very good. That part of the skill has not been refined at all. But, skill has not been refined at all. But, skill has not been refined at all. But, it's still cool that it was able to make it's still cool that it was able to make it's still cool that it was able to make that thumbnail and then go ahead and put that thumbnail and then go ahead and put that thumbnail and then go ahead and put it in there. So, I literally just have it in there. So, I literally just have it in there. So, I literally just have to make sure that it looks okay and I to make sure that it looks okay and I to make sure that it looks okay and I like it and I can publish it. Now, I like it and I can publish it. Now, I like it and I can publish it. Now, I know what a lot of you guys are probably know what a lot of you guys are probably know what a lot of you guys are probably thinking when it comes to this browser thinking when it comes to this browser thinking when it comes to this browser use stuff. It's like, use stuff. It's like, use stuff. It's like, "What's the point, Nate? Like, where's "What's the point, Nate? Like, where's "What's the point, Nate? Like, where's the value?" And honestly, I understand the value?" And honestly, I understand the value?" And honestly, I understand where you're coming from. And that's why where you're coming from. And that's why where you're coming from. And that's why I wanted to show you guys this piece I wanted to show you guys this piece I wanted to show you guys this piece where it's like where it's like where it's like pretty much API will handle 95% of your

pretty much API will handle 95% of your pretty much API will handle 95% of your automation things that you need. And automation things that you need. And automation things that you need. And then a lot of the browser use then a lot of the browser use then a lot of the browser use opportunities might just be a script. opportunities might just be a script. opportunities might just be a script. But, then when you need it, if you have But, then when you need it, if you have But, then when you need it, if you have this in your back pocket, it's good. And this in your back pocket, it's good. And this in your back pocket, it's good. And you also might think, "Okay, cool. But, you also might think, "Okay, cool. But, you also might think, "Okay, cool. But, like, how much time does this really like, how much time does this really like, how much time does this really save?" This probably saves me like maybe save?" This probably saves me like maybe save?" This probably saves me like maybe 5 to 10 minutes. Like, realistically. 5 to 10 minutes. Like, realistically. 5 to 10 minutes. Like, realistically. But, what's cool about it is that I can But, what's cool about it is that I can But, what's cool about it is that I can basically have this pipeline now where I basically have this pipeline now where I basically have this pipeline now where I have a bunch of these browser use have a bunch of these browser use have a bunch of these browser use skills, and so when I need to do skills, and so when I need to do skills, and so when I need to do something, I just open up Codex, I shoot something, I just open up Codex, I shoot something, I just open up Codex, I shoot off that skill, and I can go back to the off that skill, and I can go back to the off that skill, and I can go back to the other task that I was working on. It other task that I was working on. It other task that I was working on. It kind of just like helps you do more kind of just like helps you do more kind of just like helps you do more without context switching as much. And without context switching as much. And without context switching as much. And as you start to stack more and more of as you start to stack more and more of as you start to stack more and more of these pipelines and combine them these pipelines and combine them these pipelines and combine them together, you can get some really cool together, you can get some really cool together, you can get some really cool things to happen when you start to chain things to happen when you start to chain things to happen when you start to chain together these skills. And look, this together these skills. And look, this together these skills. And look, this one actually did it. It basically did one actually did it. It basically did one actually did it. It basically did the thing where I said it opened up the the thing where I said it opened up the the thing where I said it opened up the YouTube video, it took screenshots of YouTube video, it took screenshots of YouTube video, it took screenshots of it, and now it's going ahead and it's it, and now it's going ahead and it's it, and now it's going ahead and it's planting some screenshots from my video planting some screenshots from my video planting some screenshots from my video in the article. So, if that doesn't in the article. So, if that doesn't in the article. So, if that doesn't prove the capabilities of this thing prove the capabilities of this thing prove the capabilities of this thing being intelligent, take screenshots, being intelligent, take screenshots, being intelligent, take screenshots, look at the page, know where to click, look at the page, know where to click, look at the page, know where to click, know what to do, then I don't know what know what to do, then I don't know what know what to do, then I don't know what else will. Besides the fact that I've else will. Besides the fact that I've else will. Besides the fact that I've had this thing play chess, I've had it had this thing play chess, I've had it had this thing play chess, I've had it play games, I've had it set a world play games, I've had it set a world play games, I've had it set a world record on Tetris, it can do a lot of record on Tetris, it can do a lot of record on Tetris, it can do a lot of cool things.

cool things. cool things. Look at this. You can see that it even Look at this. You can see that it even Look at this. You can see that it even took the image and drug it all the way took the image and drug it all the way took the image and drug it all the way down to where it actually fits in the down to where it actually fits in the down to where it actually fits in the article. I haven't actually seen it do article. I haven't actually seen it do article. I haven't actually seen it do that before live. That was pretty cool. that before live. That was pretty cool. that before live. That was pretty cool. And this thing is just still going at And this thing is just still going at And this thing is just still going at it. But that is going to do it for it. But that is going to do it for it. But that is going to do it for today's video. Hope you guys enjoyed it. today's video. Hope you guys enjoyed it. today's video. Hope you guys enjoyed it. Hope you learned something new, and if Hope you learned something new, and if Hope you learned something new, and if you did, please give it a like. It helps you did, please give it a like. It helps you did, please give it a like. It helps me out a ton. As always, I appreciate me out a ton. As always, I appreciate me out a ton. As always, I appreciate you guys making it to the end of the you guys making it to the end of the you guys making it to the end of the video, and I'll see you on the next one. video, and I'll see you on the next one. video, and I'll see you on the next one. Thanks, everyone.