WEBVTT 00:00:00.000 --> 00:00:02.407 So, Codex is an absolutely incredible super app. 00:00:02.407 --> 00:00:05.851 I've been using it a lot more lately, and I'm not saying that I'm ditching Claude Code. 00:00:05.851 --> 00:00:09.378 I still use them both regularly because they're both good at different things. 00:00:09.378 --> 00:00:18.950 So, today's video, I'm going to break down every single important thing that you need to know about Codex to be able to, you know, open up the app for the first time and then actually have finished automations and websites and whatever you want to do 00:00:18.960 --> 00:00:21.070 in Codex done by the end of this video. 00:00:21.080 --> 00:00:27.271 So, whether you've never opened up a tool like this before or if you're already kind of used to using Claude Code, I'm going to break down everything as simple as I can. 00:00:27.271 --> 00:00:36.513 So, first of all, if you fit in this bucket of someone that uses ChatGPT just on the web or uses Claude, you are going to get this really quick because what we're looking at right here is ChatGPT. 00:00:36.513 --> 00:00:44.232 We have the ability to make new chats, we can search through chats, we can have different projects, we can have all of our different chats over here, and then we talk to chat right here. 00:00:44.232 --> 00:00:49.695 And if I open up the Codex app, which is what we're going to be using today for the entire video, it looks pretty much the exact same. 00:00:49.695 --> 00:00:54.480 We have projects on the left, we have chats on the left, and then we can talk to ChatGPT right here. 00:00:54.480 --> 00:00:59.670 We use this toggle to change the model whether we want to use GPT 5.5, 5.4, or other models. 00:00:59.670 --> 00:01:02.910 We can change the speed, and then we can also change the intelligence. 00:01:02.910 --> 00:01:04.911 So, low, medium, high, or extra high. 00:01:04.911 --> 00:01:08.054 And I'll get into this stuff a little bit later in more depth. 00:01:08.054 --> 00:01:15.877 And this is also very similar to the Claude Code desktop app where we have the ability to chat with Claude right here, and then on the left-hand side we can see our chats and our projects. 00:01:15.877 --> 00:01:17.187 So, that is the interface. 00:01:17.187 --> 00:01:18.310 Don't get overwhelmed. 00:01:18.320 --> 00:01:26.710 So, I'm going to get you guys all familiar with the interface and go over all the settings that you need to know, and then I'm going to show you a full project from beginning to end building skills, connecting to things, building 00:01:26.720 --> 00:01:29.859 automations, and then deploying on some sort of website. 00:01:29.859 --> 00:01:30.571 So, buckle up. 00:01:30.571 --> 00:01:32.440 All right, so what actually is Codex? 00:01:32.440 --> 00:01:35.270 Codex is basically a massive super app. 00:01:35.270 --> 00:01:43.602 We can use ChatGPT same way you talk to it on the web, but now we work in projects, and Codex can create Excel sheets, read Excel sheets, look through all your local files. 00:01:43.602 --> 00:01:49.369 It can do basically anything on your computer including using the mouse and keyboard and clicking around and automating a browser. 00:01:49.369 --> 00:01:51.632 It also lets us build these reusable skills. 00:01:51.632 --> 00:01:59.514 We can build websites, we can build apps, we can build video games, and then we can automate and push all that stuff so that it actually runs while we're sleeping every night. 00:01:59.514 --> 00:02:03.035 So, the main difference here between web chat is that you're basically just talking. 00:02:03.035 --> 00:02:06.395 And you have these connectors in chat GPT now, so you can get a little bit more functionality. 00:02:06.395 --> 00:02:10.070 You can give that AI brain a bit more of like hands. 00:02:10.080 --> 00:02:13.030 But, in Codex, it can do everything. 00:02:13.040 --> 00:02:18.438 It's one of those things where Codex can do everything that chat can do, but chat cannot do nearly as much as what Codex can do. 00:02:18.438 --> 00:02:21.022 So, you might as well just switch over to something like Codex. 00:02:21.022 --> 00:02:25.565 And if you are curious about the Claude code versus Codex difference, they're different harnesses, right? 00:02:25.565 --> 00:02:28.958 So, they fundamentally work a little bit different, but very similarly. 00:02:28.958 --> 00:02:30.588 They also use different models. 00:02:30.588 --> 00:02:37.110 So, Claude code natively under the hood uses Opus and Sonnet and Haiku, and Codex under the hood uses the different chat GPT models. 00:02:37.120 --> 00:02:42.666 Now, I did do a full breakdown where I actually tested Opus 4.7 against GPT 5.5, and I got some really interesting results. 00:02:42.666 --> 00:02:45.575 So, if you guys want to check out this video next, I'll tag that right up here. 00:02:45.575 --> 00:02:47.901 I definitely think it's worth just at least skimming through. 00:02:47.901 --> 00:02:53.009 Because ultimately, these models have very different strengths is what I've noticed after playing with them non-stop. 00:02:53.009 --> 00:02:59.747 I really like Claude for being sort of like exploratory and brainstorming and helping me get creative and think through things and plan. 00:02:59.747 --> 00:03:02.430 But then, I really like Codex for being pragmatic. 00:03:02.440 --> 00:03:06.944 And it feels like it does better at following my plan if the plan grows longer and longer. 00:03:06.944 --> 00:03:14.098 And it's really good at executing, and it's really good at finding issues and troubleshooting things that sometimes Claude, for some reason, can't handle. 00:03:14.098 --> 00:03:16.850 So, I'm not in here saying that I love Codex more than Claude code. 00:03:16.850 --> 00:03:20.589 I'm saying that I'm using them both, and I'm learning more about both every day. 00:03:20.589 --> 00:03:25.494 And one other thing I really like about Codex is you can see my little pet down here, which I'll tell you guys how you get this later. 00:03:25.494 --> 00:03:30.526 But this pet, while you're working, it stays in the bottom of your screen, and it tells you what it's working on. 00:03:30.526 --> 00:03:34.430 So, it's really nice to be able to multitask and see what's happening inside of Codex. 00:03:34.440 --> 00:03:35.770 And the pet's kind of funny. 00:03:35.770 --> 00:03:37.117 And it's more than just having chats. 00:03:37.117 --> 00:03:39.959 It's the ability to have everything organized on your workspace. 00:03:39.959 --> 00:03:49.512 So, if you guys watch my recent video about Claude code operating system, or you've seen my executive assistant video, this is my heart two project, which is basically where I live inside of Claude code. 00:03:49.512 --> 00:03:52.029 And all of this is is a bunch of folders and files. 00:03:52.029 --> 00:03:53.388 I've got a bunch of files here. 00:03:53.388 --> 00:03:54.727 I've got a bunch of different folders. 00:03:54.727 --> 00:03:55.401 I've got settings. 00:03:55.401 --> 00:03:56.114 I've got skills. 00:03:56.114 --> 00:03:56.849 I've got agents. 00:03:56.849 --> 00:03:57.798 I've got projects. 00:03:57.798 --> 00:03:59.898 I've got all these things that I'm working on. 00:03:59.898 --> 00:04:02.430 And all this is is a bunch of local files. 00:04:02.440 --> 00:04:06.942 Which means I can have Codex work inside of this directory and do everything as well. 00:04:06.942 --> 00:04:11.729 All that we're doing when we're using these different models is we're organizing things into a structure. 00:04:11.729 --> 00:04:13.803 A structure that different agent harnesses can understand. 00:04:13.803 --> 00:04:20.590 And whether you want to use Codex or Claude Code or Cursor or, you know, Open Claw, whatever it is, they can all work out of that directory. 00:04:20.600 --> 00:04:25.170 As long as you have some sort of instructions and guidelines over what actually lives where. 00:04:25.170 --> 00:04:30.732 Okay, so basically what I'm going to be building with you guys today is a bit of a YouTube comment intelligence system. 00:04:30.732 --> 00:04:34.179 So we want to be able to pull in YouTube comments from my channel. 00:04:34.179 --> 00:04:35.986 We want to be able to have those be analyzed. 00:04:35.986 --> 00:04:37.241 We want a workbook in Excel. 00:04:37.241 --> 00:04:39.184 We want like some data visualization. 00:04:39.184 --> 00:04:44.306 And we want a dashboard that lives somewhere on the web so I could go check it on my phone if I'm out on a walk. 00:04:44.306 --> 00:04:46.701 And I'm going to show you how we ship and deploy all of that. 00:04:46.701 --> 00:04:50.356 So basically from zero to a working project is what I'm going to show you guys today. 00:04:50.356 --> 00:04:53.923 So, let me go ahead and open up the Codex app and show you guys how this works. 00:04:53.923 --> 00:04:57.550 Now real quick, what you have to do is have some sort of ChatGPT plan. 00:04:57.560 --> 00:05:00.322 The good news is if you're on free, you can still try out Codex. 00:05:00.322 --> 00:05:01.907 You have limited Codex access. 00:05:01.907 --> 00:05:05.420 But I would recommend just hopping on the $20 a month plan to get started. 00:05:05.420 --> 00:05:09.670 And if you're running into your limits pretty quickly, then maybe you want to upgrade to Pro. 00:05:09.680 --> 00:05:16.364 Now what else is really nice about ChatGPT subscription is you can plug it into Open Claw or Hermes Agent, which is really really nice. 00:05:16.364 --> 00:05:21.197 Because obviously it's so much more expensive to pay per token rather than being on some sort of subscription. 00:05:21.197 --> 00:05:25.663 And then you're just going to go ahead and go to Codex and then just download the app for your operating system. 00:05:25.663 --> 00:05:27.908 That's the way that we're going to be using it today. 00:05:27.908 --> 00:05:34.635 Ultimately, you will be getting more full functionality if you're using Codex in VS Code extension or in the terminal. 00:05:34.635 --> 00:05:39.110 But for the sake of the video, using the app is going to get you super far either way. 00:05:39.120 --> 00:05:42.433 There's just a few little things you want to keep in mind, which is why I'm making this YouTube video. 00:05:42.433 --> 00:05:44.707 All right, so let's go ahead and get started. 00:05:44.707 --> 00:05:51.028 So, on the left-hand side you can see I've got one project open, and this project is actually how I built the slide deck that you were looking at earlier. 00:05:51.028 --> 00:05:59.449 So, this slide deck I built right here in this project, and you can see because I'm in the app, Codex lets us basically navigate this right here in this little localhost browser. 00:05:59.449 --> 00:06:08.030 And this is also where if I said, "Hey, can you use browser use and test out this slide deck to make sure everything looks good and make sure it functionally like clicks and moves?" 00:06:08.040 --> 00:06:13.849 Then it would bring up a mouse over here, and we would see it move around, and we would see it click, which I'll show you guys later in the video. 00:06:13.849 --> 00:06:23.791 But anyways, what we're going to do is we're going to start a new project because over here you can see we have a bunch of random chats, which can still do things like building games and building automations and simulators. 00:06:23.791 --> 00:06:32.393 But what we want to do is we want to work inside of an actual project because these chats, any deliverable that we create doesn't really have a home, you know, it just lives somewhere random in our documents. 00:06:32.393 --> 00:06:43.310 But when we're working in a certain project, I can actually grab the local working directory, so I copy that, and if I go into my file explorer and paste that in, now I'm inside of the actual project that we're working on in 00:06:43.320 --> 00:06:43.638 Codex. 00:06:43.638 --> 00:06:47.053 So, now I can see different assets that live in this project, all these images. 00:06:47.053 --> 00:06:53.315 I can see different guides, and I can have a little bit more organization to this ongoing project in my business. 00:06:53.315 --> 00:06:55.315 All right, so we're going to start a new project. 00:06:55.315 --> 00:07:03.249 I'm going to click on new chat in the top, and then right here you can see I'm inside of the Codex 95% project, but we're going to go ahead and add a new project. 00:07:03.249 --> 00:07:08.752 So, that's going to open up a little um file explorer over here, and then you choose where you want this to live. 00:07:08.752 --> 00:07:20.747 So, for this example, I'm going to go to my desktop, I'm going to go into a folder called Codex YouTube, and I'm going to create a new folder inside of this folder just called um YouTube analytics demo. 00:07:20.747 --> 00:07:27.697 And we're going to go ahead and open up this folder and select that, and now you can see it's a new project over here on this left-hand side that we're going to be working in. 00:07:27.697 --> 00:07:29.744 Now, right here you can see I have something called full access. 00:07:29.744 --> 00:07:32.950 By default, you won't see this, it'll just be on default permissions. 00:07:32.960 --> 00:07:36.814 So, I'm going to kick off some sort of chat here, and then I'll show you how we actually get that set up. 00:07:36.814 --> 00:07:45.058 Real quick, guys, I know we're going over a ton of information in this video, so what I did is I threw all of this into a complete PDF resource guide that you can use and reference later. 00:07:45.058 --> 00:07:47.423 All you have to do to get that is join my free school community. 00:07:47.423 --> 00:07:48.897 The link for that is down in the description. 00:07:48.897 --> 00:08:00.230 And once you get in here, go to the classroom and click on all YouTube resources, and you'll be able to find all of my repos, all of my skills, resource guides, everything that I've ever dropped inside of here is completely free, and anything I've shown 00:08:00.240 --> 00:08:01.910 on YouTube is usually dropped in here. 00:08:01.920 --> 00:08:04.698 So, join the community, link in the description, and let's get back to the video. 00:08:04.698 --> 00:08:05.171 Thanks, guys. 00:08:05.171 --> 00:08:12.783 All right, so the first thing that I want to do in this project is I want it to be able to just kind of familiarize with self with my workspace and with who I am. 00:08:12.783 --> 00:08:16.586 And the way that I'm going to do that is I have a project locally. 00:08:16.586 --> 00:08:25.834 If I go to my um if I go to my desktop and I go into a project here called YouTube OS, I have like all of my transcripts right here from some YouTube videos. 00:08:25.834 --> 00:08:28.308 So, what I'm going to do is I'm not going to give it that file path. 00:08:28.308 --> 00:08:35.709 I'm just going to say, "Hey, in my desktop, look inside my YouTube OS folder, and just pull in 10 of my raw transcripts and analyze them." 00:08:35.719 --> 00:08:42.727 This is just to show you guys how good it's going to be at finding different files locally and being able to organize them, move them, delete them, whatever you want. 00:08:42.727 --> 00:08:44.702 In this case, I'm just telling it to read them. 00:08:44.702 --> 00:08:52.712 All right, so I want you to go onto my desktop, and I want you to look at a folder called YouTube OS, and I just want you to familiarize yourself with me. 00:08:52.712 --> 00:08:59.375 I make YouTube videos on AI automation, and inside of this folder, I have a bunch of my raw transcripts. 00:08:59.375 --> 00:09:04.350 So, I just want you to read through like 5 to 10 of those just to familiarize yourself with the type of content that I make. 00:09:04.350 --> 00:09:05.655 You shouldn't do any organization. 00:09:05.655 --> 00:09:07.432 I just want you to read those for context. 00:09:07.432 --> 00:09:11.762 Now, what's cool about this is Codex, once again, is an agent that lives locally. 00:09:11.762 --> 00:09:22.251 So, just because it's working inside of one project, which is our, you know, um YouTube sort of demo folder, that doesn't mean that it can't navigate anywhere else inside of your local files. 00:09:22.251 --> 00:09:24.816 And because we're telling it to do so, it's going to search. 00:09:24.816 --> 00:09:27.318 Right here, you can see it's searching inside of my desktop. 00:09:27.318 --> 00:09:30.903 And then it's going to find the YouTube OS, and it's going to drill down into that folder. 00:09:30.903 --> 00:09:33.950 And it's going to keep searching until it finds what it wants. 00:09:33.960 --> 00:09:35.028 Now, a quick warning. 00:09:35.028 --> 00:09:38.621 This is not the most effective use of Codex or of your tokens. 00:09:38.621 --> 00:09:44.200 The more effective use would be to say, "Hey, this is the folder right here with all my raw transcripts. 00:09:44.200 --> 00:09:54.268 I'm going to copy this path, and I'm now just going to give Codex this exact path, so it can just look in there instead of having to search for it on its own." But I just wanted to show you how it's able to do this. 00:09:54.268 --> 00:09:59.339 Because you can see right here, inside of my transcripts folder, I have one called raw, and that's the one that I wanted it to look at. 00:09:59.339 --> 00:10:02.888 And right here it says there are two files, raw and then processed. 00:10:02.888 --> 00:10:05.091 So it doesn't know which one to look through. 00:10:05.091 --> 00:10:09.078 So anyways, the more specific you can be with your prompting and with your pointing, the better. 00:10:09.078 --> 00:10:12.569 Now let's also, while this is running, talk about the model stuff over here. 00:10:12.569 --> 00:10:14.829 So right now you've noticed that we're on extra high. 00:10:14.829 --> 00:10:18.560 And I would say that extra high is probably overkill for that sort of job. 00:10:18.560 --> 00:10:22.738 For the most part, I'm using medium to do all of my planning and my brainstorming. 00:10:22.738 --> 00:10:27.138 And then every once in a while, if I'm doing a huge build or some massive scale, I'll switch to high. 00:10:27.138 --> 00:10:33.510 I'm honestly hardly using extra high unless I'm hitting some sort of bug or issue that it's not able to solve. 00:10:33.520 --> 00:10:38.226 Anyways, it has read nine transcripts, so it has a little bit of a better of an idea now about who we are. 00:10:38.226 --> 00:10:44.105 But just to show you guys, this is still the folder that we're working in, the YouTube Analytics Demo, and there's nothing that exists here. 00:10:44.105 --> 00:10:51.202 So even though it knows this, this knowledge only really lives in our overall ChatGPT memory, and in this specific chat window. 00:10:51.202 --> 00:10:55.357 If I opened up a new chat, it probably wouldn't still have the knowledge about this. 00:10:55.357 --> 00:10:59.916 So what I'd probably want to do is say, "What I want you to do is set up an agents.md file. 00:10:59.916 --> 00:11:03.876 This should have context about me and about what the goal of this project is. 00:11:03.876 --> 00:11:13.310 Ultimately, what we're going to do here is we're going to build a dashboard that's going to be pushed to dashboard that's going to be pushed to Vercel, and it's going to have information about my channel and some analytics around the 00:11:13.320 --> 00:11:14.717 comments and stuff like that. 00:11:14.717 --> 00:11:15.661 So that's the end goal. 00:11:15.661 --> 00:11:20.474 We're going to have to connect to YouTube, we're going to have to pull in data, we're going to set up some skills and some automations. 00:11:20.474 --> 00:11:24.498 But I just want you to get us started here with a quick agents.md file. 00:11:24.498 --> 00:11:27.110 And now I'm going to go ahead and shoot that off." 00:11:27.120 --> 00:11:29.114 Now, why do we need to create an agents.md file? 00:11:29.114 --> 00:11:34.537 Well, if you're coming over from Cloud Code, you know that we always want to start a project with a Claude.md file. 00:11:34.537 --> 00:11:40.430 And this is just agents.md, it's the same thing, but Codex expects a different terminology. 00:11:40.440 --> 00:11:43.830 And what this agents file does is it's basically like it's onboarding doc. 00:11:43.840 --> 00:11:54.883 Every time you open up a new chat, it's first of all going to read the agents.md file and it's going to get organized with what is my goal, what is this user doing, and how do I help them as effectively as possible. 00:11:54.883 --> 00:11:56.433 So, this document has been created. 00:11:56.433 --> 00:11:58.649 If I click on open, we're going to be able to read it right here. 00:11:58.649 --> 00:12:00.460 And it's just a very simple markdown file. 00:12:00.460 --> 00:12:02.013 This is the project right here. 00:12:02.013 --> 00:12:04.443 This is about Nate's, Nate Herc does this. 00:12:04.443 --> 00:12:05.950 This is the project goal. 00:12:05.960 --> 00:12:07.183 This is the product direction. 00:12:07.183 --> 00:12:11.790 So, we're just giving it really important information that it needs to know about our project. 00:12:11.800 --> 00:12:17.852 And you can see now if I pull the file explorer over, it has created this agents markdown folder, which is exactly what we wanted. 00:12:17.852 --> 00:12:19.150 Sorry, not folder, file. 00:12:19.160 --> 00:12:23.510 Okay, so now that that's out of the way, I'm going to go ahead and close back out of that, and we're going to get started. 00:12:23.520 --> 00:12:26.705 So, what I'm going to do is I'm going to click on this button and I'm going to turn on plan mode. 00:12:26.705 --> 00:12:31.071 Plan mode is what I like to start with when I am creating some sort of plan. 00:12:31.071 --> 00:12:38.328 That basically means that Codex won't actually execute anything, it's just going to brainstorm and help you guys get clear on what you want to build before you actually build it. 00:12:38.328 --> 00:12:40.230 So, I always start with plan mode. 00:12:40.240 --> 00:12:41.390 Now, I'm just going to start yapping. 00:12:41.400 --> 00:12:45.957 And by the way, if you guys are curious about the tool I use for voice-to-text, check it out in the description, it's called Glido. 00:12:45.957 --> 00:12:48.732 I'm now an official member of the Glido team, which is super exciting. 00:12:48.732 --> 00:12:56.530 I've fully switched over from Whisper to Glido because it's faster, it's more private, and it is a way more agentic tool, and we've got a really cool vision. 00:12:56.530 --> 00:12:57.913 So, check it out in the description. 00:12:57.913 --> 00:13:06.192 Okay, so now that you understand that context, the first hurdle for us to overcome is how do you actually connect to my YouTube in order to be able to pull in my data. 00:13:06.192 --> 00:13:11.270 I want you to be able to specifically at this point be able to pull in a bunch of comments so that you can analyze them. 00:13:11.280 --> 00:13:14.670 So, help me figure out how we do that, and then explain it to me step-by-step. 00:13:14.680 --> 00:13:24.710 And that's really the mindset shift with tools like Codex or Claude Code is if you don't know something's possible, instead of defaulting to oh, I need to go to YouTube or oh, I want to book in a consulting call with an expert, just ask 00:13:24.720 --> 00:13:26.266 Codex or Claude Code. 00:13:26.266 --> 00:13:28.514 Ask it to do research and explain things to you. 00:13:28.514 --> 00:13:31.350 And that's basically how I learned everything that I know. 00:13:31.360 --> 00:13:35.947 So while this is running, I wanted to explain something real quick, which is called plugins. 00:13:35.947 --> 00:13:39.544 Plugins, MCP servers, skills, connectors, whatever you want to call them. 00:13:39.544 --> 00:13:43.473 We kind of have this interface inside of Codex to do stuff like this. 00:13:43.473 --> 00:13:46.028 And what you'll notice is there's a bunch of different plugins here. 00:13:46.028 --> 00:13:50.072 We've got hugging face, we've got Vercel, we've got GitHub, we've got Game Studio. 00:13:50.072 --> 00:13:54.235 We've got a bunch down here for design, Remotion, Figma, Hyperframes, Canva. 00:13:54.235 --> 00:14:00.190 We've got stuff for lifestyle, productivity, and this lets us basically connect to a lot of the tools that we already know and love. 00:14:00.200 --> 00:14:05.433 Google Drive, Slack, SharePoint, Teams, whatever you may need, a lot of that stuff is available here. 00:14:05.433 --> 00:14:06.966 And if you can't find it, you can go ahead and search. 00:14:06.966 --> 00:14:08.618 So like Slack, we have it right there. 00:14:08.618 --> 00:14:13.190 But look, if I search YouTube, there is no default plugin right here. 00:14:13.200 --> 00:14:18.377 And that's why I had to ask Codex, okay, so there's no plugin, how do I actually access YouTube data? 00:14:18.377 --> 00:14:21.550 And so it comes back here and it asks us some questions. 00:14:21.560 --> 00:14:28.110 It says for the first comment analysis milestone, which connection path should we plan around, API key, OAuth, or both? 00:14:28.120 --> 00:14:33.190 Um I'm just going to go with his recommendation cuz let's say I don't know what I need to do, and I'm going to click on API key. 00:14:33.200 --> 00:14:34.870 What should the first comment pull focus on? 00:14:34.870 --> 00:14:36.670 I'm just going to say recent videos. 00:14:36.680 --> 00:14:40.470 And now if it has any other questions, it'll go ahead and ask us those first. 00:14:40.480 --> 00:14:49.710 Now one thing you'll notice is because it already was searching through my other folders and projects, it did find an API key in a different project, but I'm still going to show you guys how you would get this set up because it comes 00:14:49.720 --> 00:14:52.790 back here with a plan, which we can go ahead and read. 00:14:52.800 --> 00:14:59.270 So what it wants to use is it it found an API key, so not full OAuth, and then it needs to actually convert everything. 00:14:59.280 --> 00:15:09.750 So what I'm just going to say is instead of implementing, I'm going to say, "I'm glad that you found that API key, but let's set up a fresh one because in my Google Cloud, I want to have a separate API key for Codex and a 00:15:09.760 --> 00:15:11.069 separate one for Claude code. 00:15:11.069 --> 00:15:16.388 So let's just go ahead and assume that we're going to create a complete new one from scratch." And now I'm able to shoot off those changes. 00:15:16.388 --> 00:15:19.087 Codex is going to review the plan and then edit it. 00:15:19.087 --> 00:15:22.345 And then once we're aligned on the plan, we'll go ahead and start executing. 00:15:22.345 --> 00:15:26.230 So now it's come back and it has okay, we're going to do a brand new Google Cloud API key. 00:15:26.240 --> 00:15:32.070 If you wanted to read through all of this step-by-step, you could, but I'm just going to go ahead and say submit, implement the plan. 00:15:32.080 --> 00:15:33.835 So, there's some stuff that we're going to have to do here. 00:15:33.835 --> 00:15:43.619 We're going to have to go into Google Cloud Console, and we're going to have to create this new project, um enable this API, and then grab the API key, and then get it configured inside of Codex. 00:15:43.619 --> 00:15:50.630 So, if this part of the tutorial isn't very interesting to you, you don't want to watch me get it set up, maybe you want to do some stuff first with the native plugins, which is much easier. 00:15:50.640 --> 00:15:58.670 Typically, these plugins you just basically sign in, the same way where you would open up Slack and sign in, or the same way you would open up Gmail and sign in, and that's a lot lot easier. 00:15:58.680 --> 00:16:02.150 Okay, so I have to go to Google Cloud and get everything set up in a project. 00:16:02.160 --> 00:16:08.169 If I didn't know exactly how to do this, it would tell me step-by-step as you guys saw on the plan, but what it's going to do is it created another file for us. 00:16:08.169 --> 00:16:10.016 So, it created this one called for us. 00:16:10.016 --> 00:16:11.550 So, it created this one called .env.local. 00:16:11.560 --> 00:16:14.536 So, what I'm going to do is head over to my Google Cloud Console. 00:16:14.536 --> 00:16:18.550 I'm signed in with my YouTube account, and I'm going to go ahead and create a new project. 00:16:18.560 --> 00:16:21.799 So, I'm going to call this one um Codex demo. 00:16:21.799 --> 00:16:26.304 I'm just going to go ahead and create this project, and once that's spun up, it's pretty simple. 00:16:26.304 --> 00:16:31.376 We just have to create a connection to YouTube Data API, and then we're going to create an API key. 00:16:31.376 --> 00:16:32.542 So, I'm going to select this project. 00:16:32.542 --> 00:16:42.650 The first thing I'm going to do is search up here at the top for YouTube is search up here at the top for YouTube Data, and we're going to grab the YouTube Data API v3, and then I'm going to go ahead and click enable. 00:16:42.650 --> 00:16:51.196 And once that has been enabled, it should pull up a new screen that looks like this, and then I'm going to go down here to credentials, and I'm going to just create a new API key. 00:16:51.196 --> 00:16:52.295 So, create API key. 00:16:52.295 --> 00:16:56.331 This is just going to be called Codex YouTube demo. 00:16:56.331 --> 00:16:59.522 And then right here for the restrictions, I'm just going to once again type in YouTube. 00:16:59.522 --> 00:17:03.858 We're going to check YouTube Data API v3, and then we're going to go ahead and create that API key. 00:17:03.858 --> 00:17:05.946 And it gives me this value that I'm going to go ahead and copy. 00:17:05.946 --> 00:17:18.058 So, I'm going to copy that, and then I'm going to pull in that file that it created, the .env.local, and I'm just going to open this file real quick with um my notepad, and here is where I'm going to put my YouTube API key. 00:17:18.058 --> 00:17:19.829 I'm just going to paste that in right there. 00:17:19.839 --> 00:17:25.790 Hit save and then I can close out of that because what we need to get next is we need to get our YouTube channel ID. 00:17:25.800 --> 00:17:27.476 I'm not actually going to do the uploads playlist. 00:17:27.476 --> 00:17:31.085 I don't think it needs that, but I am going to go find the YouTube channel ID. 00:17:31.085 --> 00:17:32.460 Oh, but this is actually cool. 00:17:32.460 --> 00:17:38.548 My YouTube channel ID is already in there and the playlist ID is already in there because it was able to just pull it from a different project. 00:17:38.548 --> 00:17:44.497 So obviously if you didn't have that already set up, it wouldn't do that, but it would explain to you exactly how to do that if you needed to. 00:17:44.497 --> 00:17:48.470 So now that we have that API key put in, let's just see if it works. 00:17:48.480 --> 00:17:52.750 Okay, so I've given you the API key in that local.env. 00:17:52.760 --> 00:17:55.198 Can you go ahead and test it to see if that connection works? 00:17:55.198 --> 00:17:57.317 And if not, then we'll have to make some changes. 00:17:57.317 --> 00:18:05.678 Okay, now while this is running, what you guys might notice when you hop into Codex is that it might pause a lot to actually ask you questions and like approve things. 00:18:05.678 --> 00:18:08.355 And that's what happens when you're on default permissions. 00:18:08.355 --> 00:18:11.310 So if you want to be able to change that, you're going to go up here to your settings. 00:18:11.320 --> 00:18:14.857 And then in general, you can see right here, auto review or full access. 00:18:14.857 --> 00:18:16.849 And this by default will be turned off. 00:18:16.849 --> 00:18:25.539 So if I turn this on, then when we're back in our chat, we now have the ability, see right here, this is exact example, allow network access and I want to say yeah, allow it. 00:18:25.539 --> 00:18:30.772 Or if I switch this to full access, now it's just going to do everything without asking for permission. 00:18:30.772 --> 00:18:36.828 So obviously it comes up as orange here because there's sometimes where you might not want full autonomous access. 00:18:36.828 --> 00:18:43.049 And I think it's best practice when you're first getting started and you're first building some automations to maybe just leave it on default. 00:18:43.049 --> 00:18:50.791 But once you start getting a hang of your skills and you start getting a hang of the flow, then moving to full access is going to save you a lot of time so that you can actually not have to baby sit it. 00:18:50.791 --> 00:18:58.333 But I had to call that out because, you know, we've seen horror stories of agents deleting databases or sending out mass emails and stuff like that. 00:18:58.333 --> 00:18:59.832 So you just want to be safe with it. 00:18:59.832 --> 00:19:02.395 I personally have never had any sort of problem like that. 00:19:02.395 --> 00:19:08.437 That usually comes from context rot or very vague instructions or or just not being super smart with your planning. 00:19:08.437 --> 00:19:11.013 So you can see what's happening here is it's trying it out, right? 00:19:11.013 --> 00:19:12.303 And it's running into some issues. 00:19:12.303 --> 00:19:17.096 But what's great about this agentic loop is that it's going to keep trying things until it actually goes through. 00:19:17.096 --> 00:19:17.599 There we go. 00:19:17.599 --> 00:19:23.512 You can see nice the key works for channel data, and I'm going to do one more test to make sure that I can pull comments from recent videos. 00:19:23.512 --> 00:19:34.950 So a big mindset shift when you're using any of these tools is to just let it run, let it try things, help steer in the right direction, ask questions, be curious, and just take a look at what it's doing because it tells 00:19:34.960 --> 00:19:36.870 you every single thing that it's trying. 00:19:36.880 --> 00:19:38.830 But now we can see I've tested the key. 00:19:38.840 --> 00:19:42.776 I can get comments from your recent videos, and it's completely working as expected. 00:19:42.776 --> 00:19:49.150 However, PowerShell's built-in web request had a local TLS issue, but Node and Python both connected cleanly. 00:19:49.160 --> 00:19:50.618 For the project, that's fine. 00:19:50.618 --> 00:19:54.110 We'll use Node and server-side code for the dashboard anyway. 00:19:54.120 --> 00:19:56.390 Now, here's something to think about. 00:19:56.400 --> 00:19:58.430 I don't really know what that means. 00:19:58.440 --> 00:20:07.430 But what I want to make sure is that that doesn't happen again, or I want to make sure that this project doesn't lose this knowledge because it it it it ran into a failure. 00:20:07.430 --> 00:20:14.136 And whenever you run into a failure, you want to treat that as golden knowledge because it means you have more data to make sure that it doesn't do it again. 00:20:14.136 --> 00:20:17.934 So all I'm going to say is, "Okay, thanks for testing that. 00:20:17.934 --> 00:20:23.529 I want to make sure that you don't ever run into that issue again, and I want to make sure that that knowledge is saved in this project. 00:20:23.529 --> 00:20:31.590 So can you just throw together a quick file somewhere in your memory, somewhere in this project to make sure that you already know that so that next time it doesn't happen again." 00:20:31.600 --> 00:20:41.390 And doing stuff like this, having this sort of habit, is how you actually make these systems get smarter over time rather than just feeling like you're always repeating yourself or that you're always running into the same issues. 00:20:41.400 --> 00:20:43.105 Another mindset shift for you right there. 00:20:43.105 --> 00:20:45.643 So here it decided to add this into the agents.md. 00:20:45.643 --> 00:20:55.904 Right now, I have no objections to that, but as your projects grow, you don't want to put everything in the agents.md because if that agents.md file gets really huge, it's going to use more of your tokens. 00:20:55.904 --> 00:20:56.150 Okay. 00:20:56.160 --> 00:21:00.790 So before we keep going, I did want to point out one other thing down here, which is this little bar. 00:21:00.800 --> 00:21:04.500 This shows you how much of your context window is currently filled up. 00:21:04.500 --> 00:21:08.058 Now, if If were using Claude Code and you're using Opus, you have a million. 00:21:08.058 --> 00:21:11.491 So, it's, you know, about four times as much as this in Codex. 00:21:11.491 --> 00:21:16.838 However, Codex automatically compacts just like Opus does and just like Cloud Code does. 00:21:16.838 --> 00:21:17.595 So, it's really nice. 00:21:17.595 --> 00:21:23.085 You don't have to worry about it too much, but you still want to be thinking about some general context management tips. 00:21:23.085 --> 00:21:27.386 I've got some videos on my channel about that that are agnostic to whatever tool you want to use. 00:21:27.386 --> 00:21:32.735 I'm not going to dive super deep into context window management in this video, but just wanted to point that out as well. 00:21:32.735 --> 00:21:33.929 Okay, so what's next? 00:21:33.929 --> 00:21:40.429 What I want to do is I want to show you guys that it's able to pull comments and that we're able to create an actual deliverable from it. 00:21:40.429 --> 00:21:42.803 So, let me just once again go back to plan mode. 00:21:42.803 --> 00:21:49.200 All right, so what I want you to do is pull in, you know, about 100 or 200 of my most recent comments and I want you to analyze them. 00:21:49.200 --> 00:21:54.247 I want you to find patterns and I want you to display all of this in a Excel sheet. 00:21:54.247 --> 00:22:05.670 And I want it to be a visual representation of this data that has interesting insights for me as a content creator so that I can keep making content that people want and I can keep answering questions that are coming up frequently. 00:22:05.680 --> 00:22:10.633 So, go ahead and do a plan for this and structure what the Excel sheet deliverable will look like. 00:22:10.633 --> 00:22:11.342 So, I shot that off. 00:22:11.342 --> 00:22:15.006 I'm going to let you guys know when we have a plan or if it asks me any questions. 00:22:15.006 --> 00:22:17.607 A couple questions here to make sure that it understands what we want. 00:22:17.607 --> 00:22:19.328 It's asking about the recent comments. 00:22:19.328 --> 00:22:21.078 I'm just going to say across recent videos. 00:22:21.078 --> 00:22:22.310 How many should we pull? 00:22:22.320 --> 00:22:23.078 Let's say 200. 00:22:23.078 --> 00:22:25.476 How should we classify and summarize the comments? 00:22:25.476 --> 00:22:27.030 I'm just going with all of its recommendations. 00:22:27.040 --> 00:22:27.796 Those were pretty good. 00:22:27.796 --> 00:22:32.962 And so, if I switch over to a different tab, let's say we're back on our slides, you can see my pet down here has a little one next to it. 00:22:32.962 --> 00:22:39.388 Well, the one's gone because I switched back into Codex, but that little one, if I would have hovered over it, it would show me what it's working on. 00:22:39.388 --> 00:22:43.390 So, now I can keep tabs on my workflow while I'm doing other things. 00:22:43.400 --> 00:22:45.622 And Codex makes multitasking really easy. 00:22:45.622 --> 00:22:49.102 Because of the fact that I could open up a new chat in this project and work on something else. 00:22:49.102 --> 00:22:51.660 Then I could open up a new chat in this project and work on something else. 00:22:51.660 --> 00:22:57.597 And it will color code and give you like a little blue dot or yellow dot on the side here if one of these sessions needs attention. 00:22:57.597 --> 00:22:58.822 So, anyways, here is the plan. 00:22:58.822 --> 00:23:01.593 What I would recommend is at this point you read through it. 00:23:01.593 --> 00:23:06.941 You make any changes to specific sections if you want, but for the sake of the video I'm just going to go ahead and submit that plan. 00:23:06.941 --> 00:23:11.125 But while this is running real quick, I wanted to show you a few other things that we can look at. 00:23:11.125 --> 00:23:15.270 So, if you do {slash} inside of this chat, there's things that you can actually look at. 00:23:15.280 --> 00:23:22.430 So, we've got auto review, code review, feedback, MCP, memories, model, personality, pet, plan mode, reasoning. 00:23:22.440 --> 00:23:29.110 There's all of these different skills that we can use like browser use, GitHub, Higgs Field, PDF, skill creator. 00:23:29.120 --> 00:23:31.799 The {slash} is going to open up a lot of different things for you. 00:23:31.799 --> 00:23:34.174 And of course, what you can do is you can also tag things. 00:23:34.174 --> 00:23:40.433 So, if I do an {at}, this is going to let us tag either specific plugins or specific files that live somewhere in this project. 00:23:40.433 --> 00:23:49.603 So, if you're ever trying to reference a specific plugin or something specific, then it's probably best to try using the {slash} or using the {at} to actually tag that in your chat. 00:23:49.603 --> 00:23:57.888 Now, the reason I wanted to bring up the {slash} is because you'll see one right here called {slash} personality, which if I shot that off, it would actually let it, you know, do something. 00:23:57.888 --> 00:24:01.470 So, what I can show you is I don't want to interrupt this main don't want to interrupt this main session. 00:24:01.480 --> 00:24:04.164 I could come up here and I could click on open side chat. 00:24:04.164 --> 00:24:09.478 And that opens up a different little conversation here that still lives in this chat, still lives in this project. 00:24:09.478 --> 00:24:13.830 So, if you're coming over from Cloud Code, this is pretty similar to {slash} by the way. 00:24:13.840 --> 00:24:16.209 So, what I can do over here is I can do {slash} personality. 00:24:16.209 --> 00:24:19.755 And now I can set if I want the personality to be friendly or pragmatic. 00:24:19.755 --> 00:24:25.975 And I guess I didn't actually need to switch over here because it just opens like this, but right now we're on friendly. 00:24:25.975 --> 00:24:27.633 I'm actually going to switch this to pragmatic. 00:24:27.633 --> 00:24:31.174 You can see this says concise, task-focused, and direct. 00:24:31.174 --> 00:24:34.774 And honestly, most of the time I'd probably prefer pragmatic. 00:24:34.774 --> 00:24:37.390 So, I'm usually working on pragmatic by default. 00:24:37.400 --> 00:24:40.414 But now that we've opened the side chat, let me just show you guys something else. 00:24:40.414 --> 00:24:46.008 Um, give me a quick update about my YouTube channel and, you know, the type of videos I've been making recently. 00:24:46.008 --> 00:24:55.990 Just to show you guys that, okay, if you have your agent working right here on something and you don't want to interrupt it, but you have some sort of side question that is relevant to this project or maybe relevant to something that you guys were working on 00:24:56.000 --> 00:24:57.852 earlier, you can ask over here. 00:24:57.852 --> 00:25:02.150 Because right here you can see it has the context of what we talked about already. 00:25:02.160 --> 00:25:05.964 And I could go back and forth a little bit, and then I could just close out of the side chat whenever I'm done. 00:25:05.964 --> 00:25:07.464 Okay, so that has been created. 00:25:07.464 --> 00:25:15.992 It pulled in 200 recent comments across three recent videos, and I could open it up right here in this dashboard sort of view right in CodaX, which is awesome. 00:25:15.992 --> 00:25:20.570 And I could actually make some follow-ups and chat with it right here, but it's a little bit finicky to be honest. 00:25:20.570 --> 00:25:25.124 So what I'm going to do is close out of that, and I'm just going to open up our folder again, which was right here. 00:25:25.124 --> 00:25:26.936 And you can see there's a lot more that lives in here now. 00:25:26.936 --> 00:25:34.454 Not only do we have our agents and our .env, but we have scripts, and we have outputs, and we have different nodes and modules, which has a lot of stuff. 00:25:34.454 --> 00:25:42.950 So if at any point this starts to feel a little bit unorganized and you don't understand the structure, all you have to do is come into CodaX and say, have to do is come into CodaX and say, "Hey, help me like reorganize this, or maybe 00:25:42.960 --> 00:25:45.510 give me a document that helps me navigate it a little bit better." 00:25:45.520 --> 00:25:51.334 Because of course this lives in a local directory, and CodaX can touch it, read it, organize it, edit it. 00:25:51.334 --> 00:25:56.367 So if I go to the outputs and I go to the YouTube comment insights, we see all of these different stuff that it did. 00:25:56.367 --> 00:26:00.855 So it took some screenshots as you can see, but then it also created the actual Excel sheet. 00:26:00.855 --> 00:26:03.826 So I'll open this up right here, and we can take a look. 00:26:03.826 --> 00:26:05.485 All right, so we and we can take a look. 00:26:05.485 --> 00:26:12.595 All right, so we have YouTube comment insights, 200 newest public comments across recent Nate Hurt videos, generated May 5th, 11:00 a.m. 00:26:12.595 --> 00:26:17.670 So we can see the question rate, the content requested rate, top mention tools CodaCode. 00:26:17.670 --> 00:26:18.066 Uh-oh. 00:26:18.066 --> 00:26:22.203 We've got high priority stuff, top patterns, skip video, stuff like that. 00:26:22.203 --> 00:26:24.611 It even started to create some visuals here, which is awesome. 00:26:24.611 --> 00:26:27.124 So this is content category mix over here. 00:26:27.124 --> 00:26:31.596 It shows the mix between general feedback or questions with um actual values. 00:26:31.596 --> 00:26:34.688 So 55 were general feedback, 53 were questions. 00:26:34.688 --> 00:26:39.415 Some of these were access, positive feedback, tool comparison, pricing stuff. 00:26:39.415 --> 00:26:41.055 Over here we have different tools. 00:26:41.055 --> 00:26:43.278 So CodaCode, Higgs Field, CodaX API. 00:26:43.278 --> 00:26:45.501 And then over here we have some other stats as you can see. 00:26:45.501 --> 00:26:47.254 Now we have a bunch of different tabs as well. 00:26:47.254 --> 00:26:48.635 So we have creator insights. 00:26:48.635 --> 00:26:51.496 So ranked comment patterns and recommended creator actions. 00:26:51.496 --> 00:26:58.867 So I'm able to see the percentage breakdown of different types of comments and it also gives me recommended actions with priority scores. 00:26:58.867 --> 00:27:00.138 So, that's pretty cool. 00:27:00.138 --> 00:27:01.640 I also can see frequent questions. 00:27:01.640 --> 00:27:03.913 So, things that are coming up as patterns. 00:27:03.913 --> 00:27:08.190 It's giving me content ideas now as well because it's analyzing those comments. 00:27:08.200 --> 00:27:12.444 It's giving me nice reply opportunities and then it's giving me just the raw comments. 00:27:12.444 --> 00:27:16.696 So, this should be 200 rows of our actual comments that it pulled. 00:27:16.696 --> 00:27:21.273 204 as you can see because the first three or four were just nonsense. 00:27:21.273 --> 00:27:22.487 So, that is awesome. 00:27:22.487 --> 00:27:25.628 And what you guys might be thinking is okay, is this actually useful? 00:27:25.628 --> 00:27:29.916 Maybe not because we just said, "Hey, give me analytics." Right? 00:27:29.916 --> 00:27:32.567 If you guys remember my actual prompt, it was very, very vague. 00:27:32.567 --> 00:27:44.230 So, if we would have spent more time in the planning phase or if we had certain analytics that we're tracking very heavy or certain comments that we're really looking out for, we would give that to Codex as knowledge and it would make this actual, um, you 00:27:44.240 --> 00:27:48.359 know, insights, it would make it much know, insights, it would make it much more customized and tailored. 00:27:48.359 --> 00:27:50.696 So, now let's talk about how do we turn this into a skill? 00:27:50.696 --> 00:27:52.200 So, first of all, what is a skill? 00:27:52.200 --> 00:27:53.110 So, first of all, what is a skill? 00:27:53.120 --> 00:27:55.405 Well, a skill is basically a repeatable recipe. 00:27:55.405 --> 00:27:58.949 So, if I come back in here and I click on plugins, we saw all these plugins, right? 00:27:58.949 --> 00:28:06.698 These are actual like connections and potentially MCP servers and kind of like some other, you know, it's a package that people are able to install and use. 00:28:06.698 --> 00:28:09.969 But, skills are more of just like instructions. 00:28:09.969 --> 00:28:11.850 So, there's an image gen skill. 00:28:11.850 --> 00:28:13.950 There is a OpenAI doc skill. 00:28:13.960 --> 00:28:17.295 There's a GitHub review follow-up skill, a document skill. 00:28:17.295 --> 00:28:23.271 And these are all basically just markdown file instructions that tell Codex how to do something better. 00:28:23.271 --> 00:28:27.497 So, how to design a website better or how to, you know, give you a morning brief. 00:28:27.497 --> 00:28:32.882 And so, what we want to do is we want to turn this, exactly what we just did, into a skill. 00:28:32.882 --> 00:28:41.544 So, that anytime I say, "Hey, go give me more YouTube insights." It knows what endpoints to hit, it knows how to pull them in, it knows how to make the Excel sheet, it knows how to do all this. 00:28:41.544 --> 00:28:52.454 And the best way that I like to make skills is I just basically brainstorm with with Codex to do something and then after I get an output I like, I say, "Okay, turn that into a skill." So, this was the ultimate deliverable, right? 00:28:52.454 --> 00:28:55.641 So, what you just did is you helped me pull in data from my YouTube. 00:28:55.641 --> 00:29:00.169 You got comments, you ran an analysis, and you created me an awesome Excel sheet deliverable. 00:29:00.169 --> 00:29:09.889 I want you to turn that into a skill so that every time I say to grab my YouTube comments and give me some insights, you do this exact flow, and that makes it more consistent. 00:29:09.889 --> 00:29:14.021 So, I'm going to shoot off that message, and while it's doing that, just think about it like this. 00:29:14.021 --> 00:29:23.630 If someone asked you to create or not create If someone asked you to make them chocolate chip pancakes, you're going to open up your cookbook or pull up your phone, and you're going to read a recipe, and you're going to follow it to 00:29:23.640 --> 00:29:23.788 a T. 00:29:23.788 --> 00:29:28.550 You're going to follow the measurements, the ingredients, and the temperature, and the timing, and temperature, and the timing, and whatever. 00:29:28.560 --> 00:29:35.405 And then next time someone asked you to make chocolate chip cookies or pancakes, you would just use that same recipe, and they'd come out pretty much the exact same way. 00:29:35.405 --> 00:29:42.623 Because if you didn't use the recipe, you would just be guessing, and you'd be you'd be sort of measuring, and you'd be feeling, and it just wouldn't be consistent. 00:29:42.623 --> 00:29:47.957 And the cool thing is, now that you have this recipe to use, every time you use the recipe, you might be able to make it better. 00:29:47.957 --> 00:29:53.512 If one time you experiment, and you add some more chocolate chips, you either like that or you don't, you update the recipe. 00:29:53.512 --> 00:29:56.820 Maybe one time you realize that you're actually leaving too much raw batter inside. 00:29:56.820 --> 00:29:57.744 So, what do you do? 00:29:57.744 --> 00:30:09.230 You update the recipe to say, "Okay, you leave it on 4 minutes on each side rather than 3 and 1/2 minutes on each side." You're able to, each time you use the recipe, have it be updated, and that is the power of building these skills. 00:30:09.240 --> 00:30:13.914 And you can see that it's able to work backwards and reverse engineer a skill from our output. 00:30:13.914 --> 00:30:25.312 And what it does is it puts them in a file called the dot Codex, which kind of lives globally, which means whenever you're working inside of any Codex project, you're going to be able to use that skill. 00:30:25.312 --> 00:30:28.897 And all you have to do to call it is you'll do a slash command, and then you will just name the skill. 00:30:28.897 --> 00:30:31.372 So, if you guys remember, down here we have all these other ones. 00:30:31.372 --> 00:30:37.551 I could do slash browser use slash image gen slash PDF, and that's how I could be able to call them. 00:30:37.551 --> 00:30:40.867 The other way you can call them is you can actually just have them be natural language. 00:30:40.867 --> 00:30:48.870 So, just to show you guys another example, if I go to my Herc 2 project, and I know this is more optimized for cloud code, but we have a dot cloud folder, which is local. 00:30:48.880 --> 00:30:55.677 So, if I click into here, I can see I have a folder called skills, and all of these are my different skills that currently live inside of my AI OS. 00:30:55.677 --> 00:31:00.711 So, let's say here I have a morning coffee skill, and I'm going to open this up real quick in my notepad just to show you guys. 00:31:00.711 --> 00:31:02.192 All this is is a markdown file. 00:31:02.192 --> 00:31:04.680 We have the name of the skill, we have the description. 00:31:04.680 --> 00:31:16.521 So, here it says, "Use when someone asks for morning coffee to prep or plan their day." So, anytime in cloud code I say, "Hey, can you help me plan my day?" cloud code will grab this morning coffee skill, read it, and then execute it. 00:31:16.521 --> 00:31:24.441 And it says, "Okay, here's the context, here's the recurring meetings, here is the meeting prep, here are these different reference IDs, here's everything you need to know, and the order. 00:31:24.441 --> 00:31:26.719 So, step one, step two, step three. 00:31:26.719 --> 00:31:32.186 Here is what you do whenever Nate asks for a morning coffee skill." So, that is all that is happening right here. 00:31:32.186 --> 00:31:37.117 You can see it created this skill called YouTube comment insights, and it did this at the global level. 00:31:37.117 --> 00:31:42.549 What I mean by that is this lives locally in our directory directory that sits across any Codex project ever. 00:31:42.549 --> 00:31:53.199 So, if I open up this other project, I could use the skill, or we could put it locally in our project, which would mean I could only use the skill in this specific YouTube analytics demo project. 00:31:53.199 --> 00:32:01.364 And all you have to do to change that differentiation is say, "Hey, instead of putting that global, put that locally in this project." Or, instead of having that locally in this project, make that global. 00:32:01.364 --> 00:32:06.030 So, now if I do a slash and I do YouTube comment insights, we have this right here. 00:32:06.040 --> 00:32:10.670 YouTube comment insights analyze comments into an Excel report. 00:32:10.680 --> 00:32:13.100 Which is the skill that we just built together, so that is awesome. 00:32:13.100 --> 00:32:20.199 All right, so before we move on to the next step of this, I wanted to talk about pets real quick just because I know you guys are dying to understand how you can get this. 00:32:20.199 --> 00:32:25.805 It's really simple, you go to your settings, and then you're going to go to your appearance and scroll all the way down, and you can see right here we have pets. 00:32:25.805 --> 00:32:27.755 And we can choose between different ones. 00:32:27.755 --> 00:32:34.103 So, right now I'm just using the Codex pet, but I could choose Dewey, or CD, or Beasod, or Stacky. 00:32:34.103 --> 00:32:38.069 So, I'm just going to go ahead and switch this to Fireball for fun, and you can see down here it changes. 00:32:38.069 --> 00:32:49.473 And yes, it's kind of a fun little UI thing, but remember if I'm not inside of Codex and I'm in this dashboard over here, we can still see the pet and it will tell us when it's working on things and when it's done with things. 00:32:49.473 --> 00:32:51.578 So, it is a little bit practical as well. 00:32:51.578 --> 00:32:52.150 All right. 00:32:52.160 --> 00:32:54.422 So, now we have a deliverable. 00:32:54.422 --> 00:32:58.738 We have an Excel sheet and we're going to use that as the back end that basically powers this next section. 00:32:58.738 --> 00:33:03.726 So, I'm going to open up a new project because we're kind of starting a new goal, a new a new deliverable. 00:33:03.726 --> 00:33:09.670 So, I want to open up a new chat and this will still be able to access everything that's in this folder. 00:33:09.680 --> 00:33:11.562 So, I'm going to go ahead and switch over to plan mode here. 00:33:11.562 --> 00:33:13.209 Okay, so here's the idea I have. 00:33:13.209 --> 00:33:19.189 You have access to a file inside of this project and what I'm going to do is actually reference the exact file. 00:33:19.189 --> 00:33:27.150 So, I'm going to look for the YouTube comment insights right here and I'm going to tag that right here and I'm going to tag that file. 00:33:27.160 --> 00:33:38.710 So, what I want you to do is create me a dashboard, spin this up on a local host, and I want it to have really nice UI elements and, you know, charts and graphics and things, so visualizing my data and I want to be able to see 00:33:38.720 --> 00:33:41.670 different insights about my YouTube different insights about my YouTube comments. 00:33:41.680 --> 00:33:48.068 What I want you to do here is I want you to use GPT image 2 and create some really nice concepts of how this dashboard should look. 00:33:48.068 --> 00:34:00.631 And also, if you want to use it for maybe like a nice logo in the top or any of the other UI elements, utilize GPT image 2 to make this thing just look really polished and really aesthetic and really fun at the same time. 00:34:00.631 --> 00:34:02.510 So, that is the idea I have. 00:34:02.520 --> 00:34:07.968 I want you to help plan this out, ask me any questions you have about this, and then we'll go ahead and execute. 00:34:07.968 --> 00:34:13.019 And so also, this default switch to extra high again, I'm just going to go ahead and switch that back to medium and then shoot that off. 00:34:13.019 --> 00:34:17.766 And you can see down here the pet has started to think and it's talking a little bit. 00:34:17.766 --> 00:34:21.608 But, the reason why you want to be careful about which models you're using, there's two reasons. 00:34:21.608 --> 00:34:27.590 The first one is because sometimes if you chuck extra high at a task that's really simple, like over engineers it. 00:34:27.600 --> 00:34:31.992 And the second piece is because each of these cost you different amounts of your tokens or your session. 00:34:31.992 --> 00:34:34.591 Obviously, low cost the least and extra high cost the most. 00:34:34.591 --> 00:34:41.859 If you go over here to your settings and you click on rate limits remaining, it shows you how much of your session you have left and when it expires. 00:34:41.859 --> 00:34:51.110 So, every 5 hours it resets and right now I have 97% remaining and then every week it resets and right now I have 99% remaining there. 00:34:51.120 --> 00:35:02.663 And so, it's really nice to be able to keep tabs on that right here, but that's why you want to be careful about, you know, your context window management and your planning and your prompting and your model usage down here. 00:35:02.663 --> 00:35:09.571 In general though, I have seen that my session is lasting way longer in Codex than it is in Claude Code. 00:35:09.571 --> 00:35:18.105 And a big part of that is because ChatGPT 5.5 is really, really efficient with tokens, with output tokens and input tokens. 00:35:18.105 --> 00:35:27.257 And if you guys go watch that video that I was talking about, you will see that exact experiment and it's really interesting to understand and look at, but I've generally found that it's really efficient with tokens. 00:35:27.257 --> 00:35:28.625 Now, we have some feedback here. 00:35:28.625 --> 00:35:34.390 It says, "Which visual direction should guide the GPT image two concepts and the final dashboard UI?" 00:35:34.400 --> 00:35:37.270 Creator Ops, Playful Studio or Executive Clean. 00:35:37.270 --> 00:35:39.001 I'm just going to go with the recommendation. 00:35:39.001 --> 00:35:42.112 For this first version, how should the dashboard get its YouTube comment data? 00:35:42.112 --> 00:35:46.340 I'm going to say to use the existing output, which was the um Excel file. 00:35:46.340 --> 00:35:49.356 And then what should the first screen prioritize most? 00:35:49.356 --> 00:35:51.431 Reply and ideas, analytics overview. 00:35:51.431 --> 00:35:54.257 I'm actually going to go with analytics overview for this one. 00:35:54.257 --> 00:36:00.691 And by the way, if you're in the app and you want to get rid of the pet really quick, you can just do {slash} pet and then that will just tuck it away. 00:36:00.691 --> 00:36:03.356 Okay, so it came up with a plan pretty quickly. 00:36:03.356 --> 00:36:05.962 You can see here that I can expand this and read about it. 00:36:05.962 --> 00:36:15.950 So, we've got like a summary, we've got key changes, we've got all this other stuff and this is where we would once again iterate with Codex before we say, "Yep, go ahead and build that for me." But I'm just going to go ahead and say, "Yep, go 00:36:15.960 --> 00:36:21.057 ahead and build that for me." You can see that it's using the image generation for GPT image two, which is really, really solid. 00:36:21.057 --> 00:36:24.270 And here is one of the kind of versions that it came up with. 00:36:24.280 --> 00:36:35.112 And I've just found if If using Codex to build games or websites or whatever it is, it just helps to give it the ability to test things out and generate some concepts first before it actually designs the rest of the site. 00:36:35.112 --> 00:36:37.571 You can see this is the little logo that it came up with, which is kind of cool. 00:36:37.571 --> 00:36:41.953 It's got like a YouTube play button with some noise and some comments coming in. 00:36:41.953 --> 00:36:51.190 And what it's going to do is it's going to store all of these assets locally somewhere in this project, so that later if we wanted to spin up different versions of the dashboard or a different landing page, it would have access to 00:36:51.200 --> 00:36:52.629 all of these assets already. 00:36:52.629 --> 00:36:53.978 And this is super cool, guys. 00:36:53.978 --> 00:37:01.184 It has like this built-in verification loop where it's going to check its work before it actually gives you an output, which is pretty cool. 00:37:01.184 --> 00:37:04.008 So, it said the automated browser verification passed. 00:37:04.008 --> 00:37:08.384 I'm now doing one visual pass to see what else there might be, what other issues. 00:37:08.384 --> 00:37:11.515 And it found three issues when it did an actual visual scan. 00:37:11.515 --> 00:37:12.772 So, now it's fixing those. 00:37:12.772 --> 00:37:14.341 It says, "Okay, those UI fixes are in. 00:37:14.341 --> 00:37:15.590 I'm going to stop the server. 00:37:15.600 --> 00:37:22.172 I'm going to rebuild, and then I'm going to verify it one more time with screenshots." And then it comes back and says, "Okay, the second visual pass looks a lot better. 00:37:22.172 --> 00:37:28.798 Here is your dashboard to actually go ahead and test out." So, let's just real quick open this up right here locally in the explorer. 00:37:28.798 --> 00:37:30.805 And now we have our creator ops signal desk. 00:37:30.805 --> 00:37:32.635 So, I'm going to expand this a little bit. 00:37:32.635 --> 00:37:34.895 We see the logo up here that it made. 00:37:34.895 --> 00:37:37.870 We see 83% creator replies, 78 total likes. 00:37:37.870 --> 00:37:43.178 We can switch between overview, replies, ideas, questions, and the explorer. 00:37:43.178 --> 00:37:44.317 And this is really cool. 00:37:44.317 --> 00:37:46.284 It looks like every single comment has a link. 00:37:46.284 --> 00:37:49.270 So, if I click on this, does it actually take us Okay, no. 00:37:49.280 --> 00:37:51.820 It didn't actually sync up every single comment to a link. 00:37:51.820 --> 00:37:55.430 But it's cool that it showed us that because that gave us a nice idea of like, "Okay, cool. 00:37:55.430 --> 00:38:04.538 I do actually want a link." Now, you can actually go ahead and work that into the back end code where every single comment should be associated with a link so that I could open it up and respond to it. 00:38:04.538 --> 00:38:14.934 Or we could take it one step further and say, "Okay, what would it look like for me to be able to respond right in this dashboard?" And you actually fire off that API call to YouTube to respond on the right comment. 00:38:14.934 --> 00:38:16.405 Because that is 100% doable. 00:38:16.405 --> 00:38:19.227 You guys have seen how I've automated my comment section a little bit. 00:38:19.227 --> 00:38:21.051 Anyways, let's Let's take a look at the overview. 00:38:21.051 --> 00:38:23.216 We can see we have this really nice chart. 00:38:23.216 --> 00:38:28.563 We have some AI insights over here where I can click on work reply queue and that goes over to the replies. 00:38:28.563 --> 00:38:31.952 I could also click on more content ideas and that takes us to the ideas. 00:38:31.952 --> 00:38:35.405 We can look at top tool mentions, reply priority, common themes. 00:38:35.405 --> 00:38:40.535 We can also see the videos that are driving comments and this would obviously grow as we pull in more and more data. 00:38:40.535 --> 00:38:47.750 So let's say at this point we like this output and we want to actually deploy this because what you'll notice is this says that it's running on a localhost. 00:38:47.760 --> 00:38:53.601 So if I copy this link right here and I go to Chrome and I paste that in, it's going to pull up exactly what we saw, right? 00:38:53.601 --> 00:38:55.670 And it works and it looks fine. 00:38:55.680 --> 00:39:03.144 But if I gave you this localhost and you copy and pasted that into your own browser, you would get nothing because this lives locally. 00:39:03.144 --> 00:39:06.041 It's being served on a server from our codebase. 00:39:06.041 --> 00:39:11.546 So what I'm going to show you how to do now is how do you actually get this from a localhost to the web? 00:39:11.546 --> 00:39:13.722 And what we're going to do is we're going to use two tools. 00:39:13.722 --> 00:39:17.723 We're going to use The first tool is called GitHub and the second tool is called Vercel. 00:39:17.723 --> 00:39:22.504 So the first thing you're going to do is you're going to type in GitHub and you're going to go over here and you're going to make a profile. 00:39:22.504 --> 00:39:25.634 It's completely free to set up, pretty much completely free to maintain. 00:39:25.634 --> 00:39:36.230 Once you've created your GitHub, all you have to do is connect this to Codex and we're going to have Codex help us set up something called a repository which is basically just a collection of your files and folders. 00:39:36.240 --> 00:39:48.390 Remember how if we open up my file explorer and we look inside of our YouTube comment or sorry, YouTube analytics demo folder, all of these files and folders are important and all we have to do is get these off of our local machine or not 00:39:48.400 --> 00:39:50.310 off, they'll still live here locally. 00:39:50.320 --> 00:39:57.594 But we're going to get them into some sort of repository where I can access them publicly or if you wanted to share these with other people, they could access them as well. 00:39:57.594 --> 00:40:06.532 So it's kind of like having a Word doc locally but instead you're putting it on into Microsoft's cloud on OneDrive or something like that so that other people can use it and you could use it from a different machine. 00:40:06.532 --> 00:40:07.771 So that's the first step. 00:40:07.771 --> 00:40:13.561 So let's go back into Codex and what do you do when you don't exactly know how something works? 00:40:13.561 --> 00:40:14.310 You just ask. 00:40:14.320 --> 00:40:15.039 know how something works? 00:40:15.039 --> 00:40:15.412 You just ask. 00:40:15.412 --> 00:40:16.493 So this looks really good. 00:40:16.493 --> 00:40:22.280 What I want to do is I want to sync this code base for this specific dashboard to a GitHub repository. 00:40:22.280 --> 00:40:24.105 So, help me get that signed up. 00:40:24.105 --> 00:40:31.057 Help me get connected here to GitHub, and then I want you to help me create that actual repo and push everything into that repo. 00:40:31.057 --> 00:40:32.924 And it even mentioned that right here. 00:40:32.924 --> 00:40:36.877 Note, this folder is not currently a Git repo, so there is no diff and status to summarize. 00:40:36.877 --> 00:40:41.372 So, I'm going to shoot off that message, and now it's going to help us actually sync up to GitHub. 00:40:41.372 --> 00:40:43.683 Now, there is a difference between Git and GitHub. 00:40:43.683 --> 00:40:49.374 Really the same thing of version control and all this stuff, but Git is local and GitHub is on the cloud. 00:40:49.374 --> 00:40:59.925 And what's important here is that it says, "I'll avoid committing secrets, especially the .env.local." And so, that's why I told you to always paste your keys in that .env, not into some random file called secrets. 00:40:59.925 --> 00:41:11.821 It has to be in the .env because that dot in front of the word env basically tells Codex or Cloud Code or whatever you're using, it tells it to exclude this from any, you know, public commits. 00:41:11.821 --> 00:41:14.102 So, this point I've already set up the GitHub CLI. 00:41:14.102 --> 00:41:17.772 If you haven't, it would just say, "Hey, do you want to set this up?" And you'll say, "Yes." Very simple. 00:41:17.772 --> 00:41:28.390 And then you'll authenticate, which means it'll basically just pop up a browser tab and you'll sign in with the account you used to create GitHub, and then boom, you will be connected to GitHub in Codex. 00:41:28.400 --> 00:41:31.345 And while this is syncing up, let me show you guys the next tool we're going to use. 00:41:31.345 --> 00:41:33.221 This one is called Vercel. 00:41:33.221 --> 00:41:35.310 Now, Vercel has a pretty generous free tier. 00:41:35.320 --> 00:41:36.713 You can see I've got a few products on here. 00:41:36.713 --> 00:41:41.049 You're going to be able to get working on Vercel for free just to get started. 00:41:41.049 --> 00:41:55.078 And what Vercel does is it basically takes that code, it takes, you know, this exact website, which is on the back end, all this is it's code, and it takes this and it serves it on a actual URL, on an actual domain that anyone can access. 00:41:55.078 --> 00:41:59.880 And what's really cool about this is Vercel and GitHub have a really nice partnership. 00:41:59.880 --> 00:42:01.534 They actually like talk to each other. 00:42:01.534 --> 00:42:06.510 So, anytime I make a change to our GitHub repo, Vercel automatically picks that up and deploys it. 00:42:06.510 --> 00:42:12.434 So, I know there's three tools here, Codex, GitHub, and Vercel, but that doesn't mean we have to manage three places. 00:42:12.434 --> 00:42:14.374 All we have to do is manage Codex. 00:42:14.374 --> 00:42:17.168 So it said that it's created a private repo for us. 00:42:17.168 --> 00:42:19.053 If I open this up, I don't want to open this up here. 00:42:19.053 --> 00:42:23.573 And the reason why it doesn't show up here is because this is a private repo and over here I'm not signed in to GitHub. 00:42:23.573 --> 00:42:29.534 So if I open this up in a browser where I am signed in to GitHub, we can see YouTube Analytics Demo. 00:42:29.534 --> 00:42:36.646 This is a private repo and what's in here is all of the different folders and files that we've actually created to spin up this dashboard. 00:42:36.646 --> 00:42:44.537 And now what's really cool is if I go into Vercel and I go ahead and click on add new project, I can connect this to GitHub and it already is connected. 00:42:44.537 --> 00:42:48.074 So you would then just sign in and you would connect your Vercel to GitHub. 00:42:48.074 --> 00:42:50.432 And now you can import any of your repos. 00:42:50.432 --> 00:42:53.710 So right here you can see YouTube Analytics Demo 1 minute ago. 00:42:53.720 --> 00:42:55.111 I'm going to click on import. 00:42:55.111 --> 00:42:56.370 And that's literally that simple. 00:42:56.370 --> 00:43:03.924 I'm going to click on deploy and then in maybe 30 seconds we will have our YouTube Analytics Dashboard, but we'll have it up on a live URL. 00:43:03.924 --> 00:43:04.416 Awesome. 00:43:04.416 --> 00:43:09.486 So it says congratulations, you have deployed a new project and I'm going to go ahead and continue to dashboard. 00:43:09.486 --> 00:43:14.790 And this gives us a youtube-analytics-demo.vercel.app a youtube-analytics-demo.vercel.app domain. 00:43:14.800 --> 00:43:18.030 And if you wanted to switch this off to your own domain, you certainly could. 00:43:18.040 --> 00:43:21.100 You would just basically have to move the DNS records over here. 00:43:21.100 --> 00:43:25.519 But I'm going to click on this so you guys can see that this is the exact same thing we were just looking at. 00:43:25.519 --> 00:43:29.212 Our replies, our ideas, our questions, our explorer, everything here is the same. 00:43:29.212 --> 00:43:31.850 Except for now I could take this URL and I could open it up on my phone. 00:43:31.850 --> 00:43:33.279 Or I could open it up on my laptop. 00:43:33.279 --> 00:43:34.522 Or you guys could open it up. 00:43:34.522 --> 00:43:38.347 And like I said, what's cool about that is we basically are able to then test in Codex. 00:43:38.347 --> 00:43:39.775 We can iterate right here. 00:43:39.775 --> 00:43:40.957 We can make changes. 00:43:40.957 --> 00:43:43.727 But just because we make changes doesn't mean that it's actually going to go live. 00:43:43.727 --> 00:43:49.590 So if I said, "Hey, I want you to change the entire background instead of blue to be red." And it would say, "Okay, cool. 00:43:49.600 --> 00:43:50.488 Here's the red background. 00:43:50.488 --> 00:43:57.230 Here's the localhost to test it out on." And if we like it, we say, "Okay, push those changes to our repo." 00:43:57.240 --> 00:44:01.475 And then as soon as we push those changes, Vercel would automatically deploy those onto the real URL. 00:44:01.475 --> 00:44:02.633 But if we said, "You know what? 00:44:02.633 --> 00:44:03.300 I don't like that. 00:44:03.300 --> 00:44:07.019 Just keep it as is." then our main production site never got touched. 00:44:07.019 --> 00:44:11.175 And that's how we keep a clean separation to test and to have something in production. 00:44:11.175 --> 00:44:12.415 Okay, awesome. 00:44:12.415 --> 00:44:14.092 So, what do we have now? 00:44:14.092 --> 00:44:21.128 We have a working project, and I'm opening up this folder just to show you how much we've actually done in the past, I don't know, 30 to 40 minutes together. 00:44:21.128 --> 00:44:23.474 And we've set up a bunch of different stuff. 00:44:23.474 --> 00:44:26.444 Now, what do I want to talk about next is automations. 00:44:26.444 --> 00:44:29.110 So, already over here you can see this tab called automations. 00:44:29.120 --> 00:44:31.314 Automate work by setting up scheduled chats. 00:44:31.314 --> 00:44:34.352 You can set up things like a status report, release prep. 00:44:34.352 --> 00:44:37.612 There's bunch of different things here that give you sort of some inspiration. 00:44:37.612 --> 00:44:45.950 But, what's really cool is you can turn all of your skills or any of your repeatable workflows into an automation that Codex will run without needing your oversight. 00:44:45.960 --> 00:44:51.245 So, I'm going to open up a new chat in our YouTube Analytics Demo project, and I'm going to go ahead and start chatting to Codex here. 00:44:51.245 --> 00:44:53.793 Okay, so we've just done a lot of stuff together. 00:44:53.793 --> 00:45:01.590 We built a skill that grabs YouTube comments from my YouTube, and it puts them into an Excel sheet after it does some analysis. 00:45:01.600 --> 00:45:03.098 And that's coming out really nice. 00:45:03.098 --> 00:45:12.350 And then we built a dashboard served on then we built a dashboard served on Vercel that actually displays visually all of those analytics and statistics from that Excel sheet. 00:45:12.360 --> 00:45:16.869 Now, what I want to do is I want to set up an automation that just refreshes this every week. 00:45:16.869 --> 00:45:23.498 So, let's just say every Sunday at 5:00 p.m., I want you to run the YouTube comments analytics skill. 00:45:23.498 --> 00:45:34.210 And then what I want you to do with that is update that data on that Excel sheet, you know, add more rows, update the statistics, and that will automatically sync to the GitHub repo. 00:45:34.210 --> 00:45:44.865 So, after you make those changes, you'll have to also reflect those changes onto the actual code base where the dashboard lives, and then you'll push those changes to GitHub so that they automatically get reflected in Vercel. 00:45:44.865 --> 00:45:59.222 So, a lot of moving pieces here, but basically high-level, you need to get more comments, redo the analysis, refresh the data into Excel, and that way I'm always getting a weekly report of what's going on with my YouTube comment replies. 00:45:59.222 --> 00:46:09.670 Okay, so honestly felt like a little bit of a messy prompt, but Codex should be able to do a good job of asking us any questions it has and making sure that it's able to actually set up this automation for us the way we want it. 00:46:09.680 --> 00:46:22.030 Now, something I want you guys to think about here is the way that I approach building AI automations and skills and stuff like this is remember when we talked about skills and I said every time you use it, it's going to get better cuz you can get feedback? 00:46:22.040 --> 00:46:24.391 You should honestly think of these automations in a similar way. 00:46:24.391 --> 00:46:27.035 You should think about it like you're teaching a kid to ride a bike. 00:46:27.035 --> 00:46:35.448 You're not going to just chuck a kid on a bike and say, "Okay, go have fun." You're going to start off by holding the handles and walking alongside the kid and saying, "Okay, you're leaning too much to the right. 00:46:35.448 --> 00:46:43.270 You need to lean more to the left and you need to center your weight and you need to make sure you're pedaling and you need to do all this." And slowly over time you'll start getting more trust and you'll take your hand off the 00:46:43.280 --> 00:46:45.863 handlebars and you'll start to walk a little bit farther behind. 00:46:45.863 --> 00:46:48.662 And eventually maybe you'll take off the training wheels and stuff like that. 00:46:48.662 --> 00:46:53.228 The point I'm making here is don't expect your automations or skills to be perfect on the first shot. 00:46:53.228 --> 00:46:54.375 That's just unrealistic. 00:46:54.375 --> 00:46:59.262 You should be expecting them to get better the more you use them because every time you use them you get more data. 00:46:59.262 --> 00:47:00.939 But look how quickly it set that up. 00:47:00.939 --> 00:47:02.510 It set up a weekly automation. 00:47:02.520 --> 00:47:09.493 It'll run every Sunday at 5:00 p.m. and it will just basically run inside of this project and it will run the YouTube comment insights workflow. 00:47:09.493 --> 00:47:11.324 It will regenerate the Excel workbook. 00:47:11.324 --> 00:47:13.575 It will preserve and merge comment rows. 00:47:13.575 --> 00:47:14.921 It will refresh the workbook. 00:47:14.921 --> 00:47:24.150 It will verify the dashboard and it will commit only those changes to our repo and it will push it to the right branch so that Vercel actually deploys all of that. 00:47:24.160 --> 00:47:25.934 And what you want to do is you come into the automations. 00:47:25.934 --> 00:47:28.929 You can see that we have this one which is Sunday at 5:00 p.m. 00:47:28.929 --> 00:47:32.685 We can click into it to see the actual prompt that it will submit to Codex. 00:47:32.685 --> 00:47:35.409 We could add some stuff here if we wanted, but we don't want to. 00:47:35.409 --> 00:47:39.014 This will get injected into a new Codex chat inside of our project. 00:47:39.014 --> 00:47:44.590 So, just as a test, if I click on run now, you can see that this starts a new chat right here. 00:47:44.600 --> 00:47:51.611 This injected that exact prompt that we looked at with the automation, the ID, the memory, the last run, and the actual prompt. 00:47:51.611 --> 00:47:57.048 And then it starts up this little progress sheet which is kind of like a to-do list and it's going to go down in this order. 00:47:57.048 --> 00:47:59.939 And we have the full Codex Agentic loop going on here. 00:47:59.939 --> 00:48:06.571 So, if you're used to Cloud Code, this is basically the same thing as running a local scheduled routine in Cloud Code or in Cloud Co-work. 00:48:06.571 --> 00:48:16.750 Now, the one thing you're going to have to think about here is because this is kind of a local cron, if you close out of the Codex app or if you turn off your PC or your laptop, this will stop running. 00:48:16.760 --> 00:48:23.957 In order for this to be truly 24/7 all the time, you would have to get this sort of Codex routine on the cloud somehow. 00:48:23.957 --> 00:48:26.830 And that's what Cloud Code just added with their cloud routines. 00:48:26.830 --> 00:48:32.812 Okay, so while this automation is running, and we know we're going to make sure that it's working as expected, and if not, we'll correct it a little bit. 00:48:32.812 --> 00:48:38.330 But, I realized that I wanted to show you guys a little bit more of that kind of computer use and and browser use functionality. 00:48:38.330 --> 00:48:45.550 So, if I go back into the actual um dashboard where it built it, which I believe was this one. 00:48:45.560 --> 00:48:46.350 Yep, it was this one. 00:48:46.350 --> 00:48:52.308 What I'm going to say here is before we kind of keep making changes, I want you to test the UI here. 00:48:52.308 --> 00:48:58.670 I want you to open up this um dashboard, and I want you to open it up in this app so I can watch you do it. 00:48:58.680 --> 00:49:02.051 I want you to use your browser use skill and click around. 00:49:02.051 --> 00:49:03.289 I want you to click on the buttons. 00:49:03.289 --> 00:49:04.842 I want you to try to break this thing. 00:49:04.842 --> 00:49:06.759 I want you to stress test it and QA it. 00:49:06.759 --> 00:49:11.410 And let me know what you find, what bugs you find, and what we might need to improve. 00:49:11.410 --> 00:49:17.246 And so, all I did here is I explained in natural language what I wanted, and we're going to be able to see it use the right skills. 00:49:17.246 --> 00:49:19.002 So, browser use is great for a lot of things. 00:49:19.002 --> 00:49:25.870 It's great for um QA-ing, like you just saw here, because it can find bugs and click around on things that typically it wouldn't be able to do. 00:49:25.880 --> 00:49:27.862 It's also really great for certain automations. 00:49:27.862 --> 00:49:33.885 So, maybe you don't have an API for something, and you want to be able to go in and download reports or go in and change some settings. 00:49:33.885 --> 00:49:38.212 I've done a few of those automations on my channel as well, and browser use can be really, really good for that. 00:49:38.212 --> 00:49:46.370 And you can even use it to just search the web, because you can use browser use in a way where it has like cookies, and it's able to remember your login info. 00:49:46.370 --> 00:49:52.716 So, you could log into something like school, where you'd have to get past the authentication, and then the browser can automate and control things. 00:49:52.716 --> 00:49:56.057 But anyways, what you see right here is the in-app browser open. 00:49:56.057 --> 00:50:01.739 And this little mouse right here, which kind of looks like the ChatGPT Alice logo, is going to click around. 00:50:01.739 --> 00:50:04.390 You guys already saw it switch from overview to replies. 00:50:04.390 --> 00:50:07.070 You can see it's moving around even more now. 00:50:07.080 --> 00:50:13.815 And as it's clicking these different links and moving around, it's going to start to document what might be wrong with this app. 00:50:13.815 --> 00:50:15.974 And then we can obviously say, "Okay, cool. 00:50:15.974 --> 00:50:19.703 Go make all of those changes for us." Right here, it found the thing with the YouTube link. 00:50:19.703 --> 00:50:25.526 So, it said they have the correct URLs, but the in-app browser did not visibly open the new tab after clicking. 00:50:25.526 --> 00:50:28.361 So, that's one of the things that we actually did notice ourselves. 00:50:28.361 --> 00:50:32.670 Now, browser use is pretty, I don't know, it can feel kind of subjective when you're looking at it. 00:50:32.680 --> 00:50:34.409 I mean, this is pretty cool to watch it move live. 00:50:34.409 --> 00:50:39.129 But that also happens in Cloud Code when I use like the Playwright CLI or something. 00:50:39.129 --> 00:50:49.419 But from my testing, Codex browser use has been much more smooth and much more intelligent than any other sort of browser use automations that I've built or used before. 00:50:49.419 --> 00:50:55.650 So, that is something that is really cool about Codex in this app here is that the browser use is really good. 00:50:55.650 --> 00:50:59.614 Now, you could obviously use it still from a CLI or whatever, but it is pretty good. 00:50:59.614 --> 00:51:03.325 And like I said, there's just so many really cool use cases with browser automation. 00:51:03.325 --> 00:51:07.971 If you want to check out a few more, even though this video was Cloud Code, you would set it up the exact same way in Codex. 00:51:07.971 --> 00:51:09.888 I'll tag a video right up here. 00:51:09.888 --> 00:51:10.922 I mean, I love this. 00:51:10.922 --> 00:51:12.672 It's literally going through the filters. 00:51:12.672 --> 00:51:14.336 You guys saw it had something else up here. 00:51:14.336 --> 00:51:15.717 It's changing these check boxes. 00:51:15.717 --> 00:51:16.809 It's changing the stuff. 00:51:16.809 --> 00:51:22.252 It did another search here, and it's really going to actually stress test this app to make sure that it didn't miss anything. 00:51:22.252 --> 00:51:29.271 And what else is really cool is you can build in this sort of QA check into skills or into the knowledge. 00:51:29.271 --> 00:51:38.910 So, next time when you're building another dashboard or next time you're building a game, before it ever comes back to you, it already does a few passes visually and, you know, from like a code perspective, but you can make 00:51:38.920 --> 00:51:47.185 sure that, "Hey, don't ever ever ever come back to me until you've stress tested with your own browser use." And that's how you can really just make this stuff smarter and smarter every day. 00:51:47.185 --> 00:51:49.384 All right, so it decided that it's done testing now. 00:51:49.384 --> 00:51:53.798 You can see that we have a bunch of things that passed, but it found a ton of improvements. 00:51:53.798 --> 00:51:55.345 It ended up finding six things. 00:51:55.345 --> 00:51:58.489 The external links for YouTube aren't really working. 00:51:58.489 --> 00:52:00.533 The empty explorer state is too bare. 00:52:00.533 --> 00:52:01.776 Search is too literal. 00:52:01.776 --> 00:52:03.538 Active tab state is mostly visual. 00:52:03.538 --> 00:52:07.958 And there's some other things that are just coming through awkward and little changes that we need to make to the UI. 00:52:07.958 --> 00:52:18.196 So, what's really cool now is I can say, "Okay, take all of these six changes and build a plan around exactly how you're going to solve those." And then once it comes back with its proper plan, we would go ahead and execute. 00:52:18.196 --> 00:52:22.122 But now that I showed you guys that, let's check back in on our actual automation that's running. 00:52:22.122 --> 00:52:24.244 You can see that it is still going through the checks. 00:52:24.244 --> 00:52:25.491 It's been about 10 minutes. 00:52:25.491 --> 00:52:32.063 So, I will just check back in with you guys once this has been fully committed and we'll see what changes we have on our actual live dashboard. 00:52:32.063 --> 00:52:32.870 Oh my goodness. 00:52:32.880 --> 00:52:40.191 So, this was pushing like 20 minutes, so I stopped it and said, "Why is it taking so long?" And it's because it couldn't overwrite a file that I had open. 00:52:40.191 --> 00:52:41.284 So, don't do that. 00:52:41.284 --> 00:52:44.505 But now we're going to go ahead and just keep this going. 00:52:44.505 --> 00:52:54.470 But honestly, there is a lesson there, which is sometimes it is nice to be able to watch it, especially before, like I said, before we know that this automation is really refined, because if it is going down the wrong path or it's 00:52:54.480 --> 00:53:05.710 hitting some sort of roadblock that you the human should be able to just be able to solve in like a quick 20 seconds, then stop it and ask a question or stop it and steer it in the right way, because it's going to help not only save 00:53:05.720 --> 00:53:07.331 you time, but it's also going to save you session limit. 00:53:07.331 --> 00:53:16.792 Because if it was just burning tokens trying things, when the fix was for me to just close out of the app, then, you know, you'd rather have stopped that earlier before it's going down multiple wrong paths. 00:53:16.792 --> 00:53:27.437 And another thing that I just noticed, which is really important to call out here, is that when you look at the automation, this automation is set up by default to run with GPT 5.2, which obviously we don't want. 00:53:27.437 --> 00:53:37.789 So, you're going to want to make sure that your model is set up correctly, that the reasoning is set up correctly, and all of this other stuff is set up correctly, because that is also a reason why that run was probably taking so long. 00:53:37.789 --> 00:53:43.519 So, I just went ahead and retriggered a new run using GPT 5.5, and I decided to try this one out using high. 00:53:43.519 --> 00:53:48.233 Now, you also might be curious about the speed thing, the difference between standard and fast. 00:53:48.233 --> 00:53:51.226 And honestly, I never really ever touch fast. 00:53:51.226 --> 00:53:57.553 I'm never working in something that's super time-sensitive where I need to go fast, because that also eats up your usage a lot quicker. 00:53:57.553 --> 00:53:58.917 But this is much more like it. 00:53:58.917 --> 00:54:02.918 We can actually see it thinking and now we're going to be able to get this back much quicker. 00:54:02.918 --> 00:54:04.751 Okay, so finally that has finished up. 00:54:04.751 --> 00:54:09.308 You can see that it was able to make changes to that Excel sheet. 00:54:09.308 --> 00:54:11.428 And it says that it analyzed 208 comments. 00:54:11.428 --> 00:54:18.235 Now, because we just did this, you know, earlier today, I'm curious if it actually analyzed 200 of the same or if it knew not to duplicate. 00:54:18.235 --> 00:54:19.748 And that's something that we'll want to take a look at. 00:54:19.748 --> 00:54:22.285 But let's actually head over to my GitHub real quick. 00:54:22.285 --> 00:54:24.087 This is the repo that we just set up, right? 00:54:24.087 --> 00:54:27.683 And if I go ahead and give this a refresh, we should now see that we have two commits. 00:54:27.683 --> 00:54:31.397 So, in the second commit, this shows we refreshed the comments. 00:54:31.397 --> 00:54:34.645 So, every single time that you make a change to this repo, it'll show that here. 00:54:34.645 --> 00:54:37.588 So, you can check at the version control and you can see what's going on. 00:54:37.588 --> 00:54:50.029 But what that means is because our GitHub repo here got a new commit, if we go to Vercel now and we look at this actual project, if I go to deployments, we should be able to see that this just picked up a new change. 00:54:50.029 --> 00:54:52.729 1 minute ago, it picked up this new deployment. 00:54:52.729 --> 00:54:57.027 So, now if we go to the dashboard and I give this a refresh, this has new data. 00:54:57.027 --> 00:55:01.434 So, this used to say 200 videos, or sorry, 200 comments, and now it says 208. 00:55:01.434 --> 00:55:05.407 So, that is just proof that we were able to actually get some fresh insights. 00:55:05.407 --> 00:55:10.413 Now, what's really nice is that it looks like it just basically added on eight new ones. 00:55:10.413 --> 00:55:16.555 It didn't like add on 200 and then 200 more and then eight more, because it realized that they were duplicated. 00:55:16.555 --> 00:55:29.550 And if we actually go and open up the actual source of truth, if I go into our repo, I go to outputs, I go to YouTube comment insights and I click on the Excel sheet that we accidentally had open earlier, we see that the dashboard is exactly the 00:55:29.560 --> 00:55:33.965 same, except for now we've analyzed eight extra comments instead of the original 200. 00:55:33.965 --> 00:55:37.070 But I wanted to show you guys what happened inside of this run. 00:55:37.080 --> 00:55:40.952 So, as you guys know, we ran into that issue where I had the Excel sheet open, right? 00:55:40.952 --> 00:55:42.174 That was the first mistake. 00:55:42.174 --> 00:55:44.593 The second mistake was that this was running with 5.2. 00:55:44.593 --> 00:55:48.254 So, we reset the automation, and now it's running with 5.5 high. 00:55:48.254 --> 00:55:50.537 But then what happened is this was running for quite a while again. 00:55:50.537 --> 00:55:52.891 So, I stopped it and said, "Hey, you've been running for a long time. 00:55:52.891 --> 00:55:54.218 Why is it taking so long? 00:55:54.218 --> 00:55:57.852 This is a very simple task." So, basically, I knew that something went wrong here. 00:55:57.852 --> 00:56:02.150 Because when we built this dashboard from scratch, it only took about 20 minutes. 00:56:02.160 --> 00:56:05.542 But updating it took 40 minutes or probably even longer. 00:56:05.542 --> 00:56:06.847 So, I knew something was going wrong. 00:56:06.847 --> 00:56:09.352 So, I stopped it, and I wanted to dig into it a little bit better. 00:56:09.352 --> 00:56:12.509 And it And I was able to find out that it was stuck on some process. 00:56:12.509 --> 00:56:21.203 So, I said, "What do you need from me in order to make sure that this doesn't happen again, and that you're able to just basically actually give us this deliverable that we're looking for?" And it had me make some confirmations. 00:56:21.203 --> 00:56:25.566 And then as soon as I did that, it took about 7 minutes, and then it was able to make all of those changes. 00:56:25.566 --> 00:56:29.265 So, the reason why I wanted to show you this is because once again, this stuff is not magic. 00:56:29.265 --> 00:56:31.935 You don't deploy something, and you just expect it to work perfectly. 00:56:31.935 --> 00:56:35.237 But what's really cool is I could say, "Awesome. 00:56:35.237 --> 00:56:37.607 So, everything worked as expected on the dashboard. 00:56:37.607 --> 00:56:39.195 The analytics have been updated. 00:56:39.195 --> 00:56:45.870 Now, I want you to dig into what you just did with this automation, and help me understand, are there any opportunities to streamline this automation? 00:56:45.870 --> 00:56:49.053 Are there any opportunities to make this better and more robust? 00:56:49.053 --> 00:56:55.213 Do you have any recommendations here?" And I'll go ahead and fire that off and see if there's any way that we can make this automation better. 00:56:55.213 --> 00:57:05.630 It's really important because there's this concept called dark code, which basically means you're writing a bunch of code when you do your vibe coding, but you don't actually know what's going on in the Python script or whatever 00:57:05.640 --> 00:57:07.195 language you're using there. 00:57:07.195 --> 00:57:13.089 And not to say that you need to understand every line of your code, but you need to understand fundamentally what it's doing and why. 00:57:13.089 --> 00:57:21.433 And if there are any opportunities to get rid of some code, or if you have to, you know, bake in some more guardrails in a certain place, or anything like that. 00:57:21.433 --> 00:57:25.148 So, it's basically looking at this to see if we can make it faster, or if we can make it safer. 00:57:25.148 --> 00:57:28.646 Now, ultimately, as long as it's working, I don't really care how fast it is. 00:57:28.646 --> 00:57:34.021 Because if this is running once a week, I don't care if it happens at 6:00 p.m. or 6:30 p.m. or even 7:00 p.m. 00:57:34.021 --> 00:57:35.460 As long as it's actually working. 00:57:35.460 --> 00:57:38.689 But sometimes speed is a big deal in your automations. 00:57:38.689 --> 00:57:47.817 So, it comes back and says, "Yes, this works, but it is still too agent orchestrated and too heavy for a weekly data refresh." So, we could add one repo script to basically run the builder. 00:57:47.817 --> 00:57:51.230 We could stop running the full next build for these sorts of updates. 00:57:51.240 --> 00:57:57.341 And it's giving us all these different insights that we could then go ahead and push to make our automation and our system better here. 00:57:57.341 --> 00:57:59.851 So, that's how you can kind of keep iterating upon it. 00:57:59.851 --> 00:58:07.187 Even if you yourself don't really know exactly how you would make this better, you can use the AI to figure out and brainstorm. 00:58:07.187 --> 00:58:07.472 Okay. 00:58:07.472 --> 00:58:10.854 So, what you guys saw here is we created this product from scratch, right? 00:58:10.854 --> 00:58:12.335 It was our YouTube analytics demo. 00:58:12.335 --> 00:58:24.950 We connected to YouTube, we set up a skill, we set up an automation, we set up a dashboard, we used some browser use, and now we have an actual system where every week it will pull in more comments, it will update our data, our Excel sheet, and 00:58:24.960 --> 00:58:28.888 then it pushes all of those changes to our actual live dashboard completely automatically. 00:58:28.888 --> 00:58:34.119 So, I hope you guys enjoyed seeing that flow from basically idea, setting up a project, all the way to the end. 00:58:34.119 --> 00:58:41.308 And just remember, what's really important is that this entire project, everything that we just did, is literally just a folder on your computer. 00:58:41.308 --> 00:58:46.259 And what that means is you can customize this folder to be used by OpenClaw or CloudCode or whatever you want. 00:58:46.259 --> 00:58:48.883 Any agent can work inside of this directory now. 00:58:48.883 --> 00:58:53.963 And if I wanted to explicitly do this inside of Codex, well, I could go ahead and click on view. 00:58:53.963 --> 00:58:55.836 I could open up the terminal. 00:58:55.836 --> 00:58:59.730 And now, because we're in this directory, I could call on Claude. 00:58:59.730 --> 00:59:04.511 And so, right here, I could be working with ClaudeCode inside of this actual repository. 00:59:04.511 --> 00:59:10.115 So, maybe right here I'm using Claude to help brainstorm, and it creates me a brainstorming file inside of this project somewhere. 00:59:10.115 --> 00:59:15.589 And then what I could do is I could just go back up here to Codex, and I could go ahead and tag that file. 00:59:15.589 --> 00:59:20.523 So, say, "Hey, here is a planning file, a brainstorm file that I just generated with Claude. 00:59:20.523 --> 00:59:26.986 I want you to be the one who actually takes this file and executes it for me." So, you can really start to play with these together and mix and match. 00:59:26.986 --> 00:59:38.448 Just like I've shown you before where we would build something with Cloud Code and then we would actually loop in Codex to do the review on it and to find like security bugs or any just like code-based functionality bugs inside of it. 00:59:38.448 --> 00:59:44.591 So, in my mind it's always about which tool is best for this specific use case, not which tool is best. 00:59:44.591 --> 00:59:46.819 All right, so I really hope that you guys enjoyed that. 00:59:46.819 --> 00:59:49.193 You should have a really good understanding of the interface of Codex. 00:59:49.193 --> 00:59:54.720 You should have a really good understanding of how you come in here, you connect to other tools, you use plugins, you start building skills. 00:59:54.720 --> 00:59:57.864 And really the next unlock is start building more and more skills. 00:59:57.864 --> 01:00:00.695 So, try to think about what are you doing on a daily basis? 01:00:00.695 --> 01:00:02.587 What are you doing on a weekly basis? 01:00:02.587 --> 01:00:07.309 And write down some of those things that are boring and repetitive and that you just wish happened when you slept. 01:00:07.309 --> 01:00:10.552 And then start to bring those into Codex and start to just brainstorm. 01:00:10.552 --> 01:00:14.733 And as you're going through this process, you're going to want to set up kind of your own AI operating system. 01:00:14.733 --> 01:00:18.163 So, I'm going to tag a video right up here that you guys should 100% go watch next. 01:00:18.163 --> 01:00:23.310 This one was kind of based on Cloud Code, but remember everything is just files and folders. 01:00:23.320 --> 01:00:28.630 So, if you follow the steps in this video, you will be able to replicate this in Codex, absolutely no problem. 01:00:28.640 --> 01:00:35.113 And what's really cool is every project that I've moved over from Cloud Code to Codex, I've said, "Hey, this is something I built with Cloud Code. 01:00:35.113 --> 01:00:46.430 Go ahead and analyze it and help me figure out what files you need to create in order to make this compatible with Codex." And all it's going to do is maybe change a few names and maybe change the cloud.md to the agent.md and 01:00:46.440 --> 01:00:47.425 it's really, really simple. 01:00:47.425 --> 01:00:50.468 It'll take like 30 seconds and then you have your project in Codex. 01:00:50.468 --> 01:00:53.773 So, anyways, I'll see you guys over there at that AI operating system video. 01:00:53.773 --> 01:00:55.317 Please give it a like if you enjoyed. 01:00:55.317 --> 01:00:56.191 It helps me out a ton. 01:00:56.191 --> 01:01:00.560 And as always, I appreciate you guys making it to the end of the video.