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
Advanced Agentic AI for Business: How OpenAI’s Codex Empowers Automated Workflows
The latest developments in AI workflow automation often remain outside the spotlight, yet some tools are already providing outsize advantages to organizations integrating them today. OpenAI’s Codex desktop application is not just another generative model or chat interface—it acts as an agentic operating layer, unifying many of the platform’s most valuable AI functions with the business software ecosystem. For business owners and decision-makers seeking tangible boosts in productivity, operational accuracy, and resource allocation, the following breakdown distills the capabilities highlighted in a hands-on demonstration of Codex’s advanced strategies.
Codex Desktop Application: Unified AI Agent for Business Ops
Unlike isolated chatbots or standalone coding tools, Codex operates as a desktop application for both macOS and Windows, directly linked to an organization’s OpenAI (ChatGPT Plus) licenses. It consolidates the capabilities of connected apps—such as Gmail, Google Drive, Slack, Notion, Linear, CRMs like HubSpot, project management tools, analytics platforms, and design apps like Canva—into a single agent. This enables cross-app data retrieval, writing, and workflow automation inside a unified environment.
Businesses leveraging Codex no longer need to alternate between dozens of browser tabs or siloed plugins. Multiple plugins and skills can be chained or run in parallel, drastically reducing friction in day-to-day operations such as client onboarding, project research, account management, scheduling, and reporting.
Multi-Source Data Aggregation: Real Example from Podcast Guest Management
One standout application of Codex is the automation of high-complexity, multi-source tasks that typically require hours of attentive manual work from staff. For instance, consolidating guest pitches and episode preparation for a business podcast typically requires gathering and triaging information from:
Multiple email accounts (Gmail, private and info emails)
Google calendars (to see bookings)
Google Sheets (for guest pitch forms)
Internal analytics (e.g., Spotify analytics for prior episodes)
Scheduling and streaming platforms (e.g., StreamYard)
Codex can be set up to plug into all these sources in a single command execution, pulling together background research, cross-referencing guest experience with episode analytics, drafting custom emails, scheduling interviews on the correct platforms, and even assembling presentations in Google Slides, Canva, or web-app format. As demonstrated, such a workflow—historically taking four to eight hours—can run autonomously in under an hour, outputting not only the research but also formatted outreach, case study searches, suggested episode titles, and even custom-generated apps or documents for the internal team.
No-Code, Advanced Automations: Scheduled Tasks and Skill Recipes
Codex’s interface emphasizes accessibility: automations can be set up with plain language. Business users can create both once-off and scheduled (recurring) automations via simple instructions, specifying daily, weekly, or custom frequencies for regular reports or task chains. These automations can be managed in an intuitive dashboard, tying each to specific projects or folders.
For common or complex operations that require a precise, high-quality output every time—such as sales pipeline updates, KPI reporting, or compliance checks—Codex’s “Skills” feature enables reusable prompt “recipes.” These skills act as templated procedures which can be invoked across multiple threads and projects, ensuring consistent, accurate outputs regardless of who triggers the action.
Direct Computer Control and Remote Operations
Codex also features “computer use,” allowing AI to operate with its own virtual cursor on the user’s desktop. Tasks such as opening business software, summarizing news or internal documents, generating reports, or interacting with browser-based platforms can be triggered without disrupting the user’s active session. Notably, Codex’s implementation supports true multitasking: AI can run background desktop operations even as employees work concurrently, something that has been a stumbling block for competing AI agents.
Accessibility extends to remote workflows as well. The ChatGPT mobile app now features direct integration with Codex, enabling remote triggering and management of desktop automations. Common operations such as documentation, project queue updates, or CRM entries can be managed and tracked from any mobile device, multiplying opportunities for asynchronous work and rapid response.
Business Impact: Quantifiable Efficiency Gains
The net effect for business decision makers is quantifiable: automations that previously took entire workdays can be launched and iterated in minutes, and run on repeat with zero manual intervention. This includes complex, cross-platform projects no longer dependent on inconsistent manual workflows.
Automating multi-step, multi-source operational projects (e.g., research, reporting, outreach, documentation)
Consolidating integrations across CRMs, CMSs, communication platforms, analytics dashboards, and more, without code
Enabling AI agents to create deliverables—presentations, formatted emails, web apps, analytics readouts—on schedule or on demand
Empowering teams to focus on high-leverage review and decision-making (“front-end orchestration and back-end taste making”) rather than getting stuck in repetitive, tactical execution
Conclusion: Codex as the Productivity Multiplier for Modern Organizations
OpenAI’s Codex desktop app demonstrates that mainstream agentic AI for workflow automation is available for organizations today, accessible to non-developers and with deep integration into everyday business tools. Businesses that invest in learning and iterating with Codex—and leverage its skills, plugins, automations, and remote control—can expect compounding returns through reduced manual workload, higher quality outputs, and faster response times across the organization’s critical functions.
For leaders evaluating where to direct AI investments, Codex represents a pragmatic move toward intelligent automation with measurable business value.
Topics Covered in This Episode:
- OpenAI Codex Desktop Overview & Benefits
- Advanced Codex Agentic Strategies Explained
- Codex vs Claude vs Gemini: Feature Breakdown
- Unified Memory & Project Management in Codex
- Codex Plugins, Skills, and App Integrations
- Scheduled Automation in OpenAI Codex
- Computer Use and Remote Desktop Control
- ChatGPT Mobile App as Codex Controller
- Automated Podcast Guest Research Workflow
- Real-Time Chain-of-Thought & Task Management
Episode Transcript
Jordan Wilson [00:00:17]:
It seems like the holy grail of AI that the masses have begged for for years is actually here today for anyone to use, yet hardly no one is paying attention. So what is that? Well, we've wanted the best model, the best limits, agents that do our work for us and connect to almost any platform we use. I mean, that was kinda like the AI pipe dream of 2022 to 2025. Right? We all wanted some futuristic AI that could be so advanced. It could write entire programs for us and complete our big projects and triage our daily grunt work and run around the clock with or without our inputs. Oh, and you should be able to talk to it from your phone and control the whole thing even when you're not in front of your computer. Well, guess what? That holy grail of AI day, it's here, and ninety nine percent of people are sleeping on it. It exists in OpenAI's codex.
Jordan Wilson [00:01:14]:
And I've been doing this everyday AI thing for more than three years. And I'm not exaggerating when I tell you that individuals in companies that are going all in on codex right now have the biggest and most unfair advantage that we've seen in the generative AI era. Claude doesn't come close. Gemini doesn't come close. Even chat g p t itself doesn't come close. OpenAI's codex desktop program is the AI that the world has always wanted, but, well, apparently, they're too afraid to touch it because of the word code in the name. So we're gonna break it all down for you today on our AI at work on Wednesday's series as we break down codex for beginners part two in our two part series. And this is one, trust me, you cannot miss.
Jordan Wilson [00:02:03]:
So here is the big picture. Codex has been the best kept AI secret for the past few months, but people are finally starting to catch on. Right? I'll say this. There was a ton of anthropic clawed momentum, in December and January, and it was well deserved. And I think how things happen. I've noticed this that I'm in the bubble of the bubble when it comes to AI. Even things that I see, I feel the rest of the AI world doesn't always see them until maybe a couple months later because I'm one of the only people in the world that spends 10 to 12 days or ten to twelve hours a day literally doing only this. Right? So, there was a lot of momentum around Claude code Claude Cowork in December and January, and I think the general world really didn't feel that until, like, April.
Jordan Wilson [00:02:45]:
So I'm telling you right now, this if you haven't seen these shift yet, it is going to happen. So whether you, feel this wave, I don't know if you're like me in Chicago or New York or Miami, wherever, I think probably in the Silicon Valley bubble, people have already felt the codecs wave, and it is coming. So you should probably get on it now. And here's what else is happening. All the big players are moving to desktop, and codecs is by far the best. Quad code is good. Right? The quad desktop program. But the problem is, well, you it's siloed.
Jordan Wilson [00:03:18]:
They don't talk to each other. Even Google Gemini went desktop, you know, last month bringing Gemini to desktop. And yesterday with their anti gravity two point o, which funny, like, funny enough, I don't know if anyone has says this. It just kinda looks like codex. Maybe that's a good thing. I don't know. But codex power features are the difference maker. So that's what we're gonna cover on part two.
Jordan Wilson [00:03:41]:
We're gonna go over scheduled automation, skills, plugins, computer use, and remote control. So stick with me for today's show. Here's what you're gonna learn. We're gonna do a very quick recap of the basics, What we went over in part one, you're gonna know the reasons most of your normal chat g p t usage should probably just be done inside codex. You're gonna know how the chat g p t mobile app is now the most powerful AI controller in the world. That one's not even close anymore either. And you're going to learn how to properly set up codex to be your around the clock agent that actually does your work. Sounds awesome.
Jordan Wilson [00:04:15]:
Right? It's not too good to be true. I'm gonna be showing it all to you today live on everyday AI. What's going on? If you're new here, my name is Jordan Wilson, and, yeah, I do this every day. It's unedited, unscripted, just bringing it to you raw and real as it gets, with our daily live stream podcast and free daily newsletter. So if you're trying to be the smartest person in AI at your in your company trying to grow your career, well, starts here with this livestream podcast, but make sure to go to our website at youreverydayai.com. We're gonna be breaking down all of the details of today's show. It's gonna be a fast and furious one full of facts. I mean, I could turn this into, like, a six hour course.
Jordan Wilson [00:04:56]:
Instead, it's gonna be, like, a thirty minute podcast, so make sure you check out the recap in our newsletter. And we're gonna have all the other AI news that you need there. Alright. Also, I went crazy overboard on this one y'all. I'm not gonna lie. Alright. So, make sure to repost this. And, not only are you going to get early access and first access to our co work codex cohort, Still not sure what the name's gonna be.
Jordan Wilson [00:05:20]:
Could just call it CCC. Right? Like our old PPP. So we're hoping to launch that in quarter two. So go repost this on LinkedIn. I'll make sure you get, early access to that. Alright? And if you are listening on the podcast, the LinkedIn link is always in the show notes. So check out the show notes for today's show, and you will find that LinkedIn link. But I also went absolutely bonkers, and I spent way too much time and probably a couple million tokens putting together the codex cookbook.
Jordan Wilson [00:05:46]:
Alright. So this is some advanced tactics. We have, I think, 50 plus, use cases by job type, by category, by skill level. I've been using codex around the clock, since it came out in February, and this is some of my the best of the best stuff that I don't have time to put in today's show. So, when you repost today's show on LinkedIn, not only are you gonna get early access to the codex cohort, and, the co work codex cohorts, but also the codex cookbook. Alright. Let's get into it. We're gonna start live.
Jordan Wilson [00:06:18]:
I'm letting you guys know this one could get messy because we're gonna be doing some well, we're gonna try to be pushing, you know, codex to the limits here, but I'm gonna be sharing, my screen and a lot of other things. So livestream audience, if you could, let me know if you can see this here. Alright. And to our podcast audience, FYI, the video version of this one might be helpful for you to watch. I know people are always like, put your video on Spotify. I I don't know why I don't. Maybe I should have codecs do that. But to go get the video version, just look on our website at youreverydayai.com.
Jordan Wilson [00:06:54]:
Alright. So we're gonna do this live, and here's why I do it. I don't edit this show. If it breaks, it breaks. If it blows up, it blows up. If it works, it works. Great. But there's a good chance it might not.
Jordan Wilson [00:07:03]:
The thing with generative AI, you get different things every single time, and I like to show you all the, you know, the the real. Right? Not just the polished version. Alright. So here's what we're gonna do. I'm gonna go ahead. I have this queued up in my codex now. So codex is a desktop app. It is literally free to use.
Jordan Wilson [00:07:21]:
Right? Your limits aren't gonna be good, but I've already said this on the last show. Even if you have a paid chat GBT account, $20 a month, you're gonna get a ton of codex usage. I've done testing. You get more out of a $20 a month codex plan, or chat GBT plan than you do a $100 a month, anthropic plan. So, it's a good deal. But, yeah, if you're like, oh, I don't have a codex plan. It's not a separate plan. Go use your paid chat GBT plan.
Jordan Wilson [00:07:44]:
So you download the app. I am on the Mac, but they also have this for Windows. It is a desktop program. You connect one time with your chat GBT account, and you're good to go. Alright. So I have a prompt, dialed up here. Let's see how it works. This is, this is hefty.
Jordan Wilson [00:08:02]:
Okay. This is hefty. So let's see. I do have a lot running on my computer, but hopefully alright. I'm going to read this off. I'm not going to read all of it, but I'm going to read most of it. Here's here's I have a problem. Okay.
Jordan Wilson [00:08:16]:
I have a problem. You probably noticed lately. I haven't done a lot of guest shows. And one of the reasons was, we had too many guests pitching. Some of our guest shows, unfortunately, ended up not being the best. People just sold way too much even though I had a hard no sell policy. Right? And I got so many emails, and they're like, this guest stinks. Don't do guest shows.
Jordan Wilson [00:08:37]:
So, like, for five months, I've done hardly any guest shows, but I'm gonna bring them back, but I wanted a different format. And right now, I'm also just to give you guys, like, I want you to feel the pain. Right? And as I'm going through this use case, I want you all to think of what are some of those projects that you just put off doing or they're so time consuming or they're hard to do because I'm telling you my pain point right now. I'm telling you my story and how I'm, well, automating this in codex. Right? Some new features over the last week or two have now gotten to one of my pain points that I don't like doing. I can automate a big chunk of it. I still keep myself in the loop intentionally. I could automate a 100% of this, but I don't want to.
Jordan Wilson [00:09:16]:
Alright. Anyways, I get too many guest pitches. They come all over. They go to my personal Gmail. Have no clue how it gets there. You know, my old company called Accelerant Agency. I have a couple info emails. People guess my private email that I just set up, and I'm transferring everything over there.
Jordan Wilson [00:09:33]:
Anyways, I I get guest pitches from about six different places. So different emails. Some of them are automated into spreadsheets. I have a form on my website. So it's it's it's a mess. Right? It wasn't like this three years ago. I was begging for anyone to be on the show, but now we get thousands of guest pitches a year, so it's hard. Also, it's a lot of time to research people.
Jordan Wilson [00:09:53]:
Obviously, in people's guest pitch, they're like, this is the best thing since sliced bread. But I what I generally do is, well, I look at people's background. You know, I'll use obviously AI to do that, but it's still a lot of these these steps. Right? Where I'm having to copy and paste a bunch of stuff, and then I get lost. I get distracted. Right? And I go down a rabbit hole and whoops, I just wasted an hour seeing if this person should be on the show or not. Alright. So here's what I have codex doing.
Jordan Wilson [00:10:20]:
So, I already have full disclosure. This isn't for vetting guests. It's for, researching. So kind of our new guest format, it's essentially, like, steal the secrets. Right? It's gonna be based on and let me know if if if you like this or maybe, you you know, livestream audience, let me know or, podcast audience too. Spotify people, you can leave a comment. The three things that I I I'm gonna have guests focus on in the future are use cases. Right? So here's the use case.
Jordan Wilson [00:10:47]:
Here's our secrets. Training. Here's what didn't work. Here's exactly what worked. Here's our secrets. And then change management. Right? Here's what didn't work. Here's how we got it figured out.
Jordan Wilson [00:11:01]:
Here's how we're continuing to invest in people. Here's our secrets. So, essentially, you come on the show, you give all your secrets away, and then our audience, you know, you get the secrets. So yeah. Let me know. Just, use case, change management. What was the other one? I think one was ROI. See, now I'm confused.
Jordan Wilson [00:11:20]:
Anyways, let me know which one of those sound good anyways. So here we go in codex. I said, please look at my Google Calendar because I do have three guests booked for next week. These are prerecorded. I wanna make sure they're good before, you know, we start doing these things live, get the format worked out, all that good stuff. So I said, please look at my Google calendar and these things that are highlighted here in the codex prompt for those of you, watching along. These are technically plugins slash apps, inside codex. Alright.
Jordan Wilson [00:11:46]:
So I said, please look at my Google calendar and find my everyday AI guest for the next week. Then carefully search for them in my Gmail, including inbox out boxes. There's a lot of back and forth. Right? I'm skipping over some of this. I need to find their original guest pitch info, which may be in the guest pitch form, Google sheet in my Google drive. So so far, I'm having it look in my Google calendar, my Gmail, and my Google drive, and kind of triaging or triangulating all this information between them. Alright. And then I'm saying, most importantly, oh, I made a mistake y'all.
Jordan Wilson [00:12:21]:
Well, this is good. You're gonna learn something, as we go. So I'm gonna, I meant to upload my my stats. I'm gonna say here's the stats. Please continue. Alright. I meant to give the stats originally, anyways. So I said most importantly, I'll need you to methodically go through the attached everyday AI Spotify, analytics g s copy file.
Jordan Wilson [00:12:47]:
So it's essentially this I I have a bunch of agents, codex, Claude code, you know, running all the time looking at all these in-depth Spotify analytics, and then putting them together in a sheet. Alright. And then I'm telling, codex to go find the most relevant to popular and align shows that might overlap with the guest based on their experience that they pitched and research what made those shows successful and why. Alright. And then I'm giving it essentially, six different tasks to do. Okay. So first, I'm just telling it to do extensive research on the guest background. And I'm saying come up to with five to seven specific follow-up questions to dig deeper based on what they pitched and based on what's working recently in our analytics.
Jordan Wilson [00:13:35]:
This is something again, this is my manual step that I would have to do every time. If I was the most focused, most locked in I've ever been, just getting through step the first part of step one would sometimes, especially in, like, 2023 when, you know, AI systems were were non reasoning and they weren't that great, just getting through that first part of the first step would take multiple hours. Right? This whole process might take a day or longer. Alright. So I'm saying come up with five to seven specific follow-up questions to dig deeper. And then I'm saying write a short and informal email draft in my tone style with proper formatting. So I'm literally having a go understand my style, and then, go through research all these guests, research the best episodes that are most aligned with their experience on what they pitched, and then come up with very specific follow-up questions so the guests are more prepared. And then I'm saying to start that draft in the email.
Jordan Wilson [00:14:36]:
That's not all. Alright. Then I'm having it, use the either the browser use or the Chrome to go into streamyard.com. That's what we use to stream. I'm having it click a new recording, so I'm giving it step by step on how to set this up. Alright. So it's like, go click the new recording, put the guest name as the title, click create recording, all this stuff. And then essentially, you're gonna get a link, and then we're gonna send that to the guest themselves.
Jordan Wilson [00:15:03]:
Alright. Then I'm saying so that's step one. That's a lot. Right? So looking at all of our analytics, looking at what the guest pitch, seeing where the crossover is, seeing where the value is, coming up with questions, creating, a StreamYard link, and then putting all of that information in a, in an email draft that if I want to, I could have it send it, but I don't want to in this case. Alright. Step two, coming up with three potential episode titles. Step three, I'm tell I'm saying to do additional research for me to prep for the interview, such as highly relevant, case studies, stats, facts, trends that are highly relevant to the suggested show. Number four, alright.
Jordan Wilson [00:15:43]:
And here's where I'm bringing in some other, plugins or apps. Alright. I'm saying create two versions of a presentation prepping me. One in presentations, which will, open as a Google, slides file, and also one in Canva. Saying include everything I need to know about the guest, their background, the show type, the show topics, etcetera. Then I'm saying, then create a simple web app using the build with apps skill. So this is a, actually, I'm trying to remember if this is a skill or a plugin. I'll I'll have to check.
Jordan Wilson [00:16:15]:
Alright? In case that is more convenient for me. Then last but not least, I'm saying also save the text only recap as a word doc in Google Docs as well as a suggested outline for the interview based on what might might what might work best. So this is all, you you know, especially now I would have a big guest. Right? Like CEO of a fortune 500 company, you know, back in 2023, just to do this these steps. Right? I wouldn't create a web app and all these things. I'm just trying to show showcase some of the capabilities. But, you know, it would take me a half day, sometimes longer, to do this. Now I can well, we'll see how good it is.
Jordan Wilson [00:16:52]:
Right? We're doing it all live. Alright. So you'll see right now, on my screen, it's already going through. It's already working. You know, I had to interrupt it midway through, with the stats that I forgot to attach, and it's still going. And then on the right hand side, it's showing me the progress. So, at any point, you can see the progress of codex because it's an agent. Right? So by default, it breaks things down into multiple steps, and you can kind of track it as it goes along.
Jordan Wilson [00:17:21]:
So I can both follow along and see what it's working on, you know, what websites it's going to, what files it's it's pulling, you know, out of my Google Drive. I can see all of these hat things happening in real time. This is literally like giving this project as if I just spit it out to a team of 10 people on the computer. Right, and they're in a circle, and I just sit there in the middle of the circle, and I look around and see what everyone's doing. I peek over their shoulder. This is the best way to get better at AI and specifically codex because it does work a little bit differently than, you know, even if you're using. Right? I'm using, GPT 5.5 extra high, so the best version. And I think I have it on yeah.
Jordan Wilson [00:17:58]:
Speed. Okay. I did put it on 1.5 speed. So using more credits, but the credits on codecs, I mean, it's like free candy. It's it's free candy at a parade. I I literally can't hit my limits, and I'm running it around the clock. Anyways, I'm on the the best model and running it 1.5 speed. So hopefully, we can see the end results here.
Jordan Wilson [00:18:18]:
But it still works a little bit differently than, you know, working with g b t five five in chat g b t would work. So it's important to have this kind of visibility and observability, as you work. So you can see the progress on the right hand side. It broke broke this big task down into, looks like seven, seven or eight smaller subtasks, and then outputs. So this is where the final, kind of artifacts are because I believe I asked for at least six things. And then right now, it's the different sources. So for the sources, these are all my connected plug ins. So it's actually pulling in my dynamic data.
Jordan Wilson [00:18:51]:
So, my Google Drive, my Gmail, Canva, Google Calendar, and web search. Alright. So we're gonna let that cook, and then let's get back into a quick recap. Right? All that. But quick recap of part one. Alright. So this is part two where we're gonna get, go over some of the more advanced, techniques and not even super advanced. Right? I'm not even gonna get into, you know, customizations and, you know, doing different things in the diff viewer and, MCP.
Jordan Wilson [00:19:21]:
Right? I'm not even getting into that. This is more the more advanced, tactics for beginners. Okay? So this is still for beginners. But in part one, we cover this, the basics. So that was episode seven seventy six, so last Wednesday, so make sure to go check that out. But here's the very quick recap. Here's what we covered. Number one, codex is the super app.
Jordan Wilson [00:19:42]:
There's been all this reporting and hype around, oh, OpenAI is creating this new super app in the future. Well, it looks like the chat g p t desktop app in the Atlas browser are probably gonna, you know, eventually go away. That's what I think. I don't know. They haven't actually said that, but it looks like they've said all along they're come out with a super app, and they alluded to the fact that codex is that. So, if you wanna be on the future, Codex is the future. So right now, Codex is positioned as the operating layer for repeatable workflows, not just a chatbot interface. That's the biggest thing, and we're gonna see that in today's episode.
Jordan Wilson [00:20:18]:
Alright. And a lot of people are instantly gonna go to Claude. Right? And let me just say, Claude is, like, the minor league baseball player right now, and Codex is the MLB all star. They're not in the same league. They're not in the same division. They aren't. Right? That I'm not biased when I say that. I I go back and look.
Jordan Wilson [00:20:39]:
Right? When I was covering, you know, Claude code, Claude co work in, you know, December, January, February, I said at that time, co work, you know, is in a league of its own, and it was, but it was clunky. And it at least what we have today, not comparable. So some of the biggest differences, and I did go over this a lot more, but Claude desktop is siloed. Alright. It's essentially three different programs that don't know the others exist. So you have to choose between chat, or co work or Claude code. And as an example, chat doesn't know what you're working on in co work. Co work doesn't know what you're working on in Claude code and vice versa.
Jordan Wilson [00:21:17]:
And to make matters even worse, and I demo this live, even if you go in, co work or code as an example, and you do, you know, new thread, new thread, new thread. Right? If you're on thread five, it doesn't know anything. It only knows thread five. It doesn't know what you talked about in thread two. It doesn't know anything else. So not only is clawed desktop siloed, but it doesn't have working memory in co work or code thread to thread or test to test, which is absolutely bonkers. Bonkers. Right? When I like, when I do trainings and I tell, like, enterprise clients that, and they're spending a lot of money and they all scratch their head and they're like, wait, what? Yeah.
Jordan Wilson [00:21:59]:
That's the reality. And so, codex is unified. It is one. There's not three separate entities and it has memory. So I did demo that, for all you naysayers. I did demo that live in part one. And then last but not least, codex and chat g p t, while there's different use cases, I still do use chat g p t on the web for some things. I'm using the, mobile app now around the clock, more on that later.
Jordan Wilson [00:22:23]:
But there are still some reasons to use chat g p t on the web. For me, I'm using it for g p t five five pro because I do feel g p t five five pro is a little bit better than the five five extra high in codecs. I also use it for workspace agents, which are a little better. Not better, different. Alright. So, for these codecs automations, that we're gonna run, codecs has to be up and running, but there's all these settings that keep it on. And then I use it for deep research. So at least for me, there's three things I still use ChatGPT on the web for because I know that's another thing people are confused about.
Jordan Wilson [00:22:56]:
Like, oh, well, should I just move everything to codex? For me, I've moved 95% of my chat GPT web usage into codex, and I haven't looked back. Alright. So the five advanced features that you need to know that we're gonna be going over, schedule, automations, skills, plugins, computer use, and remote control. Alright. Let's go ahead and reshare our screen. So, we'll check-in. Alright. Looks like we're still we're still cooking here.
Jordan Wilson [00:23:28]:
Still still, taking taking some time. I do have a version of this that's done, just in case because I did tweak a couple of things. I always tell you guys, run these things multiple times, especially if you're trying to, you know, automate a big chunk of your workflow. You should always be iterating, always be changing. So even though I have a version of this that works and I'm ready to show, after I looked at it, I'm like, oh, we should change a couple of things here to make it better. So, technically, haven't run this, but we'll see how it goes. Alright. So I'm gonna go ahead and open a, a new window of codex.
Jordan Wilson [00:23:58]:
Yeah. You can have as many windows as you want. I love using computer use and having codex control codex and codex control clod code and all these things. Alright. Anyways, let's do a quick overview of these five features. So first, let's look at plugins. So, on the left hand side of your codex app, you're gonna see, some different pans, some paints. I went over the basics of this, but your settings at the bottom, you have all of your projects, that are tied to a folder, and they can read and write.
Jordan Wilson [00:24:31]:
Right? That's another huge advantage of codex. It can read and write, files, which is can be good or bad if you don't know what you're doing. And then you have chats, and then these chats are kind of individual, and they're not tied to a certain project. Alright. So and then up in the top, you have your plugins and your automations. So let's look at plugins. So there's no dedicated space for skills. So sometimes people are like, where are skills? Well, you have to click on plugins first, then click in skills, but we're gonna talk about those in a minute.
Jordan Wilson [00:24:59]:
So plugins. There are I counted these earlier, but I forgot. There's, probably about 60 or 70, maybe more, maybe, actually closer to a 100, skills, or or sorry, plugins in here. So you can search for them or, you know, there's featured, there's coding, there's design, there's lifestyle, there's productivity, and there's research. So, very easy to install. You would just click on something. So, you know, linear. I don't have linear setup.
Jordan Wilson [00:25:31]:
I can click on linear. I can just go click add to codex, and then I would log in with my linear, credentials. Usually, it's one or two clicks, and then you're set up. Alright? But let's let's, little bit more about plug ins. So, essentially, ChatGPT changed the name. Right? So originally, they were connectors, in ChatGPT, and then they turned into apps. So now they're plugins, inside, codecs. And the reason why is because they're a little bit more than connectors and apps.
Jordan Wilson [00:26:00]:
And let me show you what I'm talking about by going into the Gmail connector. So, let me zoom in here. So the description is says, read and manage Gmail, use Gmail to summarize inbox activity, draft replies, and organize email threads through the connected Gmail app. So includes, and here's why plugins are not exactly the same thing as apps in chat g p t or as they were previously called connectors. That's because they also include skills. Not all of them do, but many of them have prepackaged skills. And we're gonna be talking about skills next. Alright.
Jordan Wilson [00:26:36]:
So, these plugins are essentially connectors that combined skills, and they link codecs to the tools that you already use. Like I said, there's a ton of popular ones. So, you know, everything from computer use and controlling Chrome, which we're gonna talk about later, to spreadsheets, Slack, Notion, Linear, Gmail, you you know, your calendar both in, Google and in Outlook, Vercel, SharePoint, Figma. I mean, Hugging Face, Netlify. I'm just, you know, scrolling through naming some of the more popular ones. Twilio, Remotion, Canva, HeyGen. Let's see what else we got here. Obviously, Docs, Atlas and Stripe, Box, Jam.
Jordan Wilson [00:27:13]:
I mean, bangers here, ClickUp, Conductor. So many I use, Fixer, Fireflies, Granola, HubSpot, monday.com, Pipedrive. So you have your, CRMs in there, Semrush, Streak, Zoom. Right? Something a lot of people use, like, half the world. Asana. Right? So, yeah, that's that's some of the more popular ones. So these are a lot of the day to day tasks that you use on an ongoing or the day to day apps that you use on an ongoing basis. And if you didn't see the visual, right, you can use multiple of them at the same time.
Jordan Wilson [00:27:45]:
When I kind of read out that prompt, I was using, I think, about six different apps. Okay. So, these are all, you know, permission is case by case, so you should go see and understand what they can do. So as an example, if I go back and click on Gmail, so it includes the Gmail app and then two different skills. But I can go down. Let's see. I always forget where this is. Where do I find this? The Gmail app Website privacy policy.
Jordan Wilson [00:28:16]:
I had all this up beforehand and I'm like, oh, I should. Okay. There we go. So you can right click, or you can click on the see, how how did I do that? They should make this a little more clear. Okay. You just click on it, but you don't know you can click on it. Anyways, you can click on it to see all of the different permissions or all of the different things that it can do. So in the Gmail's, sense, this is different than in ChatGPT because, you know, early on in the connectors and apps days, they were one one way streets.
Jordan Wilson [00:28:45]:
Now they're bidirectional and they can read. So in this case, Gmail app has 24 actions. 11 are write and 13 are read. So it can, you know, go through, create drafts, create labels, all these things, but it can also read emails. Right? So it can write emails, read emails, do all these batch tasks. So you can click on any app and see exactly, what it can do by looking at those different permissions or different tasks. And this is important too because, you know, if you're just giving very vague prompts to, especially to these plugins that have a lot of different read write actions and you're not watching the chain of thought, you might not get the desired result. That's why number one, it's important to look at the chain of thought because you will see, essentially, the the the tool calling that's happening there.
Jordan Wilson [00:29:36]:
Right? You'll see if it's, oh, it's it's grabbing the right, permission or the right, you know, tool out of those 24 from Gmail as an example. Alright. So that is plugins. So, I mean, the big upside here is, you know, no more bouncing between 37 taps. Right? Now you can just, you know, be talking to six or seven, different plugins at once. And the good thing is, well, they can be updating each other. So let's say, you need to update your HubSpot in there, according to all your emails and something in a spreadsheet. Well, you don't have to do anything.
Jordan Wilson [00:30:10]:
Right? You can set all of that up and you don't have to open anything. Alright. Next, let's go on to skills. So again, to get to skills, little confusing in the left hand pane, You're gonna click plugins, and then there's a little spot up top. A lot of people, like, struggle to find it, and they're like, where are the skills? Well, there they are. They're at the top. So skills. What's the difference? Skills are if you've used Claude, you probably know skills because I think that's one of the things that, really has set, you know, Claude apart.
Jordan Wilson [00:30:43]:
They really leaned heavily into skills. ChatGPT, not all account tiers even have access to skills, which to me, I'm like, come on. If you're paying $200 a month for chat g b d pro, you gotta have skills. Anyways, you know, they have them on, like, team plans. So skills are essentially, like, reusable instructions, and they act kind of as recipes. So it's like teaching your agent exactly how you want a task done every time. So, that's in simple terms. In technical terms, it's a series of markdown files.
Jordan Wilson [00:31:12]:
Right? That's all it is. So you can type a forward slash command and then the skill name, and then your full set of rules, formatting, and logic loads instantly. So it's why they matter is, well, you get the same high quality output every time. So you're not gonna get the exact verbatim, but you're gonna get the same quality every time. So this is like, think of it as like a series of prompts, very specific, well written prompts over and over. Right? But that's all skills really are. Is there very specific questions formatted in a, meticulous way that ensures between the different, you know, agentic, nature of these models between all the tool calling, the harness that's always changing. It makes sure that it really does, what you want it to do consistently each time.
Jordan Wilson [00:32:00]:
And the easiest one to build one inside, codex, well, there's a couple ways. You can go into the skills. You can manage the skills that you already have. Looks like I have about 56 of them here that I use. It's actually not a lot. This is one of one, this is one of my, dummy accounts that I don't use a lot. This is just for kinda demos. But you can in the upper right hand corner, you can go to create a plugin or create a skill.
Jordan Wilson [00:32:25]:
So then you can create a skill. There's actually a skill called skill creator that you just talk to. So you don't even have to be writing anything in code. It's just in natural language. Alright. So those are skills and why they're important. Alright. Next, let's go to computer use.
Jordan Wilson [00:32:42]:
This one's fun. Alright. Let's see what what could go wrong here. Alright. Let's let's go ahead and try computer use. So I'm just gonna say computer, so I'm gonna say use computer use, and, let's see. I'm gonna say open my, Apple News. We'll try that.
Jordan Wilson [00:33:02]:
We'll see. Open my Apple News and tell me what's trending. Alright? We'll do this. We'll make it, we'll go medium to go a little faster here. So computer use is actually that. It's using my computer. Alright. So, it's always funny when people are like, look, I'm doing this with no hands.
Jordan Wilson [00:33:23]:
Right? But, what's what's gonna be happening here, on my screen, I'm not gonna be doing. The difference is, the computer use plugin, is very, very good. I actually should have, yeah, it's already done. I should have used, codex five three spark, which is amazing. It's so fast. That's the one with their partnership with Cerebras. So, you'll see right here, it's scrolling. Again, it's scrolling through, Apple News.
Jordan Wilson [00:33:55]:
So it launched, a program on my desktop. It's going through, right, simple stuff, but it's so good. It's so, so good. So I say that because Claude's computer use went crazy viral when they announced it. It was a couple months, before OpenAI announced theirs in codex, and I've done a lot of side by side now. Not only is the codex computer use the default one faster and more accurate, when you use that five three spark cerebras, I've done side by side. In in in my experience, and it depends on what you ask it. Right? Generally, I have to do very simple task when I'm doing these tests.
Jordan Wilson [00:34:35]:
You know, open two or three programs, create a document, save it. Right? Something like that. Something that the average knowledge worker would be doing over and over. Computer use in codex is about five times faster, than computer use in Claude, co work. And if you've used the Cerebras, it's like 15 to 18 times faster. Alright. So the Cerebras five three spark is not as powerful of a model, but if it's basic if you're just doing basic computer use work, it is absolutely mind boggling how good that is. Alright.
Jordan Wilson [00:35:08]:
So that's computer use. So, right, it just so I click over here. It said, oh, I Apple I opened Apple News trending stories, and it recapped six of the, top stories there. So, essentially, it gives your agent its own cursor to look at the screen, clicks buttons, and type. And that's the biggest difference between, the computer use via codex and the computer use via cloud code. I think the cloud code one has gotten a little bit better since they announced it. But for the first two ish months, it was a train wreck. The main reason why is what number one, it was too slow.
Jordan Wilson [00:35:45]:
Number two, if you were on the $20 a month plan, good luck even getting it to complete a task. You would quickly hit your limits. But number three, it's screen jacked, it mouse jacked, it window jacked, everything. So you couldn't work at the same time as computer use. So, you know, I was trying to integrate computer use into my day to day workflow, but it had to have its own computer. So I don't know what kind of wizards work over there in codex, but it has its own cursor. And even if it's using an active window, you can still use your own window. So if you've ever used computer use in clawed desktop and you're like, oh, this is cool.
Jordan Wilson [00:36:23]:
Yeah. Go use codex. Again, minor league baseball player, you know, Sammy Sosa. I don't know why I said Sammy Sosa. I was trying to think of, you know, an MLB all star from Chicago and Sammy Sosa came out. Alright. So that is computer use. It is good.
Jordan Wilson [00:36:39]:
It has its own cursor. It runs in the backgrounds. No interruptions. Great. Alright. Let's go next. Scheduled automation. So now that I showed you plugins, right, which are essentially apps with skills.
Jordan Wilson [00:36:52]:
I showed you skills and I showed you computer use. What if you could just, I don't know, do all those things together and run them as a scheduled automation. Well, you can't. Alright. So, at any point, right, I could just do it here. I could say, you know, run this every day. So I'm just doing the the one that I was doing with Apple News. You know, I could say run this every day at, you know, 8AM as a scheduled automation.
Jordan Wilson [00:37:23]:
Right? That's all I have to do. So if you spend a lot of time in a thread and if you get something just right, you know, first, say, hey. Take a look at this. You you know, go step by step, and, let's create a scheduled, automation out of this to make sure that we get this kind of output every single time. And that's it. So I just say create a schedule automation, and it's done. Alright. And then you'll see up here I have that new automation.
Jordan Wilson [00:37:51]:
So this is called the heartbeat. So that means it runs daily. Alright. And then I can go and click it and I can modify it if I need to. I can pause it. I can delete it. I can change the schedule, or you can just go into the automations tab. So that's on the left hand side.
Jordan Wilson [00:38:06]:
So you have your new chat, your search, your plugins, your automations, then you have your projects in your chats. So I can just go into automation. I can just click a new one, and I can also just build it from scratch. You can have it work locally in a work tree, on GitHub. You can select the different project that you wanna tie to. So it can be it can just be a normal chat that's not tied to a project, or you can tie it to a specific project. Then you can set the cadence whether you want it to run daily at a certain time, things like that. You can also pick the model and pick the reasoning effort.
Jordan Wilson [00:38:39]:
And there are also templates, which are absolutely right. It it's like, how easy. Right? Again, if the reason you haven't used codex is because the word code have you seen me write any code yet? Absolutely not. Yet I'm doing things that, you know, I'm accomplishing, I would say, a lot so far. Alright. Let's see here, how we're doing on my other one. I have it open. Alright.
Jordan Wilson [00:39:03]:
I don't know if this one is going to, finish in time. Must have been some of the, the new things that I added. So last but not least, let's go to remote control. So, unfortunately, this is something I'm not going to be able to accurately demo, because I'm using my phone to record this. Right? The this was just announced. And now the chat gbt app is I think literally the best app on the app store. If I'm being honest, I didn't really use it a lot until the codex control came out. Mainly because I hate doing work.
Jordan Wilson [00:39:43]:
I've said this before. I hate doing work on my phone. I have fat thumbs. Right? So if anyone out there, if you've ever texted me before, I'm not texting you on my phone. I'm waiting till I get home and or office or whatever. If I'm on the go and you text me, I don't text you back. Right? I I hate it. I hate it.
Jordan Wilson [00:40:03]:
But now I'm actually using my phone a lot more, and I'm using the chat GBT app because now I can control, codex via the chat GBT app. I know this is a little confusing. It's not a codex app. It's the normal chat GBT app. And it's a new remote control feature. So, essentially, you're gonna download or or make sure you have the most updated version of codex, the most updated version of the Chat GPT app, and there's gonna be a codex tab in the Chat GPT app. And then it's gonna take you through a pairing process, which is pretty simple. If you get caught up, there's a QR code.
Jordan Wilson [00:40:37]:
Mine somehow just automatically just worked after I did that on each device, and it worked. So at any point, you can go here into settings. Alright. And then I'm trying to remember. I think it's under connections. There we go. So as an example, I have I'm on my Mac Studio here, but I also have connected, my phone, so my iPhone, via the chat g p t app, and I've also connected my, MacBook. So at any time, I can control other devices as well.
Jordan Wilson [00:41:14]:
So my MacBook is shut off and not powered on. Right. But the cool thing is on my MacBook, because my Mac Studio is always plugged in, I can control my Mac Studio from my MacBook at any time. Or vice versa, I can just control it via my phone, and that's the best part. Alright. And let me quickly call out how, again, how minor league and the only reason I said this is because I think I, like, read some comments, on the last Spotify episode and people are like, oh, this guy must not must not use Claude. Yes. I use yes.
Jordan Wilson [00:41:48]:
Y'all I know every feature of everything. This is all I do all day. Right. I know and understand that Claude, has a similar feature to this called dispatch. Okay. But if you're talking about the equivalence dispatch, it's a similar ish feature. So you can control Claude cowork. Okay? Claude cowork.
Jordan Wilson [00:42:13]:
Again, it's three different silos from the Claude mobile app. But it's weird. It's just dispatch and it's one thread. So here's why that's absolutely useless. All right. It's essentially just a, I won't even say it's a two way road. It's a piece of string. Cause the only thing it's really good for is if you have a file on your computer and you need it to send.
Jordan Wilson [00:42:41]:
Right? Because you can't actually work on meaningful projects, in there. And that's the only feature that the dispatch has to control Cloud Cowork. It is not a full control your computer. It's you have access to one thread, and you can go back and forth on that singular thread, and that's it. But if you have everything else, all your other big projects in Claude CoWork, it's not gonna do anything. Right? It's just a dedicated single threat. That's not how it is in, in codex with the, Chad GPT app. You can control everything.
Jordan Wilson [00:43:17]:
Any of your projects you have. One thing, there are some bugs, but the bugs on this are way less than the bugs in dispatch because I've said this multiple times. My dispatch completely broke. I had to uninstall it. I think it's because I literally uploaded a, I uploaded a, Excel file that was, like, six megabytes, and it crashed dispatch permanently. I'd uninstall everything, and it still didn't work. Anyways, this the the the bugs on the Chachibuty, you know, codecs connecting, connection app are very small. Like, that's the biggest one I see is it sometimes won't sync an updated folder name.
Jordan Wilson [00:43:55]:
Right? Big deal. Right? Because I changed the name of a folder, on the desktop, but when I open it up, on the iPhone, it still had the old folder name, but I still went in. I found the thread in that folder, and it's up to date, and I'm controlling it. So, literally, I this is what I did last night. Oh, can I get super dorky? I used codex to open up, Claude in the browser. Because again, you can control the browser. You can control your desktop, anything. Right? I had to go through all of my Claude, all of my chat GBD history and recap everything, put it all in a spreadsheet, and then write me, like, dozens of skills and create dozens of new projects with custom instructions based on my usage.
Jordan Wilson [00:44:40]:
Right? Talk about AI doing work for you. That's it right there. Alright. So let's see. Did we did did this finish? Did this finish? Let's see. I don't think this one, let's see. It's gonna finish. It didn't.
Jordan Wilson [00:44:55]:
It didn't. It's it it it is gonna take it is gonna take a little, a little bit of time. So let me just show you the the finished version here if I can. So, I did run this right before, pretty much the same prompt. I actually added two or three small things in the one that I just did, and unfortunately, didn't finish in time. So this one that did work successfully, the other one will work. It's just gonna take a little bit longer. That's the beauty of doing live demos of generated AI.
Jordan Wilson [00:45:24]:
So this one worked for twenty two minutes, but I added a couple of things. That's why took a little longer. Alright. So if I go click out the side panel let me do this. There we go. And I have all of my outputs here and all of the sources. So, let me go to the bottom and let's just take a look at what this created for me. So it has all of these key links.
Jordan Wilson [00:45:48]:
So let me see. Click this. Okay. Obviously, it's opening all this in a different window. Sorry. This is a little hard to jump around, but here's my, executive readout. Very good. Everything I wanted, all the different guests.
Jordan Wilson [00:46:03]:
My gosh. This is really good. Just one sheet that has absolutely everything. Love that. Here's the Google Slides version. Alright. So it created a pretty, you know, basic looking, but it did the job. Alright.
Jordan Wilson [00:46:17]:
Let's see the Canva doc. See if that worked. There we go. Alright. This looks nice. Here it has the everyday AI guest prep for next week, the executive readout, the Spotify analytics overview that tied to these different guests, the briefing on the three different guests, the current AI context, all this stuff, pretty good there. The delivery index. Alright.
Jordan Wilson [00:46:38]:
Here's all the different, links. So it did go through in StreamYard, created all these. Alright. And then it's, I'm checking in another window here. If I can, bring up these Gmail drafts without, showing too much. All right. Yeah, I can. I can, I can just take it with this person's email, so then it won't matter? There we go.
Jordan Wilson [00:46:59]:
Alright. Check it out there. There is the, the email with the, seven specific questions, the potential title directions. Everything's in there, including the link, to the StreamYard where we would record this. Alright. So amazing. This is amazing. Alright.
Jordan Wilson [00:47:16]:
And then a couple more deliverables as well. Here's a web app. It literally created okay. Look at this. It created an actual web app here. For all of this, it's interactive. Alright. So I can click on it, the overview, the different guests, the analytics that tie to these guests, the sources, the draft emails.
Jordan Wilson [00:47:34]:
My gosh. This is so good. The word doc, I think I already showed this. Yep. There's the word doc. And then also it created a a PowerPoint. So it's previewing all these things, FYI, in the code. So codex has a built in, web browser.
Jordan Wilson [00:47:51]:
So I can, you know, go and actually browse the web, and it also has a built in file viewer as well. So I was actually looking at those, in the file viewer, but at any time, I can also open a browser, as well. So did a great job. Like, my gosh. Like, I can't wait to see when the other one does finish because I did throw a couple more things at it, how much better it is because I'm always iterating, always trying to make things better. Alright. I know that was a lot y'all, but we went live. Sometimes it works perfectly.
Jordan Wilson [00:48:21]:
Sometimes it's a little slower, but it's always worth it. But here's the thing. It doesn't matter if a task like this takes twenty two minutes or forty two minutes. And the reason being is because these types of tasks, number one, I don't even have the capabilities. Right? For me, pre AI to code a little interactive website for all my upcoming guests, like, it's cool. Do I need it? No. Like, I can suffice with a word doc or, you know, the little PowerPoint presentations. Those are helpful as well.
Jordan Wilson [00:48:51]:
But these are tasks that would have taken me easily four to six to eight hours if I was absolutely locked in. But the problem is I can never lock in. Right? I have a lot going on. I have a lot of, you know, great opportunities, you know, being able to talk with a lot of, you know, really cool people in the field. I rarely ever have more than an hour or two to do dedicated focus work. So that's why it's like, okay. If this thing takes twenty minutes, forty minutes, it doesn't matter because I can have all of these things running for me around the clock. I can wake up to the work that used to take me weeks.
Jordan Wilson [00:49:27]:
Yes. I have to invest in the time. I have to stay up with the technology. I have to read the chain of thought. I have to iterate. But once I get it to that point, it's on autopilot. Right? So now I'm probably gonna have this running, at least twice a week. It's gonna look out two weeks in advance, and it's gonna do this exact same thing.
Jordan Wilson [00:49:47]:
I'm gonna go through, look at the next version, try to make it a little bit better, and then settle on it and say, okay. This one's good to go. And that's my new my new routine is I wake up and I see that work that agents do for me. Y'all, I told you this when I did my 2025, you know, prediction series. I said the future of working with AI or or or the 2026. It is front end orchestration and back end taste making. That's what I do. That's what I want you to do as well.
Jordan Wilson [00:50:16]:
And that's where we're at now. This is what we've always wanted. Right? We've always wanted an AI that just does my work. This AI just did my work. Right? I have to provide the instructions on the front end, but it's cutting down the time that it would take for me to do this by at least 90 to 95%. And the output is better. Let's be honest because I'm looking at the chain of thought. It's going to sometimes dozens or hundreds of websites.
Jordan Wilson [00:50:43]:
I wouldn't have had the time to do that level of research, in the high quality that it's outputting in all of these different artifacts that I have saved in there. And now I can just have all of these things running for me around the clock. Alright. So was this helpful? I hope it was. This is one of those ones. Again, you might wanna go to our website, youreverydayai.com. Check the video version of this, and then if you are listening, on the podcast, I always have in the show notes a little thing there that says, join the conversation on LinkedIn. So go do that and repost this.
Jordan Wilson [00:51:16]:
You're gonna get, early access to our co work codex cohort. Maybe we'll call it the CCC because that's a mouthful as well as the codex co cookbook. Y'all, chef Jordan Wilson went absolutely nuttier than a squirrel on keto on this one. The codex cookbook, it is going to be your guide. You are going to want it. I don't sell this stuff y'all. I give it to you for free because I want to be your trusted source, for knowing how to traverse the wild road that is generative AI. So I could be selling all these things for a lot of money, and people would pay for them because they're extremely valuable.
Jordan Wilson [00:51:55]:
This is hundreds of hours of my experience using codecs. I've been using the codecs app since the day it came out in February, and I literally use it around the clock aside from when I restart my computer. So putting some of the best of the best stuff in that we didn't have time to to get to in these two parts, a ton of different use cases, you know, filter it by category, by, level. Right? A lot of different ways that you can use these kind of different, recipes, to get the most out of codex. So I hope this was helpful. If it was, aside from sharing all that, make sure you go to your everydayai.com. We're gonna be recapping the highlights of today's show and a whole lot more. So thank you for tuning in.
Jordan Wilson [00:52:34]:
Hope to see you back tomorrow and every day for more everyday AI. Thanks, y'all.