Everyday AI Podcast – An AI and ChatGPT Podcast - Ep 632: ChatGPT Apps: 3 Hands-on approaches to save time today

Episode Date: October 15, 2025

You haven't used ChatGPT's Apps yet? 🫠Oh.... you like wasting time? Even for free users, ChatGPT rolled out its new Apps mode that promises to shift the future of work. Don't know how to work it? Don't know where to start? Join us as we share 3 practical ways to start saving time today. ChatGPT Apps: 3 Hands-on approaches to save time today -- An Everyday AI Chat with Jordan WilsonNewsletter: Sign up for our free daily newsletterMore on this Episode: Episode PageJoin the discussion on LinkedIn: Thoughts on this? Join the convo on LinkedIn and connect with other AI leaders.Upcoming Episodes: Check out the upcoming Everyday AI Livestream lineupWebsite: YourEverydayAI.comEmail The Show: [e-mail] with Jordan on LinkedInTopics Covered in This Episode:ChatGPT Apps Launch OverviewFile Finishing Friction ProblemChatGPT Apps vs. Plugins vs. ConnectorsSupported ChatGPT Apps: Canva, Figma, CourseraNatural Language Context in ChatGPT AppsProductivity Gains: 70% Faster WorkflowsHands-On Demo: Figma Image EditingCoursera Integration for Inline LearningCanva App Visual Guide CreationReal-Time Iteration within ChatGPT AppsTimestamps:00:00 "ChatGPT Apps: Future of Work"04:04 "ChatGPT Apps Explained Succinctly"07:53 "ChatGPT Features: Free vs Paid"10:59 "OpenAI Boosts Productivity 70%"16:51 Neural Networks vs Deep Learning18:09 "90s Bulls Triangle Analogy"21:06 Mind Map to Notebook Workflow25:40 "Consolidating Nodes with Logic"27:55 "Deep Dive into Canva Connector"33:25 "AI Efficiency vs Human Effort"36:27 "Create Simple 5-Page Deck"37:45 "AI Tools and Design Thoughts"41:10 "Time-Saving Design Strategies"Keywords:ChatGPT apps, AI app store, OpenAI, App Store moment, ChatGPT plugins, GPTs, ChatGPT connectors, ChatGPT SDK, Anthropic model context protocol, AI operating system, integrated services, drag and drop agents, third-party app ecosystem, developer submission process, app monetization, enterprise security, interactive user interface, GUI in ChatGPT, personalized business workflows, digital tasks automation, context engineering, hands-on demos, API updates, productivity increase, app discovery, developer guidelines, app approval process, paid apps, free apps, service feeSend Everyday AI and Jordan a text message. (We can't reply back unless you leave contact info) Start Here ▶️Not sure where to start when it comes to AI? Start with our Start Here Series. You can listen to the first drop -- Episode 691 -- or get free access to our Inner Cricle community and all episodes: StartHereSeries.com Also, here's a link to the entire series on a Spotify playlist. 

This is the Everyday AI Show, the Everyday Podcast where we simplify AI and bring its power to your fingertips. Listen daily for practical advice to boost your career, business, and everyday life. Meet Firefly AI Assistant, now live in Adobe Firefly, the All In One Creative AI Studio. Just describe what you want to create and the assistant handles the rest, orchestrating multi-step workflows across Photoshop, Premiere Express, and more in one conversational interface. You direct the outcome. The assistant accelerates execution. As advanced as large language models have become over the past few years,

there's still a sizable gap sometimes between actually using what AI models spit out. It's a sizable gap and I feel it myself sometimes too. I mean, I have mountains of great information that sometimes lives and dies in large language models. Because sometimes I don't want to copy and pay. and reformat or I might use a third party products inferior AI integration because it's baked in and easier versus the one that I actually want to use because it might require so many extra steps. I call it the file finishing friction, but that could soon vanish. And the gap could close with Open AIs just released chat GPT apps because now if Open AI continues to

support and improve these apps, well, you can natively chat with chat and actually finish those files in the apps where they ultimately live. So less transfer tax, less format fallout, and more just getting work done. All right, we're going to dive into that today. And I'm going to show you how on today's AI working Wednesday. We're going to go over chat GPT's new apps feature and three hands-on approaches that you can start using today and save a ton of of time. All right, what's going on, y'all? Let's get into it. My name is Jordan Wilson and welcome to Everyday AI. This is your daily live stream podcast and free daily newsletter, helping everyday business leaders like you and me, not just keep up with AI, but how we can make

sense of it, actually use it and put it to work for us to grow our companies and our careers. If you're like, wait, that's what I'm trying to do. You're in the right place. It starts here with the unedited, unscripted livestream podcast, but if you want to take it to the next level, You got to go to our website, your everyday AI.com. Go sign up there for our free daily newsletter. We're to be recapping the highlights from today's show as we do every day, as well as giving you all the AI news that actually matters. But what actually matters today is getting you caught up to speed on chat GPT apps. They're launched, they're live and even to free users.

And it is a big step forward, I think, to the future of how we will all work. I did give you yesterday on yesterday's show a little bit of a hot take. on this because I actually think chat gpt apps are going to fail in the short run, but ultimately succeed if opening I does one thing right. So go listen to yesterday's episode 631 if you want that. But on today's show, I'm going to tell you why we think chat gpte apps are the future of work. I'm going to briefly explain to you when and how you use chat gpte apps versus when you

might use something like a connector or a gpt. And then I'm going to give you a couple live demos of three of the best use cases for chat GPT apps that are available now. Because, yeah, there's only seven. So the use cases aren't that great. But I still think it's extremely important. If you are a avid chat GPT user and OpenAI says that there's 800 million of us around the globe, I think it's extremely important to start getting reps in now using chat GPT apps, even though they're not all that great, even though there's only a few.

I do feel very confident that this is the future of work, whether Open AI is the one that actually figures it out or Google or Claude or Microsoft or someone. But ultimately, we are going to be interacting with websites in a chat UI. That's what apps are all about from Open AI. So as a very quick precursor, these are brand new. So maybe if you're like, wait, I use chat chad chvety all the time. I didn't really hear about these.

Don't worry. they're actually not all in your face, right, with sometimes these new features. They're just splashed at you and you can't get rid of them. So you might have missed chat GPT apps, but OpenAI announced them October 6 at their Dev Day conference, and they kind of got buried among some other announcements, some new updates in the API, you know, SORA in the API,

as well as the new agent kit and visual agent builder. So apps didn't get a lot of shine, but, you know, go listen to yesterday's episode. Now I'll tell you why. why I think nobody and I kind of screwed that one up. But let's just give you the very quick skinny here. So what the heck are, chat GPT apps and how are they different?

Well, their native third party experiences embedded inside of the chat GPT window with a graphical user interface. So the seven available right now, and you can interact with them in natural language. That's the big benefit. Spotify, Zillow, Canva, Figma, Expedia, booking.com, and Coursera.

So, I mean, if you're like a market, I think there's some utility there, right? Specifically with Canva and Figma, those are probably going to be the ones or the only ones that I'm going to use consistently, aside from just testing them out and getting my reps in. But they're distinctly different from connectors. So a lot of people are like, wait, what's the difference in GPTs? I went into that a little bit more yesterday. But essentially, connectors bring in your enterprise data. GPTs are kind of personalized or customized versions of chat GVT that you want to create or you want to behave in a certain way.

And then apps are literally connecting to third-party experiences, like using a website almost in your browser for some of the apps. Some of the apps, it's more of like an eye frame or, you know, like a floating embedded video, something like that. But we're going to go over a couple of the different user interfaces. And right now, you know, this is Open AI's third attempt, right, to try to create kind of an ecosystem. Plugins failed, even though I loved them. GPDs have kind of been ignored. So this is, you know, Open AI is trying to do this whole Apple thing, right,

where they can charge, you know, we don't know the fees, but I'm sure it'll be maybe similar to Apple, you know, charging some 20 to 30% fee. Open AI did release a new protocol to bring checkout to chat GBT. So, you know, all the kind of things are lining up, right?

They recently announced a partnership with Walmart, so being able to shop at Walmart via ChadGBT. So I think there's going to be a lot of commerce getting done, just like you do on your, phone just like there's uh you know uh i think there was 5 000 new millionaires last year made uh from apple's iOS app store uh so i do think that this is going to be a uh if open a i gets it right a multi billion dollar endeavor in the first year uh and it's built on top of interestingly enough anthropics mcp model context protocol uh to define the logic and interface and work with the chat context

So who can use it? And well, how? Well, one of the cool things is you don't even have to be a paid customer to use these right now. And there's a reason. And you might be wondering like, wait, I can be on a free plan and use these. Like, why? And how? Well, the how is easy.

And then I'll explain the why. The how is there should be a little plus button inside chat chp t. And then you will go to apps. And then you will, well, actually first, you'll go to add sources. All right. So you click the plus, the plus icon, add sources, go to connect more. Or you can go into settings, apps and connectors, and then browse the apps. And you can choose from any of the seven apps.

You can connect them, kind of like you're installing them. But essentially, you just authorize them. So you have to have, for some of them, you have to have an account with them. And obviously, some of the features might be different depending on, you know, if you have a paid account or a free account. At least these apps right now are free to use, but you might have to have an account. So there's also some regional access issues right now. You know, if you're in the EU, you might not be able to get these right away.

So why can free users get these? Well, remember that thing. OpenAI has this new checkout protocol to complete financial transactions inside of chat, GPT. That's why, right? They want people using. chat GPT as if it was a browser because ultimately they will be collecting money on different types of transactions that happen within chat chvd so they want as many people as possible

using this like a browser right um in open a i we've seen some new uh rumors in rants this october uh that open a i's browser may be around the corner but in the interim they want people using apps just like Apple does, right? That's how Apple, one of their biggest sources of revenue is actually collecting fees and percentages from their app store when people, you know, have subscriptions and there will be subscription apps inside of chat, GBT apps. So yeah, Open AI wants as many people flocking in using these apps, but bad rollout, open AI, terrible rollout, actually. All right, but unfortunately, if you're on a business or enterprise or education plan right now, you don't have access to apps,

although that will be rolling out soon. So what makes it so unique? Number one, it is natural language context aware. And today's putting AI at work on Wednesday. So I'm going to be giving you very specific examples for what that means. Because maybe you're listening on the podcast and you're like, what the heck, I don't get it.

That's some random jumbled words. I'm going to describe it to you. Also, this is one of those ones most Wednesdays. Now, you might want to check out the video version of this. If you're listening on Spotify or Apple podcast, number one, we appreciate that. But you might want to go to our website, Your EverydayAI.com. We put all the videos up there. You can also listen to the podcast there for free.

All right. So you might want to do the video version, but I'm going to try my best to explain this. So number one, context aware, natural language. So it understands the apps, understand the context of your chat up to that point and then after. And then, like I said, being able to iterate something in real time. So if you're designing something in Figma as an example, I'm not that great at Figma. It's a very powerful design tool. I'm way better at Canva.

I'm super fast. I'm very slow at Figma. Right. And I've had to do things in a past with, you know, one of my other businesses, helping clients design things in Figma. And a lot of times I'm like Googling and watching tutorials just to like, you know, change a background color because I can't select it. Right.

So imagine that. being like, hey, change that background color from green to red, or make this vertical design stacked horizontally. It can save you a ton of time. Also, there's inline learning support, and I'm going to do an example of that and tell you exactly what that mean. But ultimately, what Open AI hopes this is, and the most unique feature is huge productivity gains.

So according to Open AI in some of their internal testing, Overall, they saw a 70% productivity increase working in these apps versus if you were, you know, doing the thing I was talking about earlier, the transfer tax, the format fallout, right? Having to constantly, you know, do something in chat, GPT, oh, and then I got to launch another app or another window or a different browser, copy and paste. Oh, it's all wrong, right? It can be time consuming, right? Ultimately, maybe you have something that's a little too tax heavy and maybe you have to

make a design heavy or vice versa, right? Or you can't find the right filter in the program you're working on. Well, it's a lot faster, apparently 70% faster, just doing it natural language inside of chat GPT. So we're going to go over it right now. Today's episode is going to be a fast and furious one. I want to keep these Wednesday ones because I heard a lot of you like these. I don't want to accidentally go 50 minutes, right?

So I'm going to try to make these fast, super actionable and things that you You can literally start doing today, dead simple, even if you're not watching, if you're just listening on the podcast. So the three hands-on approaches, and I'm going to do some demo use cases live here for the live stream audience. Number one, bringing in images or other elements. And I think that's huge. And hopefully I have a fun example that will work to start a conversation.

And I think that's especially helpful using something like Canva and Figma. Because not only do you have to understand large language monitoring, can understand your written context, well, they have a version of computer vision. So they can understand visuals as well, right? So I'm going to do an example of that and hopefully it works. Also, that's hands-out approach number one. Number two, use connectors to enrich the starting point for your chat GPT apps. All right.

And I technically already started that one for the demo that I'm going to show you. Because I did a deep research and it took a very long time, but I'll explain why that was valuable for me. And then number three, you can give personal and professional context to personalize the chat GPT app experience. All right. So those are the three different approaches that are going to save you time. And I'm going to do a quick demo showing you all those approaches. So let's look live. Live stream audience, holler at me if you can see this. All right. Hopefully we can. Let me zoom in a little. little bit here.

So we can see. So the first one that I'm going to work on is actually kind of giving the personal and professional context while using a chat chavit app. And also, we're going to try it out because also these apps are supposed to be just aware of your conversation. You're not supposed to have to talk to them. You know, ChachyvD is supposed to be smart enough. And like if you ask for a course or something, it should not.

know that I'm going to give you Coursera. So we'll see how this works. It's been a little finicky, but, you know, I don't just take what a company gives me. I test it out. I try to break it. So I'm going to start with some context first. Also, I'm using GPD5 Instant.

Never do this. I'm just doing it because I don't want to, you know, wait for, you know, two to five minutes between each prompt because I'm going to be iterating a little bit, but don't use GPT5 Instant. You should probably almost always use, you know, thinking many thinking or pro. All right. But I am saying,

I'm saying I know a lot about generative AI, but I'm trying to learn more about neural networks. And I learn best with 90s basketball references to explain that's supposed to say complex topics. I can't type today. Keep that in mind as we get started. All right. So we're good. It gives me, you know, some 90s basketball references in its reply there, yada, yada, yada. So here's what I'm going to do.

Well, number one, I'm going to put chat. to the test because Open AI says, well, you don't even need to technically talk to the apps, right? It chat chadipatee should know when it should surface an app to answer your question. So I'm going to try this and I'm going to say and I'm even going to say Coursera, all right? So Coursera is one of the apps. I have all the apps installed. So I'm going to say, find me a Coursera course on neural networks. All right.

So let's see how this goes and let's see if it gets it right. All right. So interesting. I did a test on this earlier. It didn't work. It actually just browse the web and found me courses on the web via for Coursera. So one time it worked, one time it didn't. All right. So pretty cool here. Now we have it's not a full like Coursera experience, but it embedded a Coursera course on neural networks and deep learning in the chat window. I didn't have to say anything else. Like I said, I already logged in. And I know this is a good course. This is from Andrew Ng.

So I can start, all right. I can start playing this course. You may not be able to hear it. But I'm going to kind of show you this example of the context. So I already gave it the context, right? And I'm going to start playing this course. Adobe just introduced an entirely new way to create, bringing the power and precision of its creative suite into one conversational experience.

Meet Firefly AI Assistant. Now live in the Adobe. Firefly app, the all-in-one creative AI studio. Powered by Adobe's creative agent, Firefly AI assistant lets you start with your vision, just describe what you want, and shape the outcome as it takes form with the assistant. The assistant orchestrates multi-step workflows, drawing on 60 plus pro-grade tools across Adobe Creative Cloud apps, including Photoshop, Illustrator Premier, Lightroom Express, and more to help bring your ideas to life. You can also get started with creative skills, a growing library of pre-built workflows for common creative tasks, like batch

editing photos, creating mood boards, portrait retouching, and creating social variations. Every step the assistant takes is visible so you can refine, redirect, or take over at any time. You stay in the driver's seat as the creative director. Adobe Firefly AI assistant now in public beta. See it today at firefly.adobie.com. All right. So he's saying, you know, the concept of.

of the term deep learning refers to training neural networks. All right. So right at this point, I'm going to ask Chad chief to your question. And I'm going to say explain the relationship between neural networks and deep learning. So I am a little zoomed in here. But one of the big, uh, the big value ads and time savers and this is me all the time, right? I'm constantly watching, you know, YouTube videos or courses, you know, trying to learn, right, like something.

If I'm having a guest on the everyday AI show, who's the CEO. of a quantum computing company. I'm probably going to go watch a couple of videos, take some notes on quantum computing, right? And a lot of times talk with Chad GBT or Gemini. So in this case, I can go to the Coursera course. Without having to have multiple windows open, I can just talk to chat GBT, number one, about the course.

Just click pause because it's all in the body there. But the big key here is it pulls in the previous context that I shared with it. All right, let's see if it actually does a decent job here. So it says a neural network is a computational model inspired by how neurons fire in your brain, right? Perfect. Then it says deep learning is when you create neural networks with many layers deep in structure. And then it says, so all deep learning involves neural networks, but not all neural networks qualify as deep learning. It's like how every bulls player in the 90s was a basketball player, but only the ones running the triangle offense under Phil Jackson were part.

of something truly deep. All right. It tried really hard for that 90s reference with the language. Probably just should have said. It probably should have said it's like how every player in the 90s, every bulls player in the 90s was a basketball player, but not every basketball player was on the Chicago Bulls. That probably would have been a little bit better of an analogy.

It was really trying to be a little punny there. I also have one of the custom settings, voice responses. is inside chat chabit. So it's trying to be a little overly cheeky with me. All right, but there you go. There's the first use case. So number one, I think and assume that there's going to be other kind of video apps in the future.

I don't think YouTube would ever go in, but I would assume other video platforms, other course platforms would eventually make their way inside of chat chvety. So there's a great example. Start with context before. Watch a course on Coursera. You can go watch my old course, even though I don't recommend it because it's super old. And then ask questions. And it's going to keep the context in from before and personalize your answers as you go as you learn.

All right. So that's use case number one. Let's go straight to use case number two. And this is one that will hopefully work. All right. Let's see how it goes. So this is, I'm going to start with visual context. Okay.

So again, think. This is, you know, for you creatives out there, you designers, you have to think of different modalities when you think of context because it's not just, oh, I share some text and then that text can be taken into account when I'm interacting with an app, right? Large language models are multi-modal by default input and output, right? Google Gemini, a little bit better than chat chfety at the moment. But chat chvety can obviously has a version of computer vision. So here's what I'm going to do in my next, in my next example. So inside of notebook LM, my favorite AI tool, love it. I have a mind map.

So I have some sources. I've been doing a lot of reading and research on kind of this circular funding, this, you know, AI bubble risk. Everyone's talking about the vendor financing, all that. So I put all of my sources into a mind map, which is pretty cool, right? But one thing I'm like, I would use these mind maps so much more if I could tweak them and edit them a little bit. But you can't. But what you can do is export it.

All right. So I have this, you know, this really nice and great interactive, by the way. These mind maps are interactive. A lot of people don't know that. But you can click on like a third level, a third layer node inside a mind map. And then it'll go straight in a notebook LM and you can start chatting with that kind of sub-topic, FYI. But what if I want to edit it?

What if I want to, you know, tweak this? What if I wanted to put this on my website, right? What I would have to do right now is I would have to remake this from scratch and then make my changes, which would take a ridiculous amount of time. All right? So instead, I'm saving this. And now I'm going to go into the Figma app. This time I'm going to show you how to select it since I didn't do it the first time.

I was given Chad Shibati a quiz in it surprisingly. past. All right. So I'm in a new chat window. I'm clicking the plus button. I'm going to more because I've already added these sources. Once you add and authorize them once, you don't have to do it again. And then I'm going to go to Figma. You don't know Figma. Figma is like, it's sort of like Canva, but a little more technical. It's great for wire framing, different user interfaces, right? So a lot of the more professional designers might use something like Figma versus, you know, maybe more not in a bad way, right? I love Canva.

I use Canva all day, every day. I'm probably not a good enough designer to be using Figma consistently. Right? So I'd say your average everyday designers using Canva. So what I'm going to do is I'm going to start with the context. So I'm going to upload a file. All right. So I'm going to upload this mind map.

And I have my prompt ready. So I'm saying, uh, Figma, can you make, can you remake this mind Mac, mind map verbatim with all three layers. Take your time and include every node. Except please change the color scheme to something more bold, some more bold colors and structure the mind map vertically instead of horizontally, right? Because maybe that's what I might want to, you know,

ultimately put on my website or if I wanted to put out an additional guide for our audience to better understand, you know, this AI circular funding phenomenon that everyone thinks this bubble is going to bust. All right. So, oh, this is fun. This is fun. All right. This time it didn't do it.

It's fun. All right. I don't know why. Love when this happens. Let's try it again. I'm not sure why that didn't happen or why that didn't work. Let's try it one more time. I did this once and it worked, y'all.

All right. So let's go ahead and try this again. It's funny. The thing that didn't work. the first time with the Coursera called out work. And the thing that worked in my demos the first time, the mind map didn't work. All right. So I don't think I have to click at Figma because when I added the Figma app here,

the Figma icon appears at the bottom. So this should work. Not sure why it didn't work the first time. But I might have to open up another window here and show you what happens when it does work. I will do that while a figma. Okay, now it's working. Exact same prompt, right? This is generative AI, y'all.

Got to love live stream audience. I'm sorry. Got to love live demos, right? They play around with you a lot. So just like that, Figma is designing. It looks like it's almost done. I'm getting a little,

little spinning animation. So it's been about 45 seconds so far. Again, if I had to remake this, I don't know how to make a mind mapping figma. I don't know. I probably have to find a square, rectangle, duplicated a ton of times, figure out how to draw lines between those. Honestly, it'd probably take me like five hours or longer. And we're done. Sweet. Okay. Pretty impressive, right? So it says, here's your vertical remake of the AI circular funding. So a great example there. It analyzed the

image with computer vision that I uploaded from the notebook LM mind map. And then it recreated it. But not only did it recreate it, node per node, and now it is going to be editable inside Figma, which I'll show you. But it also changed it pretty drastically. It went from a horizontal mind map to now a vertical mind map, and it changed all the colors as well. So I can click edit in Figma, and that pops up a new window in Figma, just so you can see this. And then I can go in and, you know, do whatever I want, right? But let's, I don't know, let's try something different. I'm going to try to say, let's consolidate the four second layer nodes into two.

I'm going to say, do your best to combine them in a way that makes sense. I don't even know if this part is going to work, but let's let's push it to the, let's push it to the edge. And I'm going to say also, let's do shades of green. All right. So again, try to iterate with natural language. So I don't know how this is going to work because I'm actually kind of requiring the model to use a little bit of logic. And I'm on the chat chbtv5 auto mode.

And I don't know how well Figma can handle that type of logic. But looks like it did. And it's already done. All right. So it did narrow it down just like I said. And it actually did a good job. And I see what it did. Because previously, as an example, there was a market outlook like bull view was one.

And then there was a market outlook, bear view. And then it combined them, market outlook, bull and bear. So did a good job. Logically, combine these four kind of second layer nodes in the mind map into two. And then brought in also did some combining and consolidating on the third layer. So really, really good. Right. And if you've ever used Figma, this right here.

I mean, the canvas stuff, I mean, I'm super fast in Canva. My stuff's ugly. So maybe it'll help me make less ugly designs. But the Figma one, cheat codes, right? I can see the, you know, that 70% productivity. That's, that's huge. That's huge. I actually think the Figma stat, let's see, I think I had the Figma stat here.

Let's see if I, if there was a specific productivity gain. inside Figma was there? No, but Canva, it said 400% faster designs. So let's do that one last. That is our last kind of time saving feature. So let's go ahead and this is one. Okay, this is one I already started on because it would take a long time. So I did a deep research run in my connectors.

All right. And if you're confused, y'all, this. This is why you got to listen to the show every day. I can't explain connectors for another 30 minutes, but you can connect different app sources. So Canva technically has a GPT that stinks. They have a connector, which pulls in your data,

which is great, and then they have the app. So I use the Canva connector because I have every single day on the live stream version of this podcast. I use Canva to create a little deck with some notes and some visuals. So I literally had a deep research run that chat GPT went through doing only

Canva. So it went through hundreds of Canva documents. In this version is I'm using this hands-on approach is using connectors to enrich chat GPT apps.

So it took a long time. It took 16 minutes for it to go through. And I essentially asked, I said, please carefully look at the month, at this,

the last month of everyday AI Canva docs. please slowly and thoroughly scan each page and give me the 20 most specific detailed statements about the state of AI, new trends in development, et cetera. So it looks like it did it. It went through 29 sources, which sounds about right over the last month,

because some days I'll have multiple. And it looked at every page. I know it did because it didn't just look at the front page of my Canva designs because my front pages are cover pages. And it wouldn't have pulled any of these things out. So it did a great job. And it found 20, 20 nice trends. All right.

I'm looking at these. I'm like, these are pretty good. And okay, how is this a time saving thing? Well, guess what? I'm probably, and by probably, I'm definitely going to use this content here. Because this is what I do constantly, right? I'm trying to connect and spot different trends that are happening in AI.

And I kid you not, y'all. And this is embarrassing. I'm constantly doing research and chat, chitpity, deep research, perplexity, Gemini deep research, right, all these things. And almost every single time that I'm doing a very specific deep research on something, my content is some of the content that comes up. It's a problem for me. I forget a ton.

Right. So you might be saying like, oh, why would you ever do this, Jordan? Like the last 30 days, you can't just, you know, connect the dots. You can't, you know, spot these trends. Absolutely not. Absolutely not. I consume so much AI information. I have to spend a lot of time using AI to help me understand and learn AI, but this is a great way.

I'm seeing some connections here that found in these 20 points, these trends that were not necessarily individual facts and stats. It actually connected unrelated, technically, news events and spotted trends, which is great. So we have a good thing here. So anyways, I did that with the connectors. So this is the third kind of approach to save a ton of time. Now all I'm going to do is I'm going to call on the app now. All right. So because I previously had my Canva connector, all right, I clicked the plus icon.

I added the Canva app. And then I said, all right, I said Canva, please create me a five page visual. guide on the latest AI trends based only on the data above. Again, I'm working with the context window that I gave it. That was this deep research run across all of my last month's documents, 20 sourced and cited facts, stats, and trends. And then I said, it's up to you the best way to categorize these trends, but please include all of them. Be pinpoint specific and priority. clean design with bold typography. All right.

So again, y'all, 10 years ago, if I was working with a designer, this is probably something I would say. I'd be like, hey, here's a bunch of information. Here's what I want. I want a five page guide on the latest AI trends. It's up to you first stab. However you want to put them together, go ahead. I want something that's super clean design, bold typography, right?

And then I essentially said, please don't ask any questions and complete this task autonomously. So the cool thing is now, I can. can see it working. And this is not an easy task again. This is something that would probably take me a couple of hours, even though I'm pretty fast in Canva, right? Number one, I'd have to find maybe a template.

I wouldn't use the same kind of everyday AI daily episode template because this is much different. I would probably want to try to make something really cool. And that looks really nice. So I probably spent some time going through templates, adjusting it, you know, and then a bunch of copy and paste, right? This is the point where I would be paying that transfer tax, right? The formatting fallout. So I have done this demo quite a few times, obviously, because I'm doing this live. Thanks. Demo gods. It's taking an arm and a leg forever. And I say that, which I should probably kick myself, right? It's been two minutes. And I'm like, oh, how dare you know,

how dare this, you know, Chad GPT app and this incredible AI technology take more than two minutes for something that would probably take anyone else two hours, right? Let alone, if you were creating this from scratch without templates, I mean, it would take an entire day, probably longer, right? Even thinking before Canva, imagine having to do this in like, you know, Photoshop or illustrator or in design or something like this. It would take. take forever. And it's a huge gamble because, well, what if it just stinks, right? What if it's not very good? All right. I have no clue what's going on because I've done this before. All right. So I'm actually, I'm going to hit refresh on the page. Maybe it was done and maybe it's just a rendering

issue. Like I said, these apps are brand new. They haven't even been out. They barely been out for like a week. And they can get a little buggy. The Canva one has actually been one of the more consistent ones. but let me just go ahead. I'm going to click the old refresh on the page there. And sometimes it'll actually show up rendered. All right. Awesome. Awesome.

All right. So now, now, now here's what we're going to do. All right. I'm going to have to open a new app. All right. And I'm going to bullet point here. I'm going into chat, GPT. I'm going to say bullet point the five biggest trends in AI

in 2025 and give me three bullet points for each love typing and redoing this live but y'all when i say this is sometimes the realest thing in artificial intelligence let's be honest when you're working with generative i i this kind of stuff happens i don't want to give you some unrealistic expectation right i'm not just pushing a i down your throat sometimes it stinks right sometimes obviously i'm not doing proper prompting techniques because i'm doing this live and i hate typing live um But sometimes things go awry. All right. So it's going.

Chat ChaptiD is doing a little, little bit of research, right? I'm looking at the, the chain of thought summary here. I want to pop back in on my, on my other Canva. I don't know.

Maybe, maybe Canva's broken, right? Everyone just discovered chatypD apps and cams broken. All right. So it looks like my new window. All right. So working on,

on two things that, once here. So I'm going to get ready for once it's done. And I'm going to tell Canva, I'm going to say, please put this in a simple Canva check, five total pages, everything. Design wise is up to you. Let's see if we can actually complete a demo for the Canva app. All right. I have some custom instructions that always give me sources and always has to double check everything. That's why I took a little longer. Get rid of the hallucinations like me, right? All right, here we go.

So now I'm saying, please put this in a simple Canva deck, five total pages. Everything design-wise is up to you. It's connecting to the Canada app. So we'll see if this one is a little bit better. Maybe the task I gave to the other version, you know, taking a new account that 16 minutes of research. Maybe I pushed it a little too far, even though I did the exact same demo and it took like two minutes.

I don't know. Just my luck, I guess. You know, jumping back over there, refreshing. Nothing. Nothing. We might have broke Canba, y'all. If so, that stakes. But we'll give this, we'll give it another 30 seconds.

But let me go ahead. I'm going to wrap. All right, I'm going to wrap. I don't want to the audience here to be waiting for 30 minutes for Canva to decide if it wants to finish or not. But as we wrap, I'm going to keep my eye, keep my eye on the Canva. But if not, I'll share it in the newsletter. If it does eventually finish, which I assume it does.

But the ending to this, which is actually the best example in Canva, is being able to iterate on something. And I'm actually at a test now if just Canva in general is broke. I'm going to say, you know, make me a poster. for everyday AI, right? So I'm going to see if Canvas is just broken. Might be broken. But one of the best things about using the Canva app specifically is the ability to iterate in real time, very similar to Figma. So I think this first kind of rush of these seven Chad ChbPT apps, not a ton of utility, if I'm being honest, right?

All these like booking sites. I'm like, come on. Like it, they still kick you to finish the booking process to the actual website. So I'm like, those are a waste of time. You know, the some of that next ones that are coming out, right? There's another wave that are coming out. Maybe that second wave. I think there's 11 of them will be a little bit more useful.

But I think for for the most part, unless you spend a lot of time putting together Spotify playlist, which I do, but I kind of enjoy that. But otherwise, I think the ones that you're probably looking at right now for the most business utility are Coursera, Canva, and Figma. All right. Good news. Good news. Two of our three finished. All right.

So let's go back. So here we go. The top five AI trends, right? It gives you actually four different versions. So this is the second prompt I ran. you know, um, you know, look up 2025 AI trends. So I can click one. All right. And then it's going to bring a full page view. And this does look very Canva ask, right? And from here, I can open this in Canva and edit every single thing. All right. So, uh, let's see how it did here. I did okay. Um,

some of it was just like random words and there weren't a lot of stats. So that one stinks. All right. This next one. not that great. All right. This is, this is crazy. This is crazy because like a lot right before I sat down to hit record. I ran this.

It worked really well. So this top five AI trends not doing great. Chat Chb-T apps integrated in communication platforms, right? So it's talking about itself. Good job. Open AI chat. All right. So gave me some stats here.

9.4% global PC shipment increase. So yeah, not great. Anyways, I can say iterate with Canva and I can say, you know, make this page, you know, less busy and Volder typography. Right. So I can literally just go into any, any certain part of Canva inside the app. So yes, I can obviously click the open in Canva. And in this case, I would have to do it because this Canva app pretty much failed on

this. And oh, just great, just great. I give up live demos, y'all. AI working Wednesday is officially canceled. It's not. Anyways, uh, once, once this is working a little bit better, we'll have to do a full dive. But that's it. That's a wrap. Sometimes the live demos get me, y'all. But I hope the front half of this was helpful going over the three hands-on approaches to save a ton of time. So like I said, bringing in images and visual elements, taking advantage of the computer vision, working as the context inside of Chad ChbT.

The Figma example worked great, giving the personal and professional context that worked really well inside of Coursera. And then the last one that kind of stuck and failed, right? The first half was good, using the connectors to give Chad ChbT context, but the iterating with the Canva app didn't work as well in our live demo as it's been working for me the last.

week. Go figure. Anyways, I hope this was helpful. If so, please go to your everyday AI.com. Sign up for the free daily newsletter. I'll actually be sharing. I'll find the example that actually worked in the Canva deck and maybe share it in our newsletter. So thank you for you tomorrow and every day for more everyday AI. Thanks y'all. Meet Firefly AI assistant. Now live in Adobe Firefly, the Allman One Creative AI Studio. Just describe what you want to create in your own words and the assistant handles the rest, orchestrating multi-step workflows across Adobe Creative cloud apps, including Photoshop, Premiere Express, and more in one conversational interface. You direct the outcome while the assistant accelerates execution.

Stand control with the ability to step in and refine at any time. See it today at firefly.adobie.com. And that's a wrap for today's edition of Everyday AI. Thanks for joining us. If you enjoyed this episode, please subscribe and leave us a rating. It helps keep us going. For a little more AI magic, visit Your Everyday AI. and sign up to our daily newsletter so you don't get left behind.

Go break some barriers and we'll see you next time.