1 00:00:00,000 --> 00:00:09,790 You're in the right place if you use ChatGPT, Claude, Claude Code, Claude Co-work, or Codex, but don't know which one you should use for business and how. 2 00:00:09,800 --> 00:00:13,830 Because in this video, we're talking about using AI agents effectively. 3 00:00:13,840 --> 00:00:24,129 Specifically, we're talking about Codex, OpenAI's agent tool, which is like Claude Code, except it's an easy-to-use interface for doing knowledge work and coding work. 4 00:00:24,129 --> 00:00:37,924 In this video, we're going to be breaking down the seven core capabilities of Codex, OpenAI's AI agent super app, each with real-world use cases, so that by the end, you know exactly [music] what it can do and where it fits in your workflow. 5 00:00:37,924 --> 00:00:39,853 Let's get it fits in your workflow. 6 00:00:39,853 --> 00:00:40,870 Let's get started. 7 00:00:40,880 --> 00:00:42,551 So, this right here is Codex. 8 00:00:42,551 --> 00:00:47,961 This is a clean interface for AI agents that can fully control your computer. 9 00:00:47,961 --> 00:00:55,998 At first glance, it kind of looks like ChatGPT or Claude, because you can create a chat, but they're not exactly the same. 10 00:00:55,998 --> 00:01:02,164 When you chat on ChatGPT or Claude and upload files, those files are actually stored in the cloud. 11 00:01:02,164 --> 00:01:10,267 With Codex, all of the files that you upload to Codex or that you create with Codex are stored on your computer. 12 00:01:10,267 --> 00:01:14,870 Codex is made to do any task that you might want to do on a computer. 13 00:01:14,880 --> 00:01:17,470 You can create a motion graphics video. 14 00:01:17,480 --> 00:01:24,103 You can create beautiful landing pages, and directly inside Codex, you can generate images that you can place in your site. 15 00:01:24,103 --> 00:01:29,270 On Codex, you can also create more complex games and 3D simulations. 16 00:01:29,280 --> 00:01:34,464 You can also create mobile apps with a front end and back end with a professional design. 17 00:01:34,464 --> 00:01:38,056 You can also create desktop apps in just a few prompts. 18 00:01:38,056 --> 00:01:45,767 You can ask GPT 5.5 to create you an Excel sheet after doing a ton of research, and it can create spreadsheets with multiple slides. 19 00:01:45,767 --> 00:01:59,254 It can also create any type of Word doc with many different charts, and you can also create presentations directly inside Codex and export them to Canva or any other tool you want. 20 00:01:59,254 --> 00:02:06,005 And I haven't even mentioned yet that Codex can fully control my computer, and it can also control the browser. 21 00:02:06,005 --> 00:02:08,248 But, this is something we'll talk about a little bit later. 22 00:02:08,248 --> 00:02:18,265 As we go through the main seven different capabilities of Codex, you'll realize that it is truly a super app that does any coding task or any knowledge work task. 23 00:02:18,265 --> 00:02:19,723 Let's not waste any time. 24 00:02:19,723 --> 00:02:22,012 Let's hop into capability number one. 25 00:02:22,012 --> 00:02:26,089 So, the first capability that Codex has is full file access. 26 00:02:26,089 --> 00:02:35,630 You see, when I use ChatGPT, all of the files that I give to ChatGPT or that ChatGPT generates are stored in the cloud. 27 00:02:35,640 --> 00:02:42,795 However, when we use Codex, all of the files that are created or the files that I give to it are stored on your computer. 28 00:02:42,795 --> 00:02:48,299 And the agent inside Codex has full access to your computer. 29 00:02:48,299 --> 00:02:49,339 Let me show you. 30 00:02:49,339 --> 00:02:54,409 In my downloads folder, I have a folder called receipts to process. 31 00:02:54,409 --> 00:02:59,069 And we just have 60 different little photos of receipts that I've added to this folder. 32 00:02:59,069 --> 00:03:04,258 I can simply ask Codex, "In the downloads folder, you'll see my receipts that I need to process. 33 00:03:04,258 --> 00:03:19,732 I want you to analyze them in an Excel sheet and create charts that helps me visualize the types of transactions and any other patterns that you notice." So, we can choose our model, which is GPT 5.5 high, and we can run it. 34 00:03:19,732 --> 00:03:28,207 And the agent, because it has full file access, it can access any file on my computer, it'll find the relevant folder and complete the task. 35 00:03:28,207 --> 00:03:35,459 And you can see here, it found the target folder, which is users Riley Brown downloads receipts to process with only 53 receipts. 36 00:03:35,459 --> 00:03:43,358 I'm going to OCR those, and so we're going to extract the text from those receipts, classify and categorize each transaction. 37 00:03:43,358 --> 00:03:49,670 Now, it's creating an Excel workbook on my computer that we can open up in Codex. 38 00:03:49,680 --> 00:03:50,266 All right. 39 00:03:50,266 --> 00:04:01,066 So, after 7 minutes, it is now done and we can very easily just open this Excel project up directly inside Code X and you can see that it has created this file. 40 00:04:01,066 --> 00:04:06,590 We can see there's a dashboard, the total spend is there's a dashboard, the total spend is 25,982. 41 00:04:06,600 --> 00:04:14,608 We see receipts, category summary, payment summary, and we can see all the different trends, the spend by payment method. 42 00:04:14,608 --> 00:04:16,344 We can see the monthly trends. 43 00:04:16,344 --> 00:04:28,142 This is an Excel sheet and because it's on our computer, if you click this down arrow, you can see open in folder and we can see the exact file location of this Excel spreadsheet. 44 00:04:28,142 --> 00:04:35,736 So, now that we know that all of the files created on Code X live on your computer, the question becomes how do you stay organized? 45 00:04:35,736 --> 00:04:41,407 And I will tell you the best way that you can stay organized inside Code X is to work in a project. 46 00:04:41,407 --> 00:04:44,270 So, you can create a chat in one of two ways. 47 00:04:44,280 --> 00:04:50,558 One way you can create a chat is if you just go to this chats category and you just hit this new chat button. 48 00:04:50,558 --> 00:04:54,674 It allows you to create a chat that just shows up here in the sidebar. 49 00:04:54,674 --> 00:04:57,449 It's not actually inside a project. 50 00:04:57,449 --> 00:05:13,591 Or, you can go ahead and you can create a project and you can always hit start at existing folder. all of my projects in my documents folder and then I will just create a new project seven capabilities cuz that's what we're talking about. 51 00:05:13,591 --> 00:05:20,349 We can create a new folder and now we see that we're creating a new chat inside the seven capabilities folder. 52 00:05:20,349 --> 00:05:28,502 You'll see here this project will show up here in the left side panel and as soon as I add a chat, you can see the chat shows up here. 53 00:05:28,502 --> 00:05:34,909 The cool part about Code X is you can multitask and you can create multiple chats at the same time. 54 00:05:34,909 --> 00:05:39,990 Here, I'm going to ask the agent to create a Word doc. 55 00:05:40,000 --> 00:05:44,790 And we're doing this within a chat inside the seven capabilities folder. 56 00:05:44,800 --> 00:05:55,150 Any document that the agent creates when it's in a chat inside a project will actually store the document that it creates in this folder on your computer. 57 00:05:55,160 --> 00:06:04,604 So, if we click these three dots here and say open in finder and we open the seven categories folder, we'll see that there's nothing in it. 58 00:06:04,604 --> 00:06:07,638 And that's because the agent is not done creating the document. 59 00:06:07,638 --> 00:06:14,306 As soon as the agent's done, it's going to put as the agent's done, it's going to put the uh document that it creates in this project. 60 00:06:14,306 --> 00:06:23,955 And as you can see here, we have this Word doc that was created and it's called learn 90% of OpenAI Codex in under 2 minutes. 61 00:06:23,955 --> 00:06:26,602 You can see the title of the folder right here. 62 00:06:26,602 --> 00:06:36,221 If we go ahead and open up finder at that location and we click on outputs and docs, you can see that that document is located right here. 63 00:06:36,221 --> 00:06:40,188 So, this is literally on my computer by default. 64 00:06:40,188 --> 00:06:45,122 And so, this video that I'm making now is called the seven capabilities of Codex. 65 00:06:45,122 --> 00:06:53,702 And if we were to create a new chat in this folder, the chat would be aware that it is starting out in this project. 66 00:06:53,702 --> 00:07:02,620 I can type at learn and see I can actually at mention any file that's created within this seven capabilities folder. 67 00:07:02,620 --> 00:07:15,830 And I can say, "Please turn this into a landing page, a good learning resource for my viewers." 68 00:07:15,840 --> 00:07:26,270 And so, I can take any document within this folder and I can just at mention it and say, "Please turn this to a landing page." And because it can control my computer and go look at all of the documents that are organized very 69 00:07:26,280 --> 00:07:29,853 easily, it can find the right document and then create a landing page. 70 00:07:29,853 --> 00:07:33,332 And the code for that landing page will exist on my computer. 71 00:07:33,332 --> 00:07:34,830 And here we go, it's done. 72 00:07:34,840 --> 00:07:41,909 We can open this up and we can see that it created a landing page based on that document that is stored on our computer. 73 00:07:41,919 --> 00:07:44,729 And let's go ahead and move on to the next capability. 74 00:07:44,729 --> 00:07:48,527 Next up, Codex has something called persistent memory. 75 00:07:48,527 --> 00:07:50,812 So, within Codex, there's two types of memory. 76 00:07:50,812 --> 00:07:54,283 There's manual memory, and there's auto memory. 77 00:07:54,283 --> 00:08:03,357 Manual memory is when you ask the agent to remember something, when you tell it, "Hey, can you remember this going forward in the future?" Let me show you an example. 78 00:08:03,357 --> 00:08:09,697 So, I made a few changes to that landing page and got it to create it in this format with this little left sidebar. 79 00:08:09,697 --> 00:08:14,688 We can scroll down, and we can automatically snap to the section that we like. 80 00:08:14,688 --> 00:08:16,873 I really like this format, and we like. 81 00:08:16,873 --> 00:08:27,670 I really like this format, and so from now on, can you please use this format whenever I ask for a landing page and I don't specify uh the styling? 82 00:08:27,680 --> 00:08:35,589 You should use this styling and remember that if there's a lot of text content to use this table of contents. 83 00:08:35,599 --> 00:08:47,335 So, I can simply just ask the agent to remember this, and it's automatically going to add it to the agents.md file, which is where you can see here, search for agents.md. 84 00:08:47,335 --> 00:08:50,865 This is where it's going to store this information for later. 85 00:08:50,865 --> 00:08:56,710 And so, you can see here, the agent updated its manual memory, which is the agents.md file. 86 00:08:56,710 --> 00:09:00,806 If we click on this, here are the things that I've asked it to add in the past. 87 00:09:00,806 --> 00:09:02,773 Here's the what it just added. 88 00:09:02,773 --> 00:09:12,112 It says for landing pages that are made for learning purposes, it says use this text first format, um and then it kind of describes the style that I like. 89 00:09:12,112 --> 00:09:21,000 This agents.md file is a living document that gets updated over time that acts as the manual memory. 90 00:09:21,000 --> 00:09:30,859 But, there's also a different type of memory that you should never and this is an auto memory feature that Codex kind of keeps updated automatically. 91 00:09:30,859 --> 00:09:36,287 And just like the agents.md file, this is all stored in a file on your computer. 92 00:09:36,287 --> 00:09:48,757 If we go to Codex and hit command N to create a new chat, please tell me about what you have in the and then Codex / memories folder. 93 00:09:48,757 --> 00:09:53,516 I want to understand what you know. 94 00:09:53,516 --> 00:09:56,031 Also, open that file. 95 00:09:56,031 --> 00:10:00,106 And you can see here it gave me the path to this file. 96 00:10:00,106 --> 00:10:02,525 We can go ahead and open this up. 97 00:10:02,525 --> 00:10:05,214 And this is a document you should not touch. 98 00:10:05,214 --> 00:10:10,234 You can just kind of observe it to see what the agent observes about you. 99 00:10:10,234 --> 00:10:13,720 And so every few weeks I'll actually go through this and take a look. 100 00:10:13,720 --> 00:10:19,380 And this actually gives me a nice little summary of all of the different tasks that I've asked my agent to do. 101 00:10:19,380 --> 00:10:23,711 And it can be useful when helping other people build out similar workflows. 102 00:10:23,711 --> 00:10:27,750 I do not recommend making manual changes to these memories, right? 103 00:10:27,760 --> 00:10:36,072 Just let the agent store the memories however it wants to because the agent has a skill that keeps these updated and it will get better over time. 104 00:10:36,072 --> 00:10:39,457 The agents.md file on the other hand is your manual memory. 105 00:10:39,457 --> 00:10:41,520 This is meant for you to keep it updated. 106 00:10:41,520 --> 00:10:45,993 You can tell the agent to update it or you can manually update it if you want. 107 00:10:45,993 --> 00:10:50,710 The third huge capability that Codex has is plugins. 108 00:10:50,720 --> 00:10:54,004 And so plugins are basically just Codex connections. 109 00:10:54,004 --> 00:11:02,856 They are installable, reusable bundles that connect the OpenAI Codex AI agent to external tools, apps, and workflows. 110 00:11:02,856 --> 00:11:09,174 And this allows them to have other functionality and they can connect to all of the tools that you use. 111 00:11:09,174 --> 00:11:15,659 And so if you go to the plugins tab, with two clicks I can add Slack and I can add Gmail. 112 00:11:15,659 --> 00:11:22,216 Once you've added Gmail, and you can see here this plugin actually comes with some skills. 113 00:11:22,216 --> 00:11:27,497 So there's a Gmail skill and an inbox triage skill that is part of this plugin. 114 00:11:27,497 --> 00:11:33,611 Right now, I think there's over 100 different plugins that allow you to connect Codex to the tools that you already use. 115 00:11:33,611 --> 00:11:35,233 So, let's go over an example. 116 00:11:35,233 --> 00:11:43,327 So, I created a new project, which is a folder on my computer called brand deals, and I'm going to say, "I want you to look at my email from the past 2 weeks. 117 00:11:43,327 --> 00:11:53,770 Find all the brands offering to do paid promotion, do research on all of them, and put them in a table with relevant notes." And then I can type the at sign, and here I can type in Gmail. 118 00:11:53,770 --> 00:11:59,177 All of the plugins show up in this menu, so we can very easily at mention the plugins. 119 00:11:59,177 --> 00:12:02,799 And this is a quick way to see which plugins that you have access to. 120 00:12:02,799 --> 00:12:08,550 And I really like using this menu, and then we can go ahead and click send. 121 00:12:08,560 --> 00:12:16,566 And now Codex will search through all of my recent emails because I've given it access via the plugin, and it will get back to us. 122 00:12:16,566 --> 00:12:23,597 This is taking about like 5 minutes so far, and I have another idea for a task I want an AI agent to do. 123 00:12:23,597 --> 00:12:28,701 So, I can very easily just hit this new message button, and I can type out exactly what I want. 124 00:12:28,701 --> 00:12:33,430 So, I'm making my next video on CLIs and MCPs in Codex. 125 00:12:33,440 --> 00:12:40,950 Please look at my Notion, and so I at mention Notion, which is a plugin, and find my high-quality long-form scripts. 126 00:12:40,960 --> 00:12:43,845 Then I want you to please write a script on this topic. 127 00:12:43,845 --> 00:12:45,910 Use Excalidraw diagrams. 128 00:12:45,920 --> 00:12:48,350 This is a skill, which I'll get to next. 129 00:12:48,360 --> 00:12:49,657 We can run this prompt. 130 00:12:49,657 --> 00:12:53,980 And so now we have two AI agents working, both working with plugins. 131 00:12:53,980 --> 00:12:56,225 So, the brand deals task is done. 132 00:12:56,225 --> 00:13:09,371 If we go ahead and open up this document right here, we can see that it created file, and it went through all of my emails and wrote down the companies offering to sponsor my videos all the way down. 133 00:13:09,371 --> 00:13:18,630 It literally went through all of them and took detailed notes and said, "What did they ask for?" And also they added some research notes. 134 00:13:18,630 --> 00:13:26,991 And then I could ask it to respond to the emails because of the same way that it can read my emails, it can also send emails from my account. 135 00:13:26,991 --> 00:13:41,710 And if we go to the Notion plugin that we tested, we can see here that it created this document, and it went through my Notion, found all the scripts that I made previously, and it said, "Do you ever feel like AI coding tools are getting more powerful every 136 00:13:41,720 --> 00:13:44,150 week, but also somehow more confusing?" 137 00:13:44,160 --> 00:13:51,668 And this is literally in my voice because it went through all of my scripts, and it created this document using the Notion plugin. 138 00:13:51,668 --> 00:13:56,127 And that brings us to the fourth capability that Codex has, which are skills. 139 00:13:56,127 --> 00:14:06,410 And you can think of skills on Codex as reusable workflow recipes or SOPs that your agent can use many times over and over again. 140 00:14:06,410 --> 00:14:13,838 In Codex, if you go up to the plugins tab, you see that there's actually a subtab within plugins, which are skills. 141 00:14:13,838 --> 00:14:18,025 And in the skills tab, these are similar to plugins. 142 00:14:18,025 --> 00:14:24,012 They're more like instruction files that your agent will follow every time it wants to use one of these skills. 143 00:14:24,012 --> 00:14:28,566 So, all your skills can be found in the plugins folder in the skills subfolder. 144 00:14:28,566 --> 00:14:31,190 But, how do you actually create a skill? 145 00:14:31,190 --> 00:14:34,049 In order to create a skill, you can type a prompt just like this. 146 00:14:34,049 --> 00:14:39,171 I want you to create a skill called brand deal analysis that does blank. 147 00:14:39,171 --> 00:14:47,580 And I could enter this prompt in and create this skill, and then once that's done, in order to use any skill, you just press this slash. 148 00:14:47,580 --> 00:14:53,390 And so, I can use my Excalidraw diagram skill just by use my Excalidraw diagram skill just by typing slash. 149 00:14:53,390 --> 00:15:00,750 I can also use my YouTube researcher skill or my YouTube thumbnail skill, which we'll get to in just a skill, which we'll get to in just a second. 150 00:15:00,760 --> 00:15:04,382 These are all skills that I can quickly access by typing slash. 151 00:15:04,382 --> 00:15:08,526 These are different than plugins, which I can access by typing at. 152 00:15:08,526 --> 00:15:12,590 So, there's two main ways to create a skill in Codex. 153 00:15:12,600 --> 00:15:19,726 One is the prompt to skill, which is basically just I want you to create a skill called blank that does blank. 154 00:15:19,726 --> 00:15:27,030 This will give you a reusable instructions file, which is a skill, but I don't think it will be as good as option one. 155 00:15:27,040 --> 00:15:38,325 The best way to create a skill, in my opinion, is to use the manual workflow method, where you basically ask your agent to do something, it'll do it, and then you basically go back and forth, right? 156 00:15:38,325 --> 00:15:50,658 Tell it to create something, and say, "Hey, I want you to change it." And you say, "Get the output right." If you're not happy, you iterate more, and you kind of go back through this process, and you loop around until you're happy with the output. 157 00:15:50,658 --> 00:15:57,214 And then you reverse engineer the skill, and you will basically end up saying something like, "I'm happy with this output. 158 00:15:57,214 --> 00:16:00,147 Turn it into a skill." And I'll actually show you. 159 00:16:00,147 --> 00:16:09,330 If we go back to Codex, and you can see here, I've asked the agent to put all those paid promos into a spreadsheet right here. 160 00:16:09,330 --> 00:16:11,508 And I really like this spreadsheet. 161 00:16:11,508 --> 00:16:12,870 I think it's high quality. 162 00:16:12,880 --> 00:16:16,784 I think it's color-coded, right, by the different priority. 163 00:16:16,784 --> 00:16:18,367 This is looking really good. 164 00:16:18,367 --> 00:16:24,030 And remember, you can always full screen it to get a better look at whatever document it is that you're creating. 165 00:16:24,040 --> 00:16:27,206 And so, well, all we need to do is we need to just type this in. 166 00:16:27,206 --> 00:16:28,600 "I'm happy with this output. 167 00:16:28,600 --> 00:16:38,772 Turn this into a skill that I can use." And the agent is smart enough to be like, "Okay, this is he wants to always be able to analyze his Gmail for brand sponsorships. 168 00:16:38,772 --> 00:16:40,980 Alternate into a skill." And so, now it's done. 169 00:16:40,980 --> 00:16:47,910 It says, "I've created and validated the reusable skill called brand deal researcher skill.md." 170 00:16:47,920 --> 00:16:55,105 And we can open up this skill by uh clicking on the skill.md file, and we can actually read this over. 171 00:16:55,105 --> 00:16:59,231 And it turned our entire workflow into these instructions. 172 00:16:59,231 --> 00:17:05,081 And the AI is very smart enough at taking anything that you've done with your agent, and turning it into a skill. 173 00:17:05,081 --> 00:17:17,110 So, now if we hit command N to create a new chat, "I want you uh to please do {slash} It's called uh to please do {slash} It's called brand deal researcher. 174 00:17:17,120 --> 00:17:17,509 Right? 175 00:17:17,509 --> 00:17:21,748 So, now we have this reusable skill that we can use at any point. 176 00:17:21,748 --> 00:17:24,596 And you can see here it's using all of the same plugins. 177 00:17:24,596 --> 00:17:26,710 It's using the Gmail plugin. 178 00:17:26,710 --> 00:17:35,699 So, a skill can contain instructions to use a specific plugin because at the end of the day it's just instructions to do a simple task. 179 00:17:35,699 --> 00:17:45,423 While our research brand deal task is loading, I actually went ahead and did a create Excalidraw graphics for the seven capabilities. 180 00:17:45,423 --> 00:17:53,797 The video that we're doing now, remember this document that we created earlier which is this landing page that describes all of the different things that we're talking about in this video. 181 00:17:53,797 --> 00:18:00,937 I went ahead and I just said, "Please look at that document and make a ton of graphics on a single Excalidraw doc. 182 00:18:00,937 --> 00:18:11,950 Use the Excalidraw diagram skill and make the chart super useful." So, then the AI thought and worked for 4 minutes and 23 seconds and then it created this. 183 00:18:11,960 --> 00:18:19,261 And we can open this up and we can just And we can open this up and we can just automatically basically import this project and boom, look at this. 184 00:18:19,261 --> 00:18:23,360 It created this entire outline and I love this formatting. 185 00:18:23,360 --> 00:18:27,320 This formatting that it did with the background here, I actually really like that. 186 00:18:27,320 --> 00:18:30,357 And so, it created all of the diagrams. 187 00:18:30,357 --> 00:18:32,204 Wow, this is actually fantastic. 188 00:18:32,204 --> 00:18:39,858 It has the intro, all of the summaries, memory, plugins versus skills, skill creation. 189 00:18:39,858 --> 00:18:40,944 Very cool. 190 00:18:40,944 --> 00:18:47,121 So, now I can go back to Codex and I can say, "Wow, I really like the formatting that you did here. 191 00:18:47,121 --> 00:18:59,302 Please update the skills so that you always put them in the containers that you did and I want you to always give me a link with all of the diagrams that you create when I ask you to create multiple diagrams just like this. 192 00:18:59,302 --> 00:19:00,910 I love it." 193 00:19:00,920 --> 00:19:12,310 And so, even once you've used a skill, maybe you've used it for a while and you like it and then you get surprised by something valuable like this diagram right here or these this formatting, you can always just say, "Hey, I want you to 194 00:19:12,320 --> 00:19:18,821 always format it like this." And so, every time you use the skill is an opportunity to make the skill even better. 195 00:19:18,821 --> 00:19:21,944 Just tell your agent to update the skill to always do something. 196 00:19:21,944 --> 00:19:27,356 The next capability of Codex is built-in GPT image to access. 197 00:19:27,356 --> 00:19:33,038 So, you can generate images with the best image model in the world directly inside Codex. 198 00:19:33,038 --> 00:19:41,003 So, I created a new project called content, and here I'm saying, "Generate a product photo for my uh sweater company. 199 00:19:41,003 --> 00:19:43,296 This is our first sweater. 200 00:19:43,296 --> 00:19:49,922 I can paste an image of a sweater, and you can see here, this is the first sweater, knitted sweater that I'm making. 201 00:19:49,922 --> 00:20:02,030 Please create five images with GPT/image/2 of different models of different of different models of different nationalities wearing this sweater. 202 00:20:02,030 --> 00:20:11,910 Three of the images should have one person, one image should have three people, the last image should have five people." 203 00:20:11,920 --> 00:20:17,334 And so, we can run this, and within the content folder, it's going to create images. 204 00:20:17,334 --> 00:20:20,870 And those images will live inside the content folder once it's done. 205 00:20:20,870 --> 00:20:21,653 And look at this. 206 00:20:21,653 --> 00:20:26,136 You can see here that it's using the skill.md for image gen. 207 00:20:26,136 --> 00:20:29,500 And so, this image gen skill is built into Codex. 208 00:20:29,500 --> 00:20:35,242 And so, you can go to Codex, click on skills, and you can see which skills are built into the system. 209 00:20:35,242 --> 00:20:41,870 And you don't have to enable them, but these are recommended skills by Codex, and one of them is image gen. 210 00:20:41,880 --> 00:20:45,218 And by default, this uses the latest and best image model. 211 00:20:45,218 --> 00:20:48,481 And you can see here that it generated one of the images. 212 00:20:48,481 --> 00:20:50,310 We still need to wait for the other four. 213 00:20:50,320 --> 00:20:52,827 Okay, here, it just generated the second image. 214 00:20:52,827 --> 00:20:54,727 It just generated the third image. 215 00:20:54,727 --> 00:20:57,823 The next image should have three people in one image. 216 00:20:57,823 --> 00:20:58,830 And here we go. 217 00:20:58,840 --> 00:21:01,754 Here is number four, and here is number five. 218 00:21:01,754 --> 00:21:10,139 And now that you know that you can generate images, that brings me to the next capability of Codex, which is browser use and computer use. 219 00:21:10,139 --> 00:21:13,396 And so in order to use computer use, it is a plugin. 220 00:21:13,396 --> 00:21:16,273 So remember, you just type in at computer use. 221 00:21:16,273 --> 00:21:29,510 Now I can say, "Please open the Canva app on my computer, make a new presentation, and put each one of these images on each of the slides." So one image per slide, there should be five total slides. 222 00:21:29,520 --> 00:21:32,983 We can simply tell Codex to control our computer and it will do it. 223 00:21:32,983 --> 00:21:38,361 And as you can see here, we see list Mac apps and now it's looking at Canva. 224 00:21:38,361 --> 00:21:41,622 You can see here, it's controlling my computer. 225 00:21:41,622 --> 00:21:42,931 I'm not even touching it. 226 00:21:42,931 --> 00:21:45,006 It just created this presentation. 227 00:21:45,006 --> 00:21:46,746 It's clicking in Canva. 228 00:21:46,746 --> 00:21:47,234 Okay. 229 00:21:47,234 --> 00:21:50,438 Oh, it just ran a script, I believe. 230 00:21:50,438 --> 00:21:52,390 And so it just ran a script. 231 00:21:52,400 --> 00:22:02,336 It's looking at Canva and you can see here it created this presentation and it has all five images on the computer. 232 00:22:02,336 --> 00:22:04,649 And you can see here, this is the mouse. 233 00:22:04,649 --> 00:22:08,302 You can see the mouse outline of the computer use. 234 00:22:08,302 --> 00:22:11,081 It will move around from time to time. 235 00:22:11,081 --> 00:22:14,350 It created this presentation for me. 236 00:22:14,360 --> 00:22:21,983 So this right here is a browser and you can see that if we literally exit out of this and hit plus sign, we can see browser. 237 00:22:21,983 --> 00:22:27,171 And when we open this index.html file, it's literally opening this in a browser. 238 00:22:27,171 --> 00:22:41,430 So now I'm going to say, "Turn this into an app, then test the interface and make sure the buttons and navigation work using at browser and navigation work using at browser use." 239 00:22:41,440 --> 00:22:43,161 And I can run this prompt here. 240 00:22:43,161 --> 00:22:50,830 And now it's going to take this, turn it into an app, and then it's just going to test it by controlling the browser inside Codex. 241 00:22:50,840 --> 00:22:53,842 Okay, you can see here, it's kind of like a different color. 242 00:22:53,842 --> 00:22:55,985 Look, this is my mouse right here. 243 00:22:55,985 --> 00:22:57,596 This is the browser use. 244 00:22:57,596 --> 00:23:02,496 So the AI is actually controlling the browser and it's going to start testing them. 245 00:23:02,496 --> 00:23:08,596 So, we see that it's test start button, and the AI is now taking control of the screen. 246 00:23:08,596 --> 00:23:15,626 The first visible check showed the app controls, but the start button smooth scroll is too subtle for live verification. 247 00:23:15,626 --> 00:23:17,425 You can see here it's moving around. 248 00:23:17,425 --> 00:23:19,710 It's scrolling through the app. 249 00:23:19,720 --> 00:23:27,110 It's clicking on the different quizzes that it's created. 250 00:23:27,120 --> 00:23:31,515 Now, it's testing quiz completion, and now it just marked this a correct answer. 251 00:23:31,515 --> 00:23:41,070 So, it's making sure that all parts of the application work. 252 00:23:41,080 --> 00:23:44,590 Oh, now it tested the side panel, and now we're at the bottom. 253 00:23:44,600 --> 00:23:45,592 This is very cool. 254 00:23:45,592 --> 00:23:50,623 Anything you can open up in the browser, you can ask browser use. 255 00:23:50,623 --> 00:23:58,430 You can use the @browseruse plugin to test it directly inside Codex. 256 00:23:58,440 --> 00:24:02,846 And finally, capability number seven inside Codex is automation. 257 00:24:02,846 --> 00:24:06,407 You can create automation simply by talking to Codex. 258 00:24:06,407 --> 00:24:13,595 So, remember this Excel sheet that we created in this chat here in the brand deals project called research paid promo brand deals. 259 00:24:13,595 --> 00:24:19,990 We created this spreadsheet after it analyzed all of my incoming emails with the email plugin. 260 00:24:20,000 --> 00:24:23,093 Then, we took this output, and we turned it into a skill. 261 00:24:23,093 --> 00:24:24,902 I'm happy with this output. 262 00:24:24,902 --> 00:24:26,910 Please turn it into a skill. 263 00:24:26,920 --> 00:24:32,469 Now, what I can do is I can repeatedly do this on a weekly or daily or hourly basis. 264 00:24:32,469 --> 00:24:43,190 I can simply say, "Please do this every single Friday at 9:00 a.m., please, and update this sheet." 265 00:24:43,200 --> 00:24:46,269 What this is going to do is it's going to create an automation. 266 00:24:46,269 --> 00:24:49,390 Notice here we only see two automations. 267 00:24:49,400 --> 00:24:54,350 Here it says, "I'll set this up as a recurring automation for Fridays at 9:00 recurring automation for Fridays at 9:00 a.m." 268 00:24:54,360 --> 00:24:56,030 And we can see it directly in the UI. 269 00:24:56,040 --> 00:25:02,711 Created weekly brand deal sheet updated and if we click on this, we can see the automation details. 270 00:25:02,711 --> 00:25:05,242 We can see that at Friday at 9:00 a.m. 271 00:25:05,242 --> 00:25:07,022 We can see that it's active. 272 00:25:07,022 --> 00:25:20,762 We can see that the last run is empty because it's never run before and we can see that we are using the brand deal researcher skill to scan Gmail for paid promotion sponsorship brand deal influencer campaigns, etc. 273 00:25:20,762 --> 00:25:25,286 So created this and now if we go to the automations tab, we now see it up here. 274 00:25:25,286 --> 00:25:26,835 We can see Friday at 9:00 a.m. 275 00:25:26,835 --> 00:25:28,964 We have another one at Fridays at 9:00 a.m. 276 00:25:28,964 --> 00:25:31,772 We can click on this and you can edit it directly. 277 00:25:31,772 --> 00:25:37,412 And finally, we have a bonus capability inside Codex which is something called Chronicle. 278 00:25:37,412 --> 00:25:39,723 So this is a brand new feature within Codex. 279 00:25:39,723 --> 00:25:49,404 If we go to settings and we click settings and we go to personalization and we scroll down, you will see an option to to use Chronicle research preview. 280 00:25:49,404 --> 00:25:55,892 When you turn this on, what this will do is it'll say that it is running and this one may seem a little bit invasive. 281 00:25:55,892 --> 00:26:02,125 What this one does is it basically is always recording your screen so it has context with what you're working on. 282 00:26:02,125 --> 00:26:09,790 And so if I go to my presentation here and I just kind of scroll around in my browser, use kind of scroll around in my browser, use Chronicle. 283 00:26:09,800 --> 00:26:18,430 Uh tell me what I should add to my Codex visual presentation. 284 00:26:18,440 --> 00:26:24,670 And so it shows you here all use Chronicle skill for live screen work content then cross everything over. 285 00:26:24,680 --> 00:26:33,670 Chronicle's available so I'm checking the fresh screen state first and look at this, you can see that it's pulling up recent screenshots of my screen here. 286 00:26:33,680 --> 00:26:41,967 And so it is pulling old images and it's getting context from what I've had open on my screen recently. 287 00:26:41,967 --> 00:26:49,030 And so it's able to keep track of all the things that I'm working on and the way that you invoke it is just say use Chronicle. 288 00:26:49,040 --> 00:26:52,814 And so it says based on Chronicle, I'd add these to your visual presentation. 289 00:26:52,814 --> 00:27:03,887 A Codex super app map, a full control loop diagram for prompt files, a Chronicle demo slide, reusable skills slide, and why Codex over other tools slide. 290 00:27:03,887 --> 00:27:13,510 And so, it automatically, and I didn't give it any [clears throat] information, I didn't upload an image or give it an Excalidraw document, it just knew what was in this slide deck here. 291 00:27:13,520 --> 00:27:21,041 And it's able to understand it because this Chronicle feature watches my screen and takes screenshots constantly. 292 00:27:21,041 --> 00:27:24,953 And so, those are the main features and abilities within Codex. 293 00:27:24,953 --> 00:27:30,792 And in summary, we covered that Codex has full file control, meaning you can create, edit, and delete any file. 294 00:27:30,792 --> 00:27:36,030 It has persistent memory, and whether that is automatic memory or manual memory in your agents.md file. 295 00:27:36,030 --> 00:27:39,507 We also talked about plugins, which are built into the platform. 296 00:27:39,507 --> 00:27:42,587 It connects your agent to all of the tools that exist. 297 00:27:42,587 --> 00:27:49,550 You can create skills by taking any task that you create with the agent and then converting that into a skill. 298 00:27:49,560 --> 00:28:01,190 Your Codex agent has access to image generation, and it is the best image generation model in the world, which is generation model in the world, which is GPT-image-2. 299 00:28:01,200 --> 00:28:07,390 We also have browser control and computer use, and this allows your agent to control your computer like a human. 300 00:28:07,400 --> 00:28:14,491 The human interface, which is a keyboard, a mouse, and a screen, can now be used by agents, and it's getting better exponentially. 301 00:28:14,491 --> 00:28:15,771 And we also have automations. 302 00:28:15,771 --> 00:28:19,515 You can take any useful task that your agent does and say, "Hey, do this every day. 303 00:28:19,515 --> 00:28:20,712 Hey, do this every hour. 304 00:28:20,712 --> 00:28:21,825 Hey, do this every week. 305 00:28:21,825 --> 00:28:23,618 Do this every month." That type of thing. 306 00:28:23,618 --> 00:28:25,860 And then as a bonus, we talked about Chronicle. 307 00:28:25,860 --> 00:28:28,206 Anyway, thank you guys so much for watching. 308 00:28:28,206 --> 00:28:30,035 I hope you got a lot out of this video. 309 00:28:30,035 --> 00:28:34,520 I make videos like this every single week, so make sure to subscribe and hit that like button. 310 00:28:34,520 --> 00:28:35,310 It helps me out a lot. 311 00:28:35,310 --> 00:28:38,840 I'll see you here for the next video.