Everyday AI Podcast – An AI and ChatGPT Podcast - EP 593: Google Opal: The Simplest Vibe Coding Ever? How to Use It

Episode Date: August 20, 2025

There's millions of people who want to vibe code -- but don't know where to get started.After all... vibe coding tools often are still full-stack enterprise powerhouses with a steep uphill learning curve. If only there were a simpler vibe coding platform that didn't even have code. That's Google Opal. And for this rendition of AI at Work Wednesday, we show you how to use Google's Opal to create simple apps that tackle some of your most repetitive, redundant tasks.Newsletter: Sign up for our free daily newsletterMore on this Episode: Episode PageJoin the discussion: Thoughts on this? Join the convo and connect with other AI leaders on LinkedIn.Upcoming Episodes: Check out the upcoming Everyday AI Livestream lineupWebsite: YourEverydayAI.comEmail The Show: [e-mail] with Jordan on LinkedInTopics Covered in This Episode:Google Opal Vibe Coding Tool OverviewHow to Use Google Opal: Step-by-StepOpal vs. Cursor, Replit, Copilot ComparisonBuilding No-Code AI Apps with OpalGoogle Opal Natural Language Workflow CreationOpal for Task-Based AI App DevelopmentGoogle Opal Beta Features and LimitationsPrebuilt Google Opal Apps and TemplatesVisual Editor and App Sharing in OpalOpal’s Integration with Gemini AI ModelsTimestamps:00:00 "Everyday AI for Business Leaders"04:34 "Opal: Easy No-Code AI Apps"07:33 "Validate Ideas Before Full Development"11:25 Interactive Canvas with Chat Integration14:36 "Podcast: Interactive Instruction Feature"19:13 Efficient Research for Timely Episodes22:16 "Real-Time Deep Research Process"24:20 "Trends in Smaller Language Models"29:05 Improving Podcast Visual Strategies30:58 Remixing Apps with Google Opal35:45 "No-Code Opal Revolutionizes MVP Development"37:11 "Opal Tool Demos for Users"Keywords:Google Opal, Opal vibe coding, vibe coding tool, no code AI, Google AI, Google Labs, natural language app builder, AI app generator, AI workflow automation, task apps, visual app builder, Google Gemini, Gemini app, AI chaining, Google AI models, Gemini 2.5, Gemini Pro, Gemini Flash, AI image generation, VO3, audio LM, Lyria 2, multimodal AI, deep research, interactive web application, app editor, Opal gallery, prebuilt AI apps, app remixing, AI output customization, AI for nontechnical users, AI chaining tools, Google Jules, Cursor, GitHub CopilotSend Everyday AI and Jordan a text message. (We can't reply back unless you leave contact info)

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. I still think that vibe coding has barely caught on.

Yes, it's one of the trendier words in AI in 2025 so far. Yet, I think there's literally hundreds of millions of people that would probably vibe code a lot more if there was a simpler entry point. Sure. There's software like cursor and GitHub co-pilot and so many others that are actually very easy to build full stack apps. But what if you just need something simple or a way to dip your toe into the vibe coding waters? That's exactly what we're going to be going over today in Google's newly released Opel tool. And what I think is the simplest vibe coding tool ever. I mean, talk about no code.

There's literally no code. So in today's show, we're going to go over different ways that you can use it. And I'm going to show you live how to do just that. So on today's show, we're going to go over the basics of Google's free Opel vibe coding tool. We're going to compare it to other vibe coding platforms like cursor, GitHub copilot and Replit, and show you live how it works. All right, I'm excited for today's show. I hope you are too.

What's going on, y'all? Welcome to Everyday AI. My name's Jordan Wilson. and everyday AI, it's for you. This is your daily live stream podcast and free daily newsletter, helping everyday business leaders like you and me, not just learn what's happening in the world of AI, but how we can leverage all of this to grow our companies and our careers.

So if that sounds like you, what you're trying to doing, it starts here with the unedited, unscripted, live stream and podcast. But if you want to take it to the next level, make sure you go to our website at your everyday AI.com. There, you can sign up for our free daily newsletter. We're going to be recapping the highlights from today's show. So if there's something, maybe you're listening in the car, out on the treadmill,

maybe there's something you hear and you're like, wait, what was that? You can always check in our newsletter, as well as we keep you up to date with all the other news happening in the world of AI. So this is going to be one of those that's a little bit better for our live stream audience watching the video. But if you're on the podcast, you can always go to our YouTube channel or our website, like I said, Your EverydayAI.com and watch the video of this. This is going to be a little bit more visual, but I'm going to do my best to describe this to our podcast audience.

And speaking of audience, when I say your everyday AI, it's yours. This is, you know, we started this new AI at work Wednesdays showing you ways that, you know, we're using AI internally. And I said, what do you all want? And you voted for Google's new Opel tool. It was actually pretty close between a couple different tools there. But let's get straight into it. And also, I did put together. a list of 20 ready to go Opal apps. So maybe after today's show, you're like, wait,

that sounds interesting, but what are some ways I could use it? So go repost this show on LinkedIn, and I will send you access to those. All right. So let's get into the basics. What the heck is Opel? Well, it's a free vibe coding tool released from Google. And it's much different than these other kind of vibe coding tools out there. Technically, Google has like five different ways you can vibe code. And I'm going to be comparing Opal with some of the other more popular ones, mainly jewels and some other very much more fully featured vibe coding tools like Cursor and Replit and others.

But for the most part, it is a completely new way to build apps. Okay. So the way that Google says it, it says you can build at it and share. multi, sorry, build edit and share mini AI apps using natural language. So, you know, a lot of these vibe coding tools, when people look at them, right, like lovable and bolt and cursor and all these other ones. And it can be a little daunting because you're like, wait, I thought this was like a no code thing. Like, why do I have this entire repo and I'm having to, you know, make these MD files and like, like, what the heck is going on? If, if you've ever felt that and you just,

want to like experience something for the first time. I think Opel is great for that. It is free. If you have a Google account, that's all you need to get going. And you can literally, and I'm not exaggerating this, you can build a fully functioning app that you can share with others. And it works in like less than a minute. So I'm going to do something a little more complex, but let's dive into a little bit more an overview of exactly what Opel is and how it works. So like I said, right now it is free, but it is experimental inside Google Labs. So I believe the last I read, it's only open in the beta only so you can opt into it on Google Labs. And right now, it's only available for the US.

I will double check that because Google is literally shipping things like daily. So I will make sure to double check that before we put out today's newsletter. And essentially, natural language. You just tell Google what you want it to build. and it's going to build a visual multi-step workflow that you can go in and edit later, and it chains together different prompts, model calls, and Google Gemini tools. That's a great thing. Essentially, anything that Google Gemini has released, you can use that inside of Google VOPOL.

So if you've ever seen maybe, you know, the V-O-3 video generator or the Imagine 4 or just any of Google's models, right? They have the top-end Gemini 2.5 models, and you're like, wow, I wish I could build something. on that while you can. And it takes literally less than a minute to build something extremely basic or you can spend a little bit more time modifying it. So users can edit workflows via a conversational command or a visual editor. Then you can test and refine your apps and finish apps can be shared with others who also have an Opal account.

So yeah, you can't just, you know, share it publicly. You do have to share it with anyone that has. also signed up for Opal, but like I said, all you need is a Google account right now in the U.S. takes less than a minute to get up and running. So my biggest takeaways, I've been using it since it came out on some of my different accounts. If you think that you're going to build your next SaaS or your next iPhone app with this, that's not what it's for. I like to say this is great and the best for task apps, right? So I think a lot of times when people think about vibe coding something.

They're running into an issue and then they think, okay, I need to build a fully functioning web app for this or, oh, this could be an iPhone app, right? Whereas maybe first you need to validate it just quickly, like can it be done? Is there a market for it? Or even maybe you're just like, let me just build this for myself. Maybe it doesn't need to be a full stack with a back end, login pricing, users, a dashboard, right? Maybe you don't need all that.

Maybe you just need to build yourself something that's going to solve. one of your problems immediately. And I think that's what Opel is great for. If you go back and listen to my 2025 AI prediction and roadmap series, I said non-technical people are going to be building themselves apps just to solve their daily issues. And I think Opel is the one for that because it is dead simple, right? In the same way that I think Notebook LM has changed the way a lot of people work,

even non-technical people. I think Opel might be that tool that does it for non-technical people that you can just code task apps. That's what I call. These aren't full stack, fully customizable, right, where you can, you know, change every pixel. It's not like that. These are more task apps. They're not highly customizable.

But I think if you just reframe your brain into like, okay, do I just need, you know, an AI tool that can do something for me that's repetitive. And I don't really care about how it looks, but I do have some customizable, the ability to customize how it functions. That's what Opel's for. And by far. I think this is the easiest way to vibe code away nagging problems for everyday people. And I'm going to give you an example of something that I've started to use it for. And I'm going to continue to refine it for myself as well. So like I said, Opel is free.

You don't need to pay for API usage or hosting. That's the other thing. A lot of times if you're trying to build an AI app, you have to connect it and pay for that AI usage. Right. So if you're using open AIs API or Claude's API, right, you have to actually pay for it. you're not paying for it inside Google Gemini. Right. I've been saying this since Google's AI studio came out.

It's like I feel like I'm robbing Google whenever I use it. Same thing with Opal. The fact that I can create an app that has Gemini embedded. I can use anything Google, essentially anything that Google Gemini has released and it's free. Of course, it is in beta. It's experimental. Right. So that doesn't mean it's going to be around in five years.

It might get folded into other products. But right now, I mean, I've been talking for eight minutes. You could have already built multiple AI apps that solve it. And this is the most no code vibe coder there is, mainly because there's literally no code. All right. So let's start live, shall we? All right, live stream audience. Do me a favor as always.

Let me know if you can see the screen. So this is, I started on one of my other accounts. So not littering your screen with a thousand things. So here's what we're going to do. When you go on to Opel, you'll see it's an experiment. You have to be logged in. So please follow along live for our live stream audience. Or, you know, if you're in the podcast, you're in your car, hit pause, jump back in

in in front of your computer. Let's vibe code some stuff together. So when I log in, all I'm going to do is go click create new. All right. And there's different ways that you can. can create a new app inside Opal. I'm going to show you one way, uh, and then I'm going to show you the other. And I'm not going to fully build the app out the first way.

I'm just going to show you how it functions. So, uh, for our live stream audience, you'll see and hopefully, uh, podcast audience, uh, I can explain this easy enough. So right now, there's two different pains. So the main pain, it's kind of like a canvas and I can also chat with Opel, uh, in this canvas view as well. And then on the right side, I can. actually preview the app. It's going to build it and render it as we go, which is really cool.

So if you're used to using, you know, canvas mode in Gemini or Chad GPT or artifacts in Claude, it's the same thing. You kind of chat on the left side and then you can see things rendered on the right side. So a very familiar interface. However, the big difference here is now there's essentially like a canvas, a whiteboard that you can actually drag things and build. So essentially you have user inputs, you have Generate, which is the Google Gemini capabilities, and then you have an output. So then you can also add different assets. You can upload files connected to your Google Drive, YouTube, text drawing, et cetera, right? So we're not going to get into assets. I just want to show you the two different ways that you can build an app. So one is you can do it

more manually by just clicking these assets and dragging them around the board. So as an example, I can click user input and our live stream audience will see. Now there's a bright yellow box and it just says user input. Right. And then I can go in and select it in the editor. So then on the right side, I can click the at key and then I have different options. Right. I wouldn't do these for the user inputs because for the most part, user input is going to be a text command from me, the user.

So keep that in mind when I'm building this. The user input is what the person using it, which is probably going to be you or your team. is ultimately going to put in. So I can type in different commands there. I'm going to leave this blank. I'm just showing everyone an example of how this works. All right. And then I have Generate.

So here's where the magic happens. All right. So this is all the different capabilities inside Google Gemini. So I have different models here. So I can choose different models. I can do Gemini 2.5 Flash pro. You can do in-depth research. You can plan and execute different tasks.

Here's imagine four. Google's a state of the art AI image generating model. There's audio, LM. You can generate speech from text. There's a VO. I don't, I'm not actually sure if this is VO3 or two. I will have to reach out to my friends at Google and double check that. And then you have Leria 2, which can create instrumentals from text.

So talk about a literal creative sandbox here. Right. So think if you've ever been using a large language model and you're like, man, I wish when I type something in, I could. get video out or an image out or, uh, you know, an instrumental out, right? Now you can and it's literally just on a drop down. All right. Uh, and then essentially what you would do to connect these things is you drag an arrow

from your user input to your generate, right? I have to actually, uh, connect that. There we go. All right. And there we go. Sorry. Didn't get a little, little backwards there. Okay.

So we have our user input that sends the. user inputs to the generate tab. I choose what I want it to do. All right. And then I can, you know, type in instructions, right? So, you know, I can say, you know, take the, take the user input and that's a selectable item and use, you know, Gemini 2.5 flash to blah, blah, blah, blah, blah, blah, right? And then all I have to do is click outputs.

All right. And then I drag the generate to the outputs. So it's simple. podcast audience think i have three little things up on a whiteboard user input it gets sent over to generate uh inside generate i can choose what google uh capabilities i want and that gets sent over to an output and so i essentially have an app not none of this would work yet i'm just showing you the two different ways that you can build it so that's way one but i say do it the other way it's way easier you just type something uh and describe what you want to build

Okay, so I actually have a little prompt here and I'm going to put it in and we're going to get it going. So here's what I said. And we're going to watch because it's going to be built live, right? So now I'm telling Google how I want this to be built. And actually it might take a minute or two. Actually, no, I lie. It's done. My gosh, that was fast.

All right. So it's very, it's very impressive. All right. I could even explain what I wanted to be built, uh, because it's already built. So you'll see now I have a user input. Uh, I have a multiple step, uh, generation process and I'll explain exactly what's going on. So there's some, some simple conditional logic here. All right.

There's four different processes, uh, four different generates and then it gives me an outcome. And I literally have an. app ready. All right. So now in the right hand side, it built an app. Like I said, these aren't apps that you're going to be building and, and, you know, moving things around pixel for pixel. For the most part, I mean, you have a little bit custom, like a little bit, uh, uh, customization options, uh, right. You can go in and create a certain theme again with AI. All right. So I'm just going to go in and, uh, all right. Let's see here. All right. I'm running into an issue. I think it's because when

was clicking around. All right. So actually what I'm going to do, when I was clicking around, I accidentally disconnected one of the nodes. So I'm just going to redo that app. Bam. And it's going to cook here in a second,

but in the second, let me actually take a quick pause. Halftime break. 30 second half time break. Word from our sponsors. This podcast is supported by Google. Hey, everyone. David here, one of the product leads for Google Gemini.

If you dream it and describe it, V-O-3 and Gemini can help you bring it to life as a video. Now with incredible sound effects, background noise, and even dialogue. Try it with a Google AI Pro plan or get the highest access with the Ultra Plan. Sign up at Gemini.com to get started and show us what you create. All right. Yeah, in that 30 seconds, obviously Opel rebuilt the app that I accidentally screwed up there. All right, let me just go ahead and tell everyone exactly what I told Oval to do. This is putting AI to work at Wednesdays.

This is something I'm actually using and I like it. So I said, I want to create a simple app called a podcast episode outline generator for my podcast every day AI. Give the app either, I want to be able to give the app either a basic or a specific topic and it will do very specific research for me that is timely and relevant. It should first start by searching Google for the topic I want on today's date, then this week, then this month, then prior months. So I'm giving it directions on how I need it to search because if I'm using this

to help me plan in research episodes, I need to make sure I'm researching today's news first, then this week, because I don't want to be researching stuff from months ago. It's very old. Then I say, uh, being fresh and timely with information is paramount. Essentially, I'll give the app a topic. then it will give me three different episode topic ideas and outline what should be covered. The three ideas should be different from each other. The outline should include a suggested title, five major topics to cover in each episode,

and factual bullet points of each of these topics. It should also use Google's Imagine to create a visual for each suggested episode. The app should be easy to use and interactive. All right. So it's obviously done. So essentially now I'm back on the kind of whiteboard version and I have my podcast planner on the right side because I'm in editor mode. But I can click app mode and that essentially launches this very basic app full screen. But let's go back into editor mode and explain a little bit of what happened.

So it took my prompt and it created this app in this kind of like whiteboard version. right? And I can go in here and I can edit things and refine them a little bit as well. But essentially, I can go in. Let's zoom in a little bit here to see exactly what's going on. So on the user, sorry, I'm not used to using this on my, uh, it's, it's a scroll thing. I wish I could click and drag, but it's a little different. So essentially on topic, this is the user input. So, uh, the user enters the podcast topic. Then, uh, it takes that topic and it carries that topic over, uh, to the three different generate tabs. So it's doing multiple steps of research and it's passing it on to each of

the generate tabs. And then in the end, it's creating an interactive web application. So again, the input is the podcast topic. The generate using Google Gemini, it does three different steps of researching and passes the information onto each different step. And then last but not least, the output is an interactive web application. Pretty cool, right? Let's see if it works. All right. So I have something already typed up.

So let's use the app mode. And I'm going to click start. Okay. So all it is, it now there's no, no fancy visuals, no animations. This is straightforward. That's why I call this more of a task app builder. And it's not a traditional fully featured, you know, full stack. you know, agentic coding tool.

All right. So all I'm doing is now putting in a simple prompt. And what it's showing me right now, it's conducting deep research. And I'm actually going to skip over to editor mode because it's a little more fun to watch here. Because you can literally watch as it takes my query from step to step. So it's in the first step right now. So the first of those three generate tabs is highlighted. And I can see it says conducting deep research.

So on those different modules, one of them was doing a version of Google's deep research. So this is great. This is the normal process I do. The way I normally research a topic is I will manually start typing out my ideas, my bullet points, you know, facts from the newsletter, et cetera. And then I'll send those to Google's deep research, open AI's deep research, Claude's deep research, right? And then I take all of that information and then I'll start organizing. it first myself i'll say okay based on all this i'll start browsing it and i'll start outlining it and then i'll send my a rich initial outline uh and all of this deep research uh over to different

a i tools to help me start outlining my shows right uh it's a very collaborative process i usually ultimately use open a i's canvas or uh um jemini canvas so then i can do a more interactive um element with the uh the i so now already it's moving on to the second step. So you'll see right away. You might be wondering, okay, why is this taking so long? Well, it's not because it's literally doing a multiple steps of deep research. All right, we're already now it's creating images. So now I can see the third of the three generate icons is highlighted. So I know I know right now it already did a bunch of research. It made those podcast ideas. And I assume right now what's happening because I can see it's highlighted. It's,

using Imagine 4 to create visuals as well. And now it's on the last step in the output. And it's creating an interactive kind of web app just based on the prompt that I sent. And the prompt that I sent, all my topic was quarter three, 2025 trends of smaller language models like Google's Gemma 3 270M, which just came out this week. and Open AIs GPTOSS 20B and the rise of Edge AI. So I do want to do an updated show sometimes soon on kind of this rise of the smaller language models.

They're getting much more powerful, much more robust. So I literally just built an app, customized it with natural language, and it went out, did a bunch of research, put it together how I wanted to. It should give me three different episode ideas based on my topic I gave it. It should bullet point factual information on those different episode ideas. And it should also give me some image art, right? So it's probably not image art that I would actually use, you know, on a zero shot. I would probably go in after the fact and use it a little bit.

All right. So it's done. It's done. That was pretty impressive. All right. So now I'm going to drag. I'm actually going to go in full app mode. So hopefully our live stream audience can see this.

This is pretty, this is pretty cool. All right. So I have the three different ideas here that this, this is really, really cool. I'm just cheesing a podcast audience because, man, I like this, this technology is really, really impressive. Okay. So I have the three different episode ideas. So one, it says edge of innovation, how smaller AI models are reshaping, order 3, 2025.

The second one, it says Gemma 3-270, Google's Tiny Titan of on-device AI. And then the third one, it says, open AI goes open, the GPTOSS 20B, and the future of accessible AI. So it looks like I gave it kind of two examples. So it built out episode ideas on the two examples, and then it made more of a general one. So right now, I had this kind of interactive, almost like a little miniature website. The three episode ideas, when I hover over them, I can tell there's more information. So when I click on one, okay, let's see if I can click on them all.

Okay, cool. I can't click on them all at the same time, which is pretty nice. So each of these, it should have at least five bullet points. One, two, three, four, five, six. It gave me six and that's fine. Oh, no. Oh, gosh. Okay.

It gave me a ton, a ton more information than I even asked for. So it looks like it gave me different categories. So let's just walk through. the edge of innovation, the first one, how smaller AI models are reshaping quarter three, 2025. So give me five different categories. And then in each of those kind of categories, it bullet pointed additional information. So it says first, the rise of small language models. Second, edge AI. Third, the convergence, small language models and edge AI synergies. The fourth, industry transformation in real time impact. And then privacy, efficiency, and accessibility. So pretty

good. So I'm actually going to look now at the GPTOSS version because this is the only one I've done a dedicated podcast on. And I want to look at the quality of research here. So it says the GPTOSS 20B model was released on August 5th. That's correct. It's available under the permissive Apache 2.0 license. Correct. Allowing free building, customizing and deployment without restrictive copyright. It marks OpenAI's first open way language model released since GBT2. Correct. signifies a strategic re-collaboration towards an open source strategy responding to growing open source AI community and competition. Correct.

CEO Sam Altman indicated consideration of a different open source strategy. And yeah, this is all really, really good. So this right here is something I'm going to be using all the time now because this is something this multi-step process is something that I've been doing manually. Right. I would obviously go in and refine. in this, I essentially just zero shot at this thing, right? Or one shot of this thing.

I gave it a very simple prompt, no going back and forth. And it did a pretty good job. And then it also gave me these different visual concepts down here at the bottom. None of them are breathtaking, right? But it just pulled together some different visuals based on the content. So nothing that I would probably use for the most part. I mean, there's a couple of these I might use like in an infographic or on a blog post. Nothing's blowing me away per se.

But again, all I did is say, make me some images, right? If I was more descriptive on the type of images, the style, what I would be using it for, I would assume that these visuals would be a lot better. But here you go. I essentially, for each and every podcast idea that I have, I can go get multiple different angles that I can tackle this from. Some of my base research has already done for me. And although these visuals right now might not be great.

Eventually, they might. Right. I can spend some more time, be a little bit more descriptive, and then I can go in and edit the app as well. So as an example, now I'm going back into the app editor and I'm looking at what it built. So again, all I did, natural language, but I can go back in, click any of these modules and edit them as well. So as an example, the generate podcast images. I can go in and see exactly what's happening. So I can go over here on the right hand side. And it looks like it used Gemini 2.0 flash. image generation. But maybe I want to use Imagine 4. All right. So I can do that and then I could rerun it and I'm guessing those images are going to be much, much better now. Right. So it was using a

much older older older than actually underappreciated and underutilized model than Gemini 2.0 flash because it does text and images in the same model. But the image quality is nothing near what Imagine 4 is. So if I ran this again, I'm guessing it would be much better. All right. And it saves automatically, right? So that's really, really cool. So let me show you one or two other things quickly in Opal. And then I'm going to go over some comparisons against other tools. So one other things is Opel has a gallery, which is really cool. So essentially, there's different pre-built apps that you can go in and modify. So one is learning with YouTube, right? So I can click that. Again, the app is already built. And I can click this remix. Okay. So what

the remix does is it essentially creates a version or a copy of the app. And now I can go in and, you know, do this for my own purposes. So I can just say, you know, update this to make it a dedicated learning tool that explains complex AI topics for everyday non-technical people. All right. So In a couple of seconds, I can take something that was pre-built by the Google Oval team, go in, put some simple natural language instructions, and refine this and use it for my own purposes. So you can edit things in natural language, essentially in a chat box, or I can go up in this more kind of sticky note whiteboard layout in these modules,

click them and change anything in natural language or with the drop down. So not only can you build something from scratch with the modules, you can, number two, build something with natural language or the third way that you can do it is you can go and find in Google Opel's pre-built library, go in remix something and it's done. Right. So this one is literally already done. So in that 30 seconds, I went in and kind of fine tuned a version of this web app for myself. The other thing is, you know, the themes you don't have, like I said, this isn't something where you're going to build something fully customizable. Oh, I want an app, you know, that's interactive in this way. It's really just for completing basic tasks with anything Google's AI has to offer, which is a ton. Right. But I can, you know, change the theme.

Right. So I can just say, you know, basketball themed. Click enter and it's going to change the design. So you don't have a ton of customization, but I think that's the whole point. Right. And another thing is you'll see, there's not a bunch of code flashing up on my screen. It is literally no code, which I love. All right.

So let's get back. We learned a little bit live. Let's do some comparisons quick. Let me compare these to some other popular vibe coding platforms. Even Google's own, right? And you're like, wait, Google Opel? What about Google Jules? So Google Opel, the target audience is general creators and knowledge workers.

So these are no code users. And the biggest standout differentiator for Opel is it's no code AI chaining. So the ability to use multiple Google AI features back to back to back, passing the input along without knowing any code. Google Jules is another tool from Google. I would say this is one of their more popular kind of AI vibe coding tools. There's actually so many. Google has, I would say, easily five.

But Jules is another popular one. The target audience for this one is more professional developers and team. wanting more autonomous help. And the standout differentiator here is async autonomy. And it functions more like a coding colleague that works in the background. So, you know, different, you know, vibe coding tools, different pros and cons. Let's look at some other popular ones. Cursor target audience for Cursor, developers seeking a deeply integrated AI first coding environment.

The differentiator for Cursor, it's an AI first IDE and it's a fork of VS code. that's supercharged with AI, offering codebase aware chat and predictive multi-line completion. So that's usually if you're working with a pretty big codebase cursors, a great tool for that. GitHub co-pilot. This is the target audience. I would be for dedicated software developers all the way up to enterprise.

And the standout differentiator would be the ecosystem and the integration. So it's literally everywhere developers already are. So, you know, mainly get. web, different command line editors, IDEs, and this is backed and supported by Microsoft. That's actually their product. Replit, so the target audience there are coders from learners to pros, educators, and small teams. And Replit is fully featured top to bottom. It is full stack.

It is all in one development hosting. It combines coding, running, debugging, and deploying with a self-healing, also AI agent in one platform. Replet, very impressive, but a pretty steep learning curve. Lovable. It's been kind of trending a lot recently, I would say. So for more for developers, startup founders, and product team. So if you're trying to push an app, you know, maybe a startup idea, a software as a service, you know, maybe lovable or replet is something you might be looking at. So this is a standout differentiator.

I would say for rapid MVP's generates production grade, full stack code, backend database, etc from a high level conversation but in terms of opal like i said it is the fastest easiest to use literally no code you don't even see code and i think to use multiple pieces of google gemini i i string the queries together share the context you know from a deep research uh to a gemini 2.5 to an imagine uh four to a v o3 and passing that information all along is a no-brainer to start using this immediately to just solve nagging problems. So I also have kind of a core features showdown here for our live stream audience. I'll probably include this in the newsletter as well.

But the by far, the standout feature for Opel is just no code. Literally, no code. There's no code. So if you want to go in there and write the code, this isn't for you. Opel, it's one of the simplest there is. All right. So that is a wrap, y'all. So I will say this.

I hope this was helpful. And I did create a literal starter pack, all right, of 20 different kind of ready to go apps that you can go in and modify them for yourself. All right. So I'm going to share them on my screen here. So they're ready to go. So, you know, the meeting debrief and action plan, the 360 degrees, article analyzer and these just have placeholders ready. So these have been crafted specifically for Opal. All right. And I think out of these 20, I really spend a good amount of time trying to make them

for the everyday non-technical user, just some of the most common problems that people run into on a day-to-day basis. So if you've been wanting to, you know, start vibe coding something or you're like, there has to be a different way or you're like, hey, I'm using, you know, different AIs, but I'm always having to copy and paste and use multiple ones. This is a great way to start stringing these together in Opel. And I have some great different use cases that I've already put together. It's very easy to visually see. You can copy and paste these.

There's some placeholders. You put in your information. It's a great starting point. So maybe, I mean, maybe one of these is just going to work for you right away. You copy and paste. And this could take a task that you're spending five, six, seven hours a week on and turn it into five, six, seven minutes. a week, literally.

So if you do want access to this, these ready to go Opal apps, just make sure you go share this on LinkedIn. All right. So if you're listening on the podcast, we always put the link to the LinkedIn live stream as well as we put that link on our website. So go repost this and I will send you this full list of Opel apps.

I hope this is helpful. If it was, go to your everyday AI.com. Sign up for the free daily news letter. We're going to be recapping today's show and a whole lot more. Thanks for tuning in. Hope to see back 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 refurb. find 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 EverydayaI.com 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.