Episode Categories:
Resources:
Join the discussion on LinkedIn: Got something to say? Let us know on LinkedIn and network with other AI leaders
Upcoming Episodes: Check out the upcoming Everyday AI Livestream lineup
Connect with Jordan Wilson: LinkedIn Profile
Start Here Series in our Inner Circle Community: Join for free access
OpenAI Codex Desktop: Concrete Workflow Automation for Business Leaders
OpenAI's latest updates to its Codex desktop application are not merely incremental improvements; they represent a tangible shift in how AI is poised to power business operations—directly from the desktop. With the integration of enhanced automation, persistent memory, and native system-level operation, these advances unlock practical workflow value for business owners and decision-makers seeking to streamline processes and harness AI as an effective digital coworker.
Codex Desktop App: Operating System-Level AI Integration
The Codex desktop app—distinct from browser-based or earlier desktop ChatGPT versions—operates at the actual operating system level. Unlike standard desktop agents that can "screen jack" and require users to stop working while automations are performed, Codex runs as a parallel coworker. Multiple AI-driven agents can process tasks in the background, each with its own cursor. This native desktop integration means business users can delegate repetitive or data-heavy processes to Codex without losing real-time control of their workspace.
Workflow Automation: Concrete Use of Computer Use and App Integrations
Codex’s updated capabilities allow seamless integrations with over 90 business tools, including Slack, Gmail, Notion, Canva, Figma, HubSpot, and even Stripe and Pipedrive. Users can now automate tasks like collating trending industry news from social media, cross-referencing with internal communications, gathering additional insights from external research apps, and assembling polished presentations—all within a single workflow.
For example, automating a research and reporting sequence now involves:
Navigating to social media to extract trending industry stories.
Comparing findings with the daily company newsletter drawn from connected email accounts.
Using another AI assistant (such as Claude, via the desktop) to dig deeper for web-based research.
Compiling research into a templated, company-branded multi-page presentation using Canva—triggered directly by Codex.
These capabilities eliminate the manual labor of switching between tools, copying and pasting, or overseeing each step. Instead, Codex’s native desktop agent monitors, executes, and confirms each part of the workflow with summary feedback and error-handling.
Persistent Memory and Automated Suggestions for Smarter Workflows
One of the most substantial value-adds is Codex’s persistent memory and automation suggestion feature. Codex tracks user preferences and workflow patterns across sessions, enabling it to schedule and automate repetitive tasks at suggested times. If a manual process is detected as recurring, Codex proactively recommends setting it as an automation—helping business users convert inefficient habits into streamlined procedures.
Chronicle, a research preview feature, takes this further by providing Codex with contextual recall based on previous screen interactions. This enables prompts such as “finish what I was doing” or “update this dashboard” to deliver more context-aware, accurate outputs. While privacy and organizational approvals are necessary, especially in enterprises, the capacity for context-driven automation gives a competitive edge to organizations able to deploy it responsibly.
Codex vs. Competing Agents: Key Advantages for Business Use
Anthropic’s Claude and Microsoft’s Copilot also offer computer-use agents, but Codex’s operating system-level parallelism provides unique advantages for business users. Competing solutions commonly require users to pause their work, surrender their mouse or screen, and oversee each automation step. Codex, by contrast, allows users to work side-by-side with the AI agent, reaping productivity gains without workflow interruptions.
Unification of memory, skills, and application connections under a single agent means contextual continuity is maintained. While other solutions silo tasks—leading to fragmented experiences and a lack of cross-surface awareness—Codex operates as a single platform capable of leveraging the full range of connections and context.
Five Essential Codex Strategies for Business Leaders
Based on real-world demonstration and workflow testing, the following concrete strategies are critical for immediate business value:
Connect All Core Business Tools: Integrate Slack, Gmail, Notion, and any other daily-use apps at the outset to enrich Codex’s context and prime it for effective automation.
Run Side-by-Side Prompt Testing: Compare known workflows powered by other agents with Codex to benchmark speed, reliability, and workflow continuity.
Audit and Automate Click-Heavy Tasks: Identify and script automation for high-frequency tasks involving repetitive clicking or routine data movement, minimizing labor and manual errors.
Leverage Persistent Memory: Allow Codex’s memory to track preferences and recurring tasks to bypass setup time, especially for complex tech stacks and multi-step workflows.
Iterate and Schedule Recurring Processes: Refine automations through repeated prompt testing, then set them to run at scheduled intervals for ongoing business efficiency.
Scheduling and Error Handling: Real-World Reliability
Codex’s automation engine allows scheduling by day, week, or custom intervals—useful for regular reporting, analytics, or industry intelligence updates. Error handling in live demonstrations shows Codex's transparency in reporting failed steps, supporting rapid troubleshooting and adjustment, which is vital for business-grade reliability.
Business Takeaway: Immediate Competitive Advantage Through Codex
By moving AI-powered automations to the operating system level and unifying context, tools, and persistent memory, Codex empowers business owners to automate knowledge work with reliability and precision. The barrier to entry is significantly lowered—no coding experience is required, as plain language and existing app connections dictate workflows.
Organizations that deploy Codex today stand to gain an operational advantage, integrating AI as a true parallel coworker while competitors continue relying on manual coordination and fragmented toolsets. This practical, accessible automation is available to any organization that opts in, providing a head start—so long as there is willingness to invest some time in setup, workflow audit, and iteration.
For those seeking to modernize processes with AI on the desktop, Codex’s latest feature set is a concrete step beyond chatbots and workflow bots, bringing system-level AI coworking to the forefront of business productivity.
Topics Covered in This Episode:
- OpenAI Codex App Major Update Review
- ChatGPT Super App Preview and Roadmap
- Autonomous Desktop AI Agents Explained
- Codex vs Claude Computer Use Comparison
- New Persistent Memory & Automations Features
- Integrated Plugins: Gmail, Slack, Atlas, GitLab
- Multi-Agent Parallelism on Codex Desktop
- Step-by-Step Codex Workflow and Demo
- Top Five Tips for Codex Power Users
- Claude Desktop Fragmentation vs Codex Unified Experience
Episode Transcript
Jordan Wilson [00:00:17]:
Maybe you noticed the OpenAI updates to codecs in the middle of last week, but chances are you either didn't see them, you didn't really test them, or maybe you forgot about them already because in the AI space, you assume feature updates like these are a dime a dozen. But in this case, that assumption would be a gargantuan mistake. Why? Well, I think that what OpenAI released in its updated codex app actually represents one of the largest changes in how AI works that we've seen over the past three years that I've been covering it daily. And if you listen to this show, you know I don't say things like that lightly. So why is this random codex update potentially one of the biggest shifts in the modern AI era? It's not because that this is an official preview of OpenAI's forthcoming super app, where it's kind of forging three of its different desktop apps into one. No. It's more about what this update represents. This is the first true autonomous coworker that you can actually work with.
Jordan Wilson [00:01:25]:
So it is our weekly putting AI at work on Wednesday show, and we're going hands on with what will likely be the future version of ChatGPT in the latest codex release from OpenAI. So before we get started, here's the big picture. ChatGPT is going through a huge change, and you can get a sneak preview of the future super app in today's codex. And overall, if we look at the bigger picture about what's going on, it's undeniable. Both the consumer and the enterprise momentum is moving to autonomous operations on the desktop. Right? Whether you wanna talk about things like OpenClaw, one of the most popular open source, well, the most popular open source, piece of software ever, or more enterprise offerings like what you have from Claude. Everything's moving toward the desktop. And speaking of Claude in Anthropic, they actually jumped off to a big early lead in that very category, both with their Claude code, you know, when they release it for the desktop and what it ultimately led to.
Jordan Wilson [00:02:33]:
Well, Anthropic noticed that people were using its Claude code to do nontechnical things, which led them to create Claude co work. Right? Now we've seen a whole bunch of variations of this co work from Microsoft with their co pilot co work, all the way to Google's upcoming rumored agents, their updated agents. But what we've seen is this shift to desktop autonomous work. And, ChatGPT has been building their super app in plain sight to take advantage of those actual things. And they aren't saying, here's a preview of the super app. No. They've just been rolling it out into codecs. And the cool thing is is you can start using it today, the future version of ChatGPT.
Jordan Wilson [00:03:19]:
If you can just get over the word code in codex and stick with me as I show you how nontechnical business leaders like you and me can use it, and all you really need is a paid Chad GPT plan, nothing else. So on today's show, stick with me for the next probably thirty minutes because we're gonna go hands on, and that one could get crazy. Alright. But here's what you're gonna learn. You're gonna learn how to use codex and why the traditional chat GPT interface may change forever. You're gonna know why Claude is actually way behind in the desktop race by being first and also really good. You're gonna know how to leverage OpenAI's, version of their desktop, software. And you're also going to know the five essential steps to go from codex beginner to novice in no time.
Jordan Wilson [00:04:07]:
Sound good? Sound like a plan? Alright. Let's get after it. Welcome to Everyday AI. My name is Jordan Wilson. If you're new here, this thing is an unedited, unscripted, live daily, live stream podcast in newsletter, helping everyday business leaders like you and me keep up with the non stop barrage of AI updates coming at us. We just gotta duck our heads. Don't worry. I spend literally my entire day every day seeing what gets thrown at the wall, what sticks, what's worth it, what's not.
Jordan Wilson [00:04:34]:
I tell you how to use it. Alright. So if that's what you're trying to do, make sense of everything that's going on to build to grow your company or career, it starts here. But make sure you go to youreverydayai.com. Sign up for the free daily newsletter. We're gonna be recapping the highlights from today's show as well as keeping you up to date with all of the other AI news and updates that you need to know to be the smartest person in AI in your department or company. Alright. Did you guys know that there's this new super app thing? Right? OpenAI after, you know, months of rumors, they did, confirm it recently that they are working on a super app, but it's not out yet.
Jordan Wilson [00:05:12]:
But they essentially confirmed that, well, what they're rolling out in previewing in codex is the foundation for their super app. So, make sure if this episode is helpful, we're gonna eventually do a co working type, cohort or a co working, class, right, where we go over Claude co work, but we're also gonna be going over, codex or whatever it's called at the time. So, if you do want early access to that, it's gonna be free. I don't know if it's gonna be a live cohort, or a recorded class, but just make sure to, repost this show on LinkedIn. So if you are listening on the podcast, thank you. We always put the link to today's show, via the LinkedIn post. So make sure to go repost that, and I'll make sure that you get early access to that cohort whenever we do launch it. Today's gonna be slightly less hands on, but we're still gonna do it at the end, and it could go terribly wrong, but we'll see.
Jordan Wilson [00:06:07]:
So not only do I think this new codex update changes what's possible, but I also think it changes who can use it simply. And what I mean by that, I think, well, I've been very vocal about how good codecs is since the app came out in February. My gosh. It seems like it's been out for years. It's running on my computer. If my computer's open twenty four hours, it's running twenty four hours a day. But I do I do think you had to have a baseline technical understanding, not of code, but you had to be comfortable around things like GitHub and work trees. Right? But I think now we're past that with some of these recent updates.
Jordan Wilson [00:06:50]:
So that really changes who can use it and who can take advantage of this today. So first, let's go over what is actually new. So, yeah, to hit rewind, if you have a paid chat GBD plan, that's all you need. So you download this. This is a desktop program. Alright? It's different from their Atlas browser. It's different from the chat g p t app. It is codecs app.
Jordan Wilson [00:07:12]:
And the big difference is, well, when you're setting it up and you go through permissions, we're not gonna go through that a lot in-depth today, but you essentially set it up to where it can both read and write certain folders on your desktop. You give it access, and depending on if you're on Mac or Windows, there's different accessibility settings that you enable where it can go perform actions much like a human would. So here's what's new with the update that codex, sorry, that OpenAI just rolled out to the codex app. So now it essentially to simplify it, it works at the operating system level, not the user interface level. So you can still see what it's doing on the user interface, but but it actually works in the background. And that part right there is huge. We're gonna be explaining that a little bit and how that's different from other computer using agents like computer use in Claude code or computer use in Claude co work, but that is the big step change here. And the the what goes along with that is it has its own independent cursor on Mac.
Jordan Wilson [00:08:09]:
Right? So, you can literally see that, and we'll see in the demo, and that part is huge as well. You can also with those new changes, you can also have multiple agents that run, simultaneously. It doesn't screen jack or interrupt your work, and that's why I say this is the first true agent that you can literally work with. Right? And that part I'm gonna touch on a little bit later as well. Whereas clause computer use requires you to kind of stop working because it takes over whatever you're doing. So some new, some other new features, in codex. Well, it now has access to the new images to model. Alright.
Jordan Wilson [00:08:47]:
That open AI released on Tuesday. There's an integrated web browser that lives inside of codex as well as an integrated file viewer. Those two things are huge. We're not we're not gonna be touching as much on the, the technical side. Right? But in terms of previewing, debugging code, different web apps that you're working on, whatever, to be able to do that inside of an actual, in app browser is huge. The same thing with, you know, having an in app file browser. It just makes things more reliable and faster, and ultimately, that makes things more token efficient. Right? Also, there's, 90 plus new plugins including, Atlas and GitLab.
Jordan Wilson [00:09:27]:
You know, there's all this usual Gmail, Slack, all that good stuff. And then Chronicle, which isn't always on memory. I do believe you have to be on the pro plan, the $200 a month pro plan for that one. We'll see if they roll it out laters, later. But essentially, this is a version of, like, Windows recall. More on that later. But, yeah, a very viral Windows recall that, you know, was under scrutiny for like eighteen months. Yeah.
Jordan Wilson [00:09:50]:
Codecs just literally rolled it out and I don't think anyone really noticed. Alright. Also what's new and updated is the memory and automation. So there's now persistent memory that remembers preferences and workflows across sessions. Alright. Codecs can also schedule future work across days or weeks. Alright. That part's not necessarily new, but it will suggest sometimes schedule tasks for you, because now it will proactively suggest automations based on previous actions.
Jordan Wilson [00:10:18]:
So if it sees that you're doing the same thing manually over and over, it's essentially gonna give you a nudge and being like, hey. Why don't you set this up as an automation? Here it is for you. Do you wanna run it? So not only do we actually have a true autonomous coworker, in the computer use, but we actually have a proactive assistant that is suggesting things when it sees us working too much manually over and over. Right? It's when you're hitting your head against the wall and someone's like, hey. Maybe you should stop hitting your head against the wall and do this instead. Right? That's essentially what we have. Availability, like I said, it's available right now on Mac and Windows desktop. Some features are not yet available for Windows users, but most are.
Jordan Wilson [00:10:58]:
It does require any, paid chat GPT plan. And that part's important because, this might have already been squashed, but, like, late, Tuesday. So last night, there's all this back and forth of anthropic may have removed quad code from their base paid plan. Alright? So we'll see if they actually get that solved. It'll be in today's newsletter. So it's looks like it's still working itself out. But regardless, OpenAI's leadership came on and said, hey. You're always gonna have access, to chat g b t, or sorry, to codex on any paid plan.
Jordan Wilson [00:11:33]:
Alright. So now let's go through some of these features a little bit more in-depth, and set the context here because, you know, this yes. This is our AI at work on Wednesdays. I tried to describe and show you in-depth one feature, but I think that you have to understand the context and why this is important. Because I'm guessing the majority of people listening to this, you're you're saying, okay. I use chat GPT in the browser. Right? I tried the chat GPT desktop app. It wasn't that much better.
Jordan Wilson [00:11:59]:
It wasn't that much different. Like, I'm good. Right? Or, you know, maybe I'm using Claude code or Claude co work, and I love it. But you have to understand here. This is where the puck is headed with the super app. So Tivo, the head of, codex said in a recent interview. So I'm I'm quoting this from an in gadget article. So he says, we're building the super app out in the open.
Jordan Wilson [00:12:23]:
The release is about developers. In the future, we will broaden it up to a wider audience. Until then, and that's end quote. Until then, the latest version of codex offers developers multipurpose AI agents that can work across a larger surface area while being more proactive in practice that translates to a host of new capabilities starting with computer use. Alright. Here's what that means. Right? You essentially have these three different desktop apps. And until codecs came along, I was using all three of them every day.
Jordan Wilson [00:12:53]:
Right? The chat g p t desktop app, which is was not very, different than the web version. There were some different things, you you know, you used to, kind of be able to quickly give, you know, Chat gbt access to different, apps that were running on your computer. It It had kinda like a meetings mode, but some of those things got phased out. So the actual ChatGPT app wasn't that difference than different than what you could access on the web. Then they had their, Atlas app that is their agentic web browser, which has been really great. And then you had the codex. So codex is actually a year old, but the, the the desktop version just came out in February. And now, yeah, the stats already, outdated here.
Jordan Wilson [00:13:35]:
Moves quickly. So now, OpenAI says that it's already used by 4,000,000 people right now. But that is the past. But now, like I said, they are treating codex as at least a preview of the future super app. Who knows? Maybe that super app will be called the codex. Maybe it'll be called something else. I hope it's called something else because I think people look at the word code and they're like, it's not for me. Trust me.
Jordan Wilson [00:14:01]:
It is. But here is the big takeaway that I cannot emphasize in my life. This is the shift from the user interface level interface to the operating system level autonomy. Right? Because most computer using agents, right, whether you're talking about Claude Co work, CloudCoord, there's a dozen or so kind of popular, desktop computer using agents. For the most part, they all run the exact same. They literally screen jack your computer. So what that means, you could be working on something, and I've complained about this for weeks. Right, probably months on the show.
Jordan Wilson [00:14:39]:
You can be working on one thing, try to work, co work with Claude, and, well, you can't co work with Claude because it would take over your mouse. It would take over your screen, your browser tab, whatever it was you're trying to work on. So although, yes, very impressive, very viral moments for computer use, but it wasn't a true autonomous coworker. It was just an autonomous agent or a semi autonomous agent that needed your actual computer. But now with the, codex update, you have that background parallelism. So it operates natively within the Mac OS operating system. So it understands the user interface, but it actually works. Yes.
Jordan Wilson [00:15:20]:
It does. It can work across the user interface, but it can simultaneously work at the operating system level. So literally multiple cursors, multiple agents working on your computer while you're working on it as well. So it can both test, you know, front end app changes silently. It can use in app web browser and file browser to test those things. It can create images via the new images to, feature. And then it can, you know, if you are coding, it can, you know, review PRs simultaneously. So and that's why it's a big deal.
Jordan Wilson [00:15:58]:
Because whether you're looking at something like OpenClaw, right? OpenClaw, if you're running it safely and using it the right way, it should have its own computer. But then it seems like you're so constantly having to monitor it. Claude code, I already talked about the downsides. I love Claude code, Claude co work. I can't use it, when I'm working. So for me, it wasn't a true autonomous co worker. It was a worker that sat at my desk. Right? And I didn't like that.
Jordan Wilson [00:16:25]:
You know? Because the only time Claude co work could do any work for me is overnight. And right at that point, you kind of risk things. And that's why I think it's important to dissect this a little bit, because things come up all the time. Right? And things obviously still come up, you know, in codex. But the difference is when you can share your computer and share your space with this autonomous agent, if something comes up, you don't have to stop what you're doing and you see it. Right? So many times. Right? I would think I'd be kicking off. Oh, here's a great, you know, session on Claude Cowork on Claude Cove that, you know, hopefully, you can get a lot of work done overnight.
Jordan Wilson [00:17:00]:
And sure enough, you know, twenty, thirty minutes in, I'm asleep. Right? So it's in the other room, and sure enough, an error pops up or a permission even though I'm on dangerously skipped permissions. Right? Which is a bummer. So, I mean, you still could run into that with, with codex. Right? In terms of trying to get it to do, you know, long range work overnight or something like that. But this is something you can literally have someone else working with you. And when you do need to check on something or approve something you can't. So in, in terms of a true unlock of consistent productivity, this is the first true autonomous AI agent that I think everyday people can benefit from.
Jordan Wilson [00:17:44]:
Alright. And then we didn't even get into the, the windows recall feature that is essentially just, chronicle. So let me just quickly touch on this. We're not gonna actually demo this because it's a little, I don't wanna be accidentally doxing people. Right? So I'm very careful on the live demos that I do. So, the chronic chronicle is a research preview, but, I'm reading the definition here. So chronicle is an experimental feature that augments memories with context from your screen. With Chronicle enabled, codex references what you've seen to provide more helpful contextual responses to prompts like finish what I was doing or update this dashboard.
Jordan Wilson [00:18:22]:
There's obviously, you know, ongoing costs in terms of, you know, your kind of, rate limits. It does cost more because it's essentially taking, persistent screenshots and committing those things to memory, which is both really cool, but there's obviously privacy concerns around that. So I wouldn't recommend that unless you, you know, if you do work in a larger organization and you've gotten codex approved, you might wanna run that one up the food chain if you do have approval, to use it. You know, obviously, use your own best caution if you are, you know, a business owner, entrepreneur, or whatever. But regardless, that is a huge unlock. Alright. Now I'm gonna quickly go over the five essential steps to get the most out of these codex updates before we go live and do a demo. Alright.
Jordan Wilson [00:19:05]:
So number one, connect your tools before you do anything else. Right? So whether that's Slack, Gmail, Notion, 90 others. Right? There's custom MCPs, which are great as well as computer use. And when you combine computer use, you'll see well, you could essentially any other desktop that or sorry. Any other program that you have downloaded on your desktop, it essentially looks like and functions like an actual app. Right? So it's not just like this loose computer use. It it's strange. I don't know what kind of witchcraft, the team at OpenAI, had brewing in the pot for this one.
Jordan Wilson [00:19:41]:
But even just the the the the use the how this computer use interacts with your computer and interfaces with it, I don't understand the technology. It is mind baffling, and it's just kind of fun to watch. Alright. So the reason why this is the first step is, you know, this if you've taken our free prime pump polished course, if you've heard me talk context over everything. Right? Not just context, but, you know, committing that to memory, cross chat memory, things like that, chat history. Right? But the more context from day one means smarter suggestions immediately and the ability to schedule things. Number two, pour your top three Claude cowork prompts and run them side by side. Right? Don't take my word for it just because I've done my own testing.
Jordan Wilson [00:20:27]:
Right? I say this, don't believe benchmarks, run your own use cases. Find the true value, maybe three things that you are getting great results out of co work or cloud code, and maybe three things that you haven't been able to. Run those things side by side, in codex, to see if it's going to be the best for your needs. Number three, audit every single workflow that requires clicking or browsing and test it in codex. Here's I don't think people realize just the amount of mundane tasks. Right? And here's here's a huge cheat code. I don't know if I've ever shared this secret in 750 plus episodes. One thing I love doing this, doing this, or how I can do this is I record a quick video.
Jordan Wilson [00:21:12]:
I'm very descriptive in what I'm doing, and then I upload that to Google's AI studio. You can use one of the flash models. Right? But the thing is Google's AI studio can see video and say turn this into a very descriptive, step by step tutorial according to both what is said in the transcript and what you see on screen. Right? Share with it, you know, codex or cloud code or whatever you're using, and it's gonna write you up a great little manual FYI. But Claude's computer use as an example locks you out of your own machine. Right? Because you can't really use it. Codex runs in the background, so you need to audit anything that you do that takes up time. Right? If you do the same little process, right, a bunch of clicking, context dragging, thirty minutes every single day.
Jordan Wilson [00:21:56]:
That is one of the first things I would I would look at. Is it low risk, high, you know, high scalability? Those are the things if you're doing them routinely, you should audit that workflow. Number four, let memory replace your setup time. Right? Stop reexplaining your preferences every session. So codex does and can learn your stacks tech stack and workflows once and then carry it forward automatically. Like I said earlier, the combination of that persistent memory plus chronicle plus suggested automations is, I think, one of the stickiest combos for power users. I've been loving it so far. And then last but not least, schedule one recurring task after iterating.
Jordan Wilson [00:22:36]:
I I I say this all the time. You should be studying the chain of thought. I'm gonna show you here a way to get a little bit more out of codex, but you need to understand how these systems work. And sometimes they give you more context and, you know, one app versus another. Right? You're gonna get way more context, on how, you know, GPT five four pro works inside of chat g p t versus, you know, how it works inside of codex. So I'm gonna show you some tricks as we do this live, but you should always be iterating, because generative AI is generative AI. I've run the exact same prompts verbatim two or three different times in codex, more on the, general side and getting very different results. So, by by by doing it multiple times and really, trying to look as as much chain of thought as possible, you can see where things may or may not go wrong and then make adjustments, in your prompt.
Jordan Wilson [00:23:27]:
And in doing that, all you're doing is so you can then set a schedule and I'll show you how to do that as well. Alright. This y'all I've done hundreds of live demos. This one might be the trickiest one. So, live stream audience, bear with me. Podcast audience, you can always go to our website at youreverydayai.com. We have all the video versions up there. So, yeah, hopefully, this works.
Jordan Wilson [00:23:51]:
Live stream audience, let me know if you can see my screen. Let's see if we can get this to work. Alright. So, there's a very good chance this stream could cut out. We'll see, because I am gonna use computer use, and I'm gonna tell it to launch a new tab. So I hope that it's gonna work on the tab that I have open, but I don't know if I can describe this, but to switch over to share that part of my screen, I have to click on, you know, I'm using StreamYard. So it's usually gonna see the active window and then open a new tab. So hopefully I don't lose everyone in the middle of this, but, let's go for it.
Jordan Wilson [00:24:30]:
Alright. So I will quickly describe kind of this prompt that I'm running. Alright. And I do have it up here on my screen, and apologies. I'm gonna read it all, but I'll try to go fast. And you and you'll see for our live stream audience, there's certain things that are lit up. Right? So essentially, you know, there's all kinds of different commands in the interface, and I'm gonna go over this interface later. But essentially, when I click the app button, I can at tag, or call on these different tools or apps.
Jordan Wilson [00:24:57]:
So that's the things that are kind of colored in. That's what I'm calling to those apps for. So here's what we're doing, and this is again, I want you don't get caught up in the weeds of my very specific use case. I want you as I go through this to think of your specific use case. Where can you, pull together all of these different apps and tools that you use, combine them with computer use, combine them with a super smart brain, and start to schedule and repeat some of these workflows. In context, I am using the model g b t five three codec spark. I love it, especially for computer use because it is faster. So it is not nearly the most powerful model.
Jordan Wilson [00:25:34]:
I would probably get way better results if I didn't use the spark model, but it's faster. And I kinda do want you guys to see how fast computer use is because computer use on cloud is slow, slow, slow, slow, slow doing simple things, you know, like going to a website, finding something on a dropdown menu, navigating to one page over and summarizing something might take, like, ten minutes. Right? So we'll see how long a very drawn out, kind of prompt here goes. So here's what I'm saying. Please navigate to Twitter in the open browser using computer use. Click on the home tab and find five AI stories that are trending. Don't do any searches or filtering. Just see what people are talking about on the home screen and scroll a bit.
Jordan Wilson [00:26:20]:
Then using my connected Gmail app, find today's everyday AI newsletter sent from info@youreverydayAI.com and see if any of those, I should probably say those AI news stories were covered in that day's newsletter. And I should say in today's newsletter, find the one most interesting topic based, actually, I don't know if today's would work in yeah. In that day's newsletter, find the one most interesting topic based on what you know about everyday AI and what our audience may want to know. Again, I'm using my, memory persistent both saved and persistent memory. Then I'm saying then with computer use, open the Claude app on my desktop. Alright. So you'll see here, Claude is showing up as if it was a connected app, but it's actually not. There is no Claude app.
Jordan Wilson [00:27:12]:
It's showing up like that because it's because computer use, it sees that it's an app. Right? So I don't even know how that works. It's amazing. Anyways, open the Claude app on my desktop. Do not use the Claude Chrome extension. You must launch the connected Claude app on my desktop. Let me just do that one more time. Here we go.
Jordan Wilson [00:27:32]:
The Claude app. Where'd it go? Claude app on my desktop. Sorry. Once the app opens, search for more information on that story you selected, making sure to specify information from today's date. You should instruct it you should instruct Claude, to pull information from the web for that date. Searching in Claude may take two to three minutes, so be patient and wait for Claude to respond. Depending on how fresh the AI news is, example, ten minutes versus ten hours, there may or may not be information on the web. If your first option out of the three does not turn any reputable or verified results and additional information, then move on to the next AI story that you found until you found one that returns enough information.
Jordan Wilson [00:28:13]:
Lastly, take that information from Claude and then use the connected Canva app and create a simple yet detailed three page explainer on the topic. And then I'm just saying, you know, go through, do this step by step, don't stop, all that good stuff. Alright. So I'm gonna hit go on this. I'm gonna very, very quickly, click over it. Let's see if I can do it. Okay. We'll see if this works.
Jordan Wilson [00:28:33]:
I'm gonna very quickly click over and hopefully I don't lose everyone. Great. Alright. Let's see. Let's see what could go wrong. Alright. So again, I hate when people do this. Oh, look.
Jordan Wilson [00:28:47]:
I'm not using hands. Right? But in this, I'm not using hands. So anything you see happening on my screen, will hopefully be, codex. So, right now, I I I just want people to be able to hopefully see the cursor. Hopefully, this works. Right. So on my screen, I do have Chrome open. There you go.
Jordan Wilson [00:29:05]:
There's the, look at that magical cursor. So, codex has its own cursor. You can see my cursor on the screen. So it opened a new tab. It went to, you know, Twitter or x.com. It's clicking the home. You'll see how my gosh. If you've ever used any, computer use, products, you can instantly see how fast this is.
Jordan Wilson [00:29:27]:
This is just lightning fast. So right now, even though I told it not to go on the for you, alright, it went to the for you. Alright. So now now I'm gonna have to this is interesting. Right? It's opening. Right? I'm hoping it's it's not gonna, you know, accidentally dox myself or anyone else. So far, so good. It actually opened my g mail dot com in the browser, not my Gmail app, even though I told it to, but that I should have clarified, probably multiple times.
Jordan Wilson [00:29:57]:
Do not go to, you know, gmail.com, even though I did say use the Gmail app and hit at on the app. Right? When I ran this in five four, it didn't happen, but, five three codex is much faster. Alright. So I'm actually gonna switch over here and kind of read what we have going on. Because one of the things that I told it to do, was to, very much describe what it's kind of doing step by step. Because what I found, is if you don't do that, you only really get a sentence or so, and then it's hard to iterate and improve that prompt. Because the ultimate goal here of what we're trying to do is we're trying to get a consistent result that gives us a good and verifiable output. And the reason why is because I want to turn this into a schedule, something that I can say as an example will run every single day at 7AM.
Jordan Wilson [00:30:50]:
So I wake up and a ton of work can be done, or this could be the first step in a series of schedules. Right? So I wanna make sure that I can get consistent outputs reliably. So I already saw one thing is even though I tagged the Gmail and told it to use the connected Gmail app, instead, it went to gmail.com, which I did not want it to do. Anyways, let's see. It says error running remote task. Your input exceeds the cut. Okay. Yeah.
Jordan Wilson [00:31:16]:
Fun. Let's try this again. Yay. Live demos. Alright. Let's try it again. Here we go. So what, what I'm gonna have to do here is, is copy this.
Jordan Wilson [00:31:26]:
So bear with me. And if you look at the left side, inside codecs, right? You see only one has an error sign. Obviously it was the one that I did live. Right. I did this three or four times beforehand, and everything worked perfectly. So, you know, the demo demon's fun. Alright. Let's do this one more time.
Jordan Wilson [00:31:43]:
So bear with me. I'm going to have to click the app button, a couple of times. Alright. So, give me a second. So for this computer use, I'm gonna have to click that and computer use. We'll see if I can do it. Alright. And then I'm gonna say Gmail app, and then I'm going to tell it this time, then using my connected Gmail app.
Jordan Wilson [00:32:05]:
And I'm going to say, do not use gmail.com or the browser. You must use the connected app. Alright. Then it's gonna say five today's everyday, lose letter. There we go. Let's make sure. Sorry. Y'all nothing more.
Jordan Wilson [00:32:25]:
I love that's troubleshooting a Gentic AI live. Alright. So all I'm doing is I'm just retyping these. So when I paste it in, it doesn't carry over kind of the at mentioning or at tagging. So that's what I'm having to do. You know, I don't know. Live stream audience, tell me tell me, what are your plans for this this afternoon? Right? Let's let's let's keep everyone else, entertained. What what big AI project are you trying to knock out? Alright.
Jordan Wilson [00:32:51]:
So let's make sure I think I had one more. I think I might Canva one here. There we go. The Canva app. Alright. Let's see. Let's hope this works now. Let's hope this works.
Jordan Wilson [00:33:04]:
Alright. I'll just do that again. I don't know if mentioning the same app multiple times is eating into the context window. I'm not sure I haven't tested that, but that's obviously something I'm gonna try to do. Alright. Let's hope this doesn't fail. Alright. So same thing.
Jordan Wilson [00:33:24]:
I'm bringing back up my my Chrome here. Hopefully the first step is it should, open up a new tab or take over the current tab and go to twitter or apps.com, and then kind of browse around and look for, some trending AI news stories. How did I know this is gonna happen? Alright. But, hey, at least you get to see a second time. That really cool, right? So you can see my cursor moving on the right hand side, and then you can see Codex's cursor, moving on the left hand side. So, it's scrolling through, scrolling through Twitter, which sometimes there's relevant stuff, sometimes it's not. Alright. So alright.
Jordan Wilson [00:34:06]:
Apparently, it already got all of the topics that it needed. Okay. So this time, it is correctly using the connected Gmail app. So I can see that when I'm looking at what's happening on my screen in the main, codex panel, I see that it properly called on the tools. So one of the tools that it called on, was we're we're we're we're we're going fast. Alright? It correctly called on the Gmail app. But if you notice, it already opened up Claude. So now you look at the bottom, you can see my Claude app on my computer is open.
Jordan Wilson [00:34:37]:
I didn't have to do anything. It wasn't open when I started. So it found let's see what it found. So talking about the anthropic $100,000,000,000 compute, OpenAI's GPT to image drop. So it found some different things here, and let's see how it's actually using Claude right now. So alright. It looks like, this is funny. Yeah.
Jordan Wilson [00:35:03]:
Claude Claude just threw an error. As as always, Claude's downtime is absolutely garbage. Alright. So, it did properly open up, Claude. It gave it a prompt. It said research the latest web coverage on OpenAI launching GBT image two and chat GBT. So it did what it should have done. It looked at looked at Twitter.
Jordan Wilson [00:35:24]:
It saw what we didn't cover in-depth in the newsletter. It found one thing because by the time we sent our newsletter out yesterday, it was right before GBT, image two was released. So it spotted that. Now it's having Claude pull this information. So there we go. It's doing a good job. I'm gonna I don't wanna hijack the work that my coworker is doing. Right? So I can kind of look over in in my own, monitor here.
Jordan Wilson [00:35:50]:
So now it's looking at Claude. It's gave it time, to run. So it looks like let's look. Yeah. It looks like Claude is still, Claude is still working, but it's almost done. I did tell it in the prompt. It's gonna take, like, two to three minutes. So give it time.
Jordan Wilson [00:36:07]:
Be patient. I can see, the codex cursor there kind of float around, so I know it's still working. Alright. So it says Claude finished. It produced a usable source linked research brief on GPT image two. What changed, who gets it, tiers, implications, and uncertainty. Then it says next I'll generate a three page Canva explainer directly from this material and finish with a concrete openable design link. So it is working correctly.
Jordan Wilson [00:36:36]:
There we go. So the cool thing to know about, about codex, right? It obviously has way more capabilities than what you you would use inside chat GPT or the chat GPT app, the desktop app, because not only does it have, right, MCPs, model context protocols, so you can connect it to literally anything. You can connect it to almost literally anything and automate anything. Right? When you think about, you know, Zapier or just how easy and how readily available MCPs are for, like, literally anything, you can now start to automate anything. But codex, remember, it has read, write, access for any folder that you give it access to. So it can access all of your local files. It can use your terminal, right, which is a big thing because that really unlocks a lot of capabilities on what you can accomplish while you're away from your computer. Alright.
Jordan Wilson [00:37:28]:
And just like that, we're done. Alright. So we didn't have to run this a second time. I don't know why I did this. Like I said, I did five tests, and they all worked well, but such as, such as life. Alright. So here we go. So, it says Canva output created.
Jordan Wilson [00:37:43]:
So it went through I don't know why the previews, the generated previews aren't working, but it did leave a link. So let me go ahead and click this, the three page explainer. Or do I need to go to the edit link? Let's see. Bam. Look at that. So we have a decent looking, a decent looking presentation. Right? This is probably something way better than I could have put together in two minutes. Alright.
Jordan Wilson [00:38:11]:
So it it says let's see. Three pages just as I asked. There's a cover page, GPT image two, the key features. There's the instant mode, the thinking mode, improved quality, enhanced outputs, multilingual support, and API uncertainty. And then for each of those six categories, it does have an image. So, and the images are actually relevant and make sense, which is fairly impressive. Right? So I don't know if that's more, if I should be more impressed with Canva, or codex in this case. I don't even know which AI did the work.
Jordan Wilson [00:38:43]:
Right? Who knows? But it's actually a really nice looking deck. Right? For it did it in thirty seconds. I could have had a template saved. I could have given it, style considerations, things like that. Right, like the new, you know, Claude design, which is, you know, really impressive. But I didn't. I just open ended, said, go do all this, put it together in a three page deck, and then it has the business impact of generative images. So, overall, it created a very usable deck that came from a very general prompt.
Jordan Wilson [00:39:15]:
Right? But I wanted to start, very wide. And, you know, if I did want to use this, I would obviously iterate and improve on this. Right? But you just saw there, obviously, with a hiccup, how this can be an absolute game changer. Maybe maybe one day I'll do side by sides of, you you know, codex versus Claude code, Claude co work. But if it involves computer use, at least right now, like, I can't make you guys suffer through that. The the computer use and I've been saying this since it came out. It's obviously super impressive or it was super impressive, but now it's absolutely stinks. It is slow and ineffective.
Jordan Wilson [00:39:56]:
And, you know, for people on the $20 a month plan, right, on Claude Co work, if you're trying to do anything with computer use, like, good luck. You're gonna completely eat through your tokens by looking at it the wrong way. Right? Your your rate limits are gonna be hit, and you gotta wait another five hours. So very impressive. Right? So let me just very quickly recap what we did there. Alright. Again, second time. But and and and this is why I need non technical people to get over the fact that this program is called codex because I didn't write any code.
Jordan Wilson [00:40:30]:
I didn't see any code rendered on screen. I didn't have to, you know, may wave a magic CSS, Ajax Next JS wand right now. Just did everything for me. So it used my actual computer. It connected, two apps that I had already connected with my dynamic data. It opened and used programs on my actual computer that it didn't have a direct app for. So just figured all that out on the fly. Right.
Jordan Wilson [00:41:02]:
This is absolutely amazing. All right. So, I do want to quickly give everyone a very, very brief overview of the codecs app. Right? I know we're already forty minutes in, ran into a little hiccup, but that's fine. But it if it this looks kind of familiar, if it's your first time, well, it's essentially chat g b t. Right? Which is, again, you know, you can see why they only really need one app, especially once you bring in the browser capabilities. But here's essentially how how it works, how codex works. On the left hand side, you have things like new chat, search, plugins, automations, and then you have projects.
Jordan Wilson [00:41:36]:
Projects don't work the exact same as they would work in chat GBT. They're a little bit different. So let me explain. So in this project, I have what's called Zapier test. Right? So when you set up a project here, you can, or you do need to have a folder that it is linked to. So what that means is each project needs a folder to output files. Right? Or to or to read files. Right? So you can give it access to, you know, your downloads file, your documents.
Jordan Wilson [00:42:11]:
I probably wouldn't do that, because, yes, mistakes can happen, especially if you're new. So I would probably try to sandbox this in a just a dummy folder as you're learning it. Alright. So, aside from that, that's the only big thing. And you like, you don't really have to worry if you're a beginner about, you know, things like the, you know, the the the repo, whether you're gonna, you know, work work locally, whether you're gonna, you you know, push it to GitHub. You don't even really have to worry about that unless you're trying to, you know, build a production app. But for nontechnical people that are trying to get work done, this is going to look and feel very much like Chachigati. Then there is kind of this new feature down here just called chats.
Jordan Wilson [00:42:50]:
This wasn't here last week. Right? But, essentially, that just allows you to quickly chat without giving it access or requiring access to a certain folder. Alright. So aside from that, it is very simple to use. Right? There is a, a search bar. There's a permissions thing. So there's default permissions, full access, or a custom permissions, and that's all. So when it opens different files, if it's using the terminal, all those different things, if you put the default permissions, it's gonna ask you every step of the way because a lot of those things may carry some risk, especially if you don't know what you're doing, or if you just give it some wild commands.
Jordan Wilson [00:43:27]:
It might just be like, hey. I'm going to do this. Do you want to allow? Do you want to allow once or allow for this full session? Or you can do full control, kind of the, you know, YOLO mode if you know what you're doing, if you have it sandboxed. Right? If if if you're an entrepreneur, solopreneur, business owner, whatever, there's, you know, less risk to doing, some of these things. So that's aside from that, it is very much just like using chat g v t. You have these backslash commands. So you can, you know, fork something. You can bring in an MCP.
Jordan Wilson [00:43:55]:
You know, you can access your memories. You can switch the model personality, go into plan mode, you know, see the status, check your rate limits, all those things. There's skills in the same way that again, it's crazy to me that there's no skills in the $200 ChatGPT Pro plan. This is why I don't use ChatGPT on the web much anymore. I use it for, deep research. I use it for certain GPTs, but I'm kind of converting all of those over to skills anyways. So you have all of your skills there, And then if you click the at key, that's where you have your, your different plugins. You can upload files, just like you can inside of, ChatGPT.
Jordan Wilson [00:44:35]:
One difference you will see is there's something called a plan modes. That essentially just breaks a complex task down into a plan. Alright? And that's very helpful, you know, because this thing can work for a lot of hours at a time. Right? If you crank it up to, you know, GPT five four on extra high, And, you know, you go through plan mode and you give it a huge, like, refactor. Right? Mainly if you're doing coding or something like that. Or I did have it, you know, go to, like, every single page on my website and save all the transcripts. Right? That took a couple couple of hours. But this thing can work for a couple of hours for you at a time.
Jordan Wilson [00:45:09]:
Alright. Aside from that, you know, I'm not gonna go through all the settings. You all are smart, but two other things I did wanna check, show you is plug ins. So in the upper left hand corner, you have all these different plug ins. So everything from, you know, computer use that's technically a plug in that you install. You have to, you know, change some accessibility settings, give it access, all those things. But, you know, there's Notion, Google Calendar, Teams, Outlook email, Figma, Outlook calendar, Vercel, SharePoint, Google Drive, Linear, Slack. Right? You know, a bunch of coding tools, Netlify, even though I'm kinda focusing this on our nontechnical audience, Canva, Remotion for video, productivity tools.
Jordan Wilson [00:45:47]:
I mean, you have, Stripe, Box, Jam, Adeo CRM, Brex, ClickUp, you you know, a lot of just common tools, Firefly, Granola, HubSpot. Right? Monday.com, Pipedrive, Semrush. Right? So you think, oh, this is a a technical you know, this is for coders. I mean, what I just named off there, what I just rattled off, that might be half of your tech stack. That might be two thirds of your tech stack. All of a sudden, you're like, wait. I could probably automate a good chunk of what I'm doing every single day. You might be saying, wow.
Jordan Wilson [00:46:21]:
Why would I ever use chatgpt.com again? Again, if you have access and availability to use codex. Alright. And then last but not least, automation. So I'm actually, changing a lot of my automations since the, the update from last week, so I don't have a lot in here. But in natural language, you can just create a, an automation. So you can set it to a certain work tree. So that's, you know, something from GitHub or or you can just run it locally or in the chat. You can select a project.
Jordan Wilson [00:46:52]:
So you can set up an automation to run-in a certain project, and then you can schedule it for when. So, you know, daily, weekdays, weekly, custom, etcetera. Then you can select the model that you want that scheduled run to go on. You know? So for something, if there's a lot of computer use, maybe you wanna do one of the spark models, which is a little bit faster, and then you can set the reasoning level as well. And then there's also templates, for, kind of automations. So that's it kind of bumpy, you know, slightly bumpy live demo, but it is what it is. All right. So let's quickly wrap this one up and I want to give you guys the blunt truth.
Jordan Wilson [00:47:27]:
I don't care if you're a non technical user, you need to use codex now. It is that good. And here's how good it is. I don't even see myself using chat GBT on the web much in the future, at least not right now. Right. I mean, you have the, you know, oh, I I I love the new, you know, GPT images too. Right? It's built in. Right? Presumably, you know, Atlas at some point, some of those capabilities will be built in.
Jordan Wilson [00:47:55]:
So the only thing I'm really using Chad g b t on the web for is is deep research. And there's certain things I I I like the chain of thought, on gbt54 pro better, in chadgbt.com than I than it is, in codex. It's a little more limited, and I really like to learn and improve, you know, kind of my prompting skills and how I piece together different workflows. So I do like reading the summarized chain of thought a lot better, both in, deep research and in, GPT five four. And then like I said, maybe for some GPTs, but the majority of my day to day work is no longer happening in chat GPT. It's happening in codex. Right. So I also will say this hot take right now.
Jordan Wilson [00:48:41]:
Claude is extremely fragmented. Right. Because you might be looking at these things, and you could say, oh, I can do most of these things in Claude code or Claude co work. Right? Aside from the computer use, yeah, you probably can, but it is absolutely fragmented. It is siloed. And that's the, the thing that I couldn't really showcase live, but the importance of persistent memory under a unified agentic context is huge. Right? Because if you're using the cloud desktop app, aside from the computer use being absolutely terrible, cloud code doesn't know what cloud cowork is doing. Cloud cowork doesn't know what Claude Chat is doing.
Jordan Wilson [00:49:22]:
Those are three different areas. So at at times, right, even for myself, I'm a I'm a power Claude user. I I I do love Claude. I love Claude desktop. But even at times, I find myself saying, like, which one should I use? Sometimes I configure an MCP server, you know, on the web, and it doesn't show up on the desktop. Sometimes I configure it inside cloud code, but then it doesn't show up on cloud co work. And I can't even reconfigure it because it says it already exists, but I can't use it. Right? So there's all these things that, you know, the the chat co work Claude code layout of the desktop.
Jordan Wilson [00:49:55]:
It's actually very annoying for me. Right? I do think Anthropic has hinted that in the event, in the future, it will be a unified system. But I think this is one of those instances where Claude code or Claude in general, by being first to really dominate this kind of agentic desktop, experience might have actually, set itself back because I don't know, right, if this was OpenAI's plan. Right? But I can assume, right, they you know, in February, they put out their version of codecs and, you know, Anthropic's been shipping like crazy, and they're probably seeing and understanding what people are complaining about. And they're like, wait. We can just create a better version of this. Sometimes it might be better to be, you you know, the second. Right? You know, obviously, codecs has been out for a year, but the desktop app has only been out since February.
Jordan Wilson [00:50:40]:
So right now, they just don't work well together. And codecs, like I said, is probably a top three AI tool or release, at least for me ever over the past three years. And I don't say that lightly, probably notebook LM in the, chat gbt plus the first, paid version of chat gbt would probably be those two other moments. This is huge. So I'm wrapping it with this. Use codex. Now, whether you are a heavy chat GPT user, whether you are a heavy Cloud Code, Cloud Cowork fan, you need to be using it because there is a period. I don't know how long that period is going to be, but it is such a cheat code to understand the basics.
Jordan Wilson [00:51:24]:
I gave you the five steps. Go follow them. Right? So once you give it some time, once you, refine and perfect some of your workflows and schedule those, Again, maybe everyone comes out with this in a week. I don't know. But at least today, if you do these things, take some time, set it up, improve it. It is an un unfair advantage. Go take advantage of it. Alright.
Jordan Wilson [00:51:49]:
That's it. If you do want access to whatever our future cohort or course is, right, the co working court, make sure to repost this on LinkedIn. Alright. And then if you haven't already, please go to your everydayai.com. Sign up for the free daily newsletter. Thanks for tuning in. We'll see you back tomorrow and everyday for more everyday AI. Thanks, y'all.