Reviewing Claude Opus 4.5

I sat down with James, the Boring Marketer, to stress-test Claude 4.5 Opus against Gemini 3 Pro for real-world coding and design work. Together we live-build and compare landing pages and clickable prototypes for an “EstateClear” probate-family dashboard, then zoom out into conversion copywriting frameworks, “elevated direct response” brand voice, and ad creative workflows. The episode is a practical walkthrough of how non-technical builders can go from idea → landing page → prototype → ads using modern AI tools without vibe-coded, low-converting sites. Timestamps 00:00 – Intro 02:00 – Startup Idea: EstateClear 03:17 – Claude Opus 4.5 04:47 – Gemini 3.0 Pro 09:02 – Reviewing Opus’ landing page 11:16 – Reviewing Gemini’s version 12:17 – Comparing the two 17:29 – Reprompting Opus 4.5 and Gemini 19:02 – Google’s vertically integrated stack (AI Studio, Anti-Gravity, TPUs, Workspace) 21:50 – Nano Banana Pro and ad creative experiments 27:35 – Opus 4.5 builds a clickable EstateClear prototype 31:38 – Gemini’s prototype and comparing product depth 36:40 – Anti-Gravity + Nano Banana workflow for mockups and code 44:41 – Claude Skills Workflow and Best Practices 56:41 – Final Thoughts Key Points Claude 4.5 Opus can act like a senior engineer for non-technical builders when paired with a tight skill and tools setup. Conversion wins come more from “elevated direct response” copy and clear page architecture than from fancy visuals alone. Claude’s front-end design skill meaningfully reduces “AI-looking” gradients and vibe-coded layouts, producing cleaner, production-grade UIs. Live tests show Opus 4.5 generates more refined layouts and deeper product thinking, while Gemini often injects clever AI product features. Google’s integration of Anti-Gravity, Nano Banana, and AI Studio points to a powerful end-to-end environment for shipping and promoting products. The #1 tool to find startup ideas/trends - https://www.ideabrowser.com LCA helps Fortune 500s and fast-growing startups build their future - from Warner Music to Fortnite to Dropbox. We turn 'what if' into reality with AI, apps, and next-gen products https://latecheckout.agency/ The Vibe Marketer - Resources for people into vibe marketing/marketing with AI: thevibemarketer.com Startup Empire - get your free builders toolkit to build cashflowing business - https://startup-ideas-pod.link/startup-empire-toolkit Become a member - https://startup-ideas-pod.link/startup-empire FIND ME ON SOCIAL X/Twitter: https://twitter.com/gregisenberg Instagram: https://instagram.com/gregisenberg/ LinkedIn: https://www.linkedin.com/in/gisenberg/ FIND JAMES ON SOCIAL X/Twitter: https://x.com/boringmarketer LinkedIn: https://www.linkedin.com/in/jadickerson/

Speaker names marked ? are inferred from speaking time and the show’s known hosts — they are not voice-verified.

• 0:00Greg Isenberg?

  Guess what? Claude Opus 4.5 is here. And people are saying it is the world's best coding agent. But I needed some proof. So I put Opus 4.5 head to head with Gemini 3 Pro. I built a SaaS app and I wanted to see who would win. And the results might shock you. I did it with my friend, The Boring Marketer. And in this episode, we are going to show you how Opus 4.5 stacks against Gemini 3 Pro. And also how you can get the most out of Opus 4.5. Hint, it has to do with setting up Claude skills. And we show you exactly how to do it. Enjoy the episode.

• 0:49Greg Isenberg?

  We got The Boring Marketer on the pod. James, by the end of this episode, what are people going to learn?

• 0:55Speaker 01

  Well, I'm just going to open the curtains and show everyone sort of how I'm using the latest models. I want to dig into Claude Opus 4.5. I want to jam a little bit on Gemini 3.0 Pro. And I want to show people how I'm building landing pages and websites as a non-designer, non-engineer that are driving great conversion.

• 1:16Greg Isenberg?

  Can we live play with 4.5, Opus 4.5 and see what happens?

• 1:23Speaker 01

  Let's do it. Let's do it. And I also think something that would be kind of interesting is if we did sort of like a test. So let's use Opus 4.5 with the front end design skill. Let's see what we can come up with. And then let's do Gemini 3 Pro with the same prompt. And let's see what we can come up with there as well.

• 1:45Greg Isenberg?

  Let's do it.

• 1:46Speaker 01

  All right. So, ooh, here's a way we could do this, Greg. You want to, you want to get an idea from Idea Browser? And, and run that and see what it comes up with?

• 1:55Greg Isenberg?

  Sure. So, uh, do you want me to give you today's idea of the day?

• 2:00Speaker 01

  Yeah.

• 2:01Greg Isenberg?

  I actually really like this idea. Estate dashboard for keeping families informed during probate. Estate executors face constant phone calls and texts from anxious relatives saying, "What's happening with Dad's estate?" Estate Clear creates a real-time family dashboard where executors can post updates, upload documents, and track progress while family members get instant notifications instead of playing phone tag. I mean, it's one of those small ideas, like the, you know, there's like not, how many estates are there? Not millions, in the US at least, I don't think. Actually, maybe there are.

• 2:37Speaker 01

  I don't know how many, but like, I've gone through that process before and, you know, it's a black box and it takes over a year. You have no idea what's going on. You're getting these replies from lawyers and stuff like that. Like, give me the DoorDash visual that's like just letting me see what's going on, you know?

• 3:01Greg Isenberg?

  Totally.

• 3:02Speaker 01

  And you'd probably save a lot of like money on billable hours to attorneys going back and forth, asking them questions and stuff.

• 3:09Greg Isenberg?

  And the retention is probably insane.

• 3:12Speaker 01

  Yeah.

• 3:12Greg Isenberg?

  You're not, you're not going to cancel that. All right, let's get to it.

• 3:15Speaker 01

  All right, cool. So I'm just gonna paste this into here, kind of the full thing that you, that you sent me. So it's truncating it, but you get the idea. So let's see. I want to create a conversion optimized landing page for my new startup. Build a dot HTML that I can view locally.

• 3:50Speaker 01

  You must use the front-end design skill.

• 3:58Speaker 01

  To generate the page. So typically, what I would do here is I would put this whole description, and actually, let me go ahead and paste this here, just so people can can see it. Typically, what I would do is I would do some foundational research, you know, like I would put this into there. Hey, use the perplexity MCP. Tell me who is in this space. What's a unique kind of differentiating angle that we can take, blah, blah, blah. But, you know, we really just kind of want to see, hey, what do these models do with minimal direction if we just give it the concept? So you must use the front end design

• 4:39Speaker 01

  skill to generate the page. Let's just start there and we'll get a gauge on on design and what it cooks up. All right. So meanwhile, I'm going to go over to AI Studio, and I'm going to give the exact same prompt.

• 4:59Greg Isenberg?

  And could you use, like, do you have to go to AI Studio? Could you not have used Cursor and just done it within Cursor? Sam Altman, the co-founder of OpenAI, just said that it is the era of the idea guy, and he is not wrong. I think that right now is an incredible time to be building a startup. And if you listen to this podcast, chances are you think so, too. Now, I think that you can look at trends to basically figure out what are the startup ideas you should be building. So that's exactly why I built idea browser.com. Every single day, you're going to get a free startup idea in your inbox, and it's all backed by high quality data trends. How we do it, people always

• 5:43Greg Isenberg?

  ask, we use AI agents to go and search, what are people looking for? And what are they screaming for in terms of products that you should be building? And then we hand it on a silver platter for you to go check out. We do have a few paid plans that, you know, take it to the next level, give you more ideas, give you more AI agents and more, almost like a chat GPT for ideas with it. But you can start for free idea browser.com. And if you're listening to this, I highly recommend it.

• 6:13Speaker 01

  You can, you could use the cursor agent there. However, I just don't want to create some like confusion of it working on like the same things. I want to try to keep this like a, I don't know, a unit test or something like that where we're kind of isolating variables.

• 6:34Speaker 01

  So let's, we'll do it this way and we'll see. Okay, so right now Claude is working on our design already. Let's show AI Studio and we'll get it, we'll get it cooking there. All right, so let's go back to the start. Let's just paste this in and let's get my, my prompt that we used for the actual page. And we said, I want to create a conversion optimized landing page for my new startup, build an HTML that I can view locally.

• 7:15Speaker 01

  And I'm going to remove the piece about the, the actual like front end design skill. Because we know that Gemini already has those skills. So let's let her rip and let's see what happens.

• 7:31Greg Isenberg?

  What do you think's going to happen? Like who do you think's going to win?

• 7:36Speaker 01

  I think that if I were to create a prediction here, I think that Gemini is going to come up with something more outside of the box. I think Claude is going to create something a little more of like what you'd expect.

• 7:54Speaker 01

  I think both will be good, but that's, that's just my gut vibe. What do you got? What do you think?

• 8:00Greg Isenberg?

  I wouldn't be surprised if Gemini put in AI features in the MVP.

• 8:08Greg Isenberg?

  I've noticed it's been doing that. I think that's interesting.

• 8:11Speaker 01

  Yep.

• 8:12Greg Isenberg?

  I think that the, my guess is Opus is going to come up, come and do like a very solid, fully featured SaaS app, but it's going to be like more. Kind of similar to what you're saying. It's gonna be, it's gonna be similar to what you'd expect, but I think it's gonna be really, really solid.

• 8:30Speaker 01

  Yeah.

• 8:31Greg Isenberg?

  Whereas the Gemini might have like a couple bugs and it's, you know, explored edges that we probably didn't even think of.

• 8:40Speaker 01

  Yeah, yeah. After we look at these initial ones too, I've, I've had a lot of fun lately also just prompting the model and saying, all right, this is cool, but like come up with something completely outside the box and seeing how creative each model can get. So after we see the initial ones, we'll, we'll give that a spin too and see what happens.

• 9:00Greg Isenberg?

  Cool.

• 9:01Speaker 01

  Okay, let's see where we're at. So Claude is currently doing its thing. And here we go. So this is Opus 4.5 with the front end design skill. One shot, we have the description from Idea Browser and literally like a one to two sentence prompt.

• 9:20Greg Isenberg?

  Stop answering the same questions from everyone in the family. So good.

• 9:25Speaker 01

  Yep. Estate executors face constant calls and texts from anxious relatives. Estate Clear gives you a private family dashboard where everyone stays informed without overwhelming you. So I, I like the overall like aesthetic of this. I mean, going through probate and doing all that and dealing with this in the family like, isn't exciting, right? So like, it's got like a, a nice sort of like subtle tone to it. It's not like screaming in my face with a bunch of like wild colors and stuff like that. Clearly it is not just using the same kind of like purples and typical AI stuff. So let's scroll down and see what else it did.

• 10:10Greg Isenberg?

  So this is your skills that you created hard at work, right? Like from a copy perspective?

• 10:16Speaker 01

  Yeah, this is so I only told it to reference the design skill, actually.

• 10:21Greg Isenberg?

  Okay.

• 10:23Speaker 01

  I didn't explicitly ask it to reference any of the copy skills. So I don't think that it's actually using those. I think this is just what Opus came up with.

• 10:33Greg Isenberg?

  Okay, cool.

• 10:34Speaker 01

  Yeah, so we can we can go through it, though, and try to optimize the copy with those skills and see what it does.

• 10:44Speaker 01

  So I think this is really awesome. Like, this is definitely like all you need for like an MVP or getting this getting something like this live.

• 10:55Greg Isenberg?

  And what happens if you click Star Free Trial?

• 10:58Speaker 01

  Um, let's see. So probably nothing yet because we only built the landing page.

• 11:04Greg Isenberg?

  Okay.

• 11:05Speaker 01

  Yeah.

• 11:06Greg Isenberg?

  Got it.

• 11:06Speaker 01

  Landing page. Yeah, if we were actually wanting to build out this app, it would take a little bit more time for Claude to do. So.

• 11:16Greg Isenberg?

  Anecdotally, it does feel like we've with Opus 4.5 and Gemini 3, it does feel like we've entered a new stratosphere of vibe coding. Would you agree?

• 11:26Speaker 01

  I would definitely agree. Like, I think that the lines are just blurring across the board. Like, you know, the line between a non-technical person being able to code blurred. And I would always feel very frustrated with like the design portion of this whole process, you know? Yeah, you can build stuff, but everyone can tell it looks vibe-coded or it just doesn't look right. Now, that's that line is getting blurred. So all these lines are just blurring and, you know, it's not necessarily like vibe coding or vibe marketing or vibe designing or whatever. It's just like vibe building in a way.

• 12:10Speaker 01

  And the entire stack is just kind of coming together into one place, which is nuts. All right, so there's Claude. Let's check in on Gemini and see what we've what we've got there. All right, here's Gemini's version.

• 12:27Greg Isenberg?

  Keep the family united goes hard.

• 12:30Speaker 01

  That does go hard.

• 12:31Greg Isenberg?

  Yeah.

• 12:32Speaker 01

  Manage the estate, keep the family united, stop playing phone tag, the private dashboard for executors to share updates, documents, and milestones with the whole family at once. Very clear.

• 12:42Greg Isenberg?

  Clear, but I don't know, it doesn't have a

• 12:46Greg Isenberg?

  I like some of the animations on 4.5. I don't know if you noticed that.

• 12:53Speaker 01

  Yes, like the box on the right had a little movement. I also like the layout of the 4.5 one. I can get the copy and I can get that initial visual like right away without needing to scroll or scan down the page.

• 13:10Speaker 01

  Alright, so we've got this here.

• 13:15Speaker 01

  Social proof.

• 13:19Speaker 01

  This is very similar between both models, like this section.

• 13:26Greg Isenberg?

  Here it is, the AI. Don't know what to say, let AI write the update.

• 13:31Speaker 01

  You called that for sure. Yep.

• 13:34Greg Isenberg?

  But I think that's like really interesting. Like to me, I probably wouldn't have thought of this. And it's also, you know, if you're trying to create a startup right now that, you know, gets traction, I think having some of these AI-first ideas really helped.

• 13:48Speaker 01

  Yep. I was curious. This is cool. Like it already built a little kind of like preview of some functionality here into the landing page. So I like that idea a lot. I like the imagery here. Feels

• 14:08Speaker 01

  more human, I guess, which is also something that, you know, coding models have missed in the past. Everything feels very robotic. You've got the emojis, you've got the same style of like illustrations and stuff like that. And I think with, I mean with Nano Banana 3 or Pro coming into the fold too, like Gemini has an incredible asset to leverage with its design capabilities for, you know, things like this.

• 14:43Speaker 01

  We've got a very similar kind of like pricing card between both designs.

• 14:50Speaker 01

  So, man, it's tough. I think both are good. I think, I think from a pure aesthetic standpoint, I think I like the Claude version better. That's just me.

• 15:02Greg Isenberg?

  I think you're right there. Like, I think objectively, it was nicer.

• 15:09Greg Isenberg?

  I think, you know, from the feature perspective, like I said, like, the AI feature is really interesting. Impressed that it worked, too. I mean, my real question with 4.5 is like, okay, great, now it's made a landing page, but can it create a SaaS app? You know what I mean? Like,

• 15:25Speaker 01

  Yeah.

• 15:26Greg Isenberg?

  Ultimately, I'm interested in pushing 4.5 to the limits. And I would, you know, I would be curious if it actually could build an app that I can sell.

• 15:39Speaker 01

  It absolutely could. I mean, you know, if you wanted to build this entire product in Claude code with 4.5, you could definitely do that.

• 15:50Speaker 01

  You know, like, I, like, with Claude 4.5 Sonnet, like, I've taken, you know, an idea for a SaaS from zero to production-ready. So you can certainly do it with either of these models. Now, what I have personally found, and to be clear, I haven't tried to build a full-on application with Gemini 3 yet, but I think that Claude's earlier models, like, I would always go back to them. Like, when I was, I was trying to use Codex and GPT-5 before 5.1 came out, and, you know, Gemini 2.5 Pro and stuff like that.

• 16:35Speaker 01

  And while the logic is good and the thinking and the debugging is good, getting from zero to fully ready was easier with the Claude models. That's just been my experience. So I always kind of try to lean on Claude as the workhorse and then have these other models doing what they're good at as sort of an advisory model, if you will.

• 17:04Speaker 01

  So here they are like side by side. Now, I mean, if we wanted to, we could, we could see how each of these builds out beyond the landing page and just say, hey, create a clickable prototype for, for the concept and we can kind of get a gauge on how, how it's thinking there.

• 17:23Greg Isenberg?

  Let's do that.

• 17:25Speaker 01

  Okay.

• 17:26Greg Isenberg?

  And, because I'm curious.

• 17:27Speaker 01

  Let's do it. Let's do it. All right, let's go back to Cursor and we will get started there. So I want to build the full clickable prototype of the app locally so that I can open up a .html and see how it looks and feels.

• 17:54Greg Isenberg?

  And if we wanted to build, I know we're not going to do it today because we don't have two and a half hours.

• 17:59Speaker 01

  Yeah.

• 18:00Greg Isenberg?

  But if we wanted to build the backend.

• 18:03Speaker 01

  Oh, yeah. Oh, absolutely. I mean, we could, you know, we could set up the entire backend. So some of the things that I've used in like my most recent builds are like Neon, which is kind of the, the database, plugs in nicely and plays well with Vercel, Clerk for auth and login, easy to spin up OAuth or anything like that. I would probably deploy onto Vercel or Railway or, you know, something along, along those lines. You could integrate Stripe for the payments and the subscriptions relatively

• 18:43Speaker 01

  easily as well. And, you know, you could build the entire logic and application here for sure. So I'll give the same prompt while we're waiting there to, to Gemini.

• 19:02Speaker 01

  You know, one of the things that I really like about Gemini and just Google generally is how like, and we've talked about this a lot, is just how vertically integrated it is.

• 19:17Speaker 01

  Now, developers and stuff have their preferences for what tools and what things they want to use, like at different levels of their stack. But if you think about like 90% of people, like someone who's just trying to build their app or get something out there or whatever, having everything like integrated into AI Studio from, you know, off to your storage or database, to easily integrating AI models into your product, to hosting, et cetera. Google has the full range of capabilities there that they own, that, you know, they can integrate directly into like AI Studio.

• 20:02Speaker 01

  Which I think from just a convenience perspective, for most people, is a really powerful value proposition. And from a cost perspective, from a speed perspective, from just keeping things organized perspective, that's a huge advantage that they have as they push this forward.

• 20:22Greg Isenberg?

  Totally. I mean, I don't think I'm going to switch from my iPhone, but I've never been closer to switch to an Android.

• 20:31Speaker 01

  It's pretty crazy, like, you know, something else that we've talked about is, you know, not only do they own the foundational model, you know, the Gemini model, and all these other tools and stuff, the data that Google has is insane. Obviously, we all know that. You know, a lot of people use Google Workspace like to basically run their life, like their email, their calendar, their documents, their spreadsheets, whatever. And so you have that whole layer, that application layer and the tools layer. And then, you know, you've got the devices, like you mentioned. But beyond that, like the TPUs and everything. Now, I'm not like a semiconductor expert by any means.

• 21:16Speaker 01

  But what I do know is that, you know, they work with like Broadcom or whatever to manufacture like their own chips. And it's a lot cheaper, which is something that Google loves is being able to offer, you know, undercut the market. And like owning this entire stack is just crazy to think about where it's all headed, you know?

• 21:38Greg Isenberg?

  And they also own, I think, 14% of Anthropic.

• 21:42Speaker 01

  True, true.

• 21:43Greg Isenberg?

  So they're both kind of Google products at the end of the day, right? 4.5 and Gemini.

• 21:49Speaker 01

  Yep. Have you been playing with Nano Banana at all, Greg?

• 21:53Greg Isenberg?

  I have. It's, you're talking about Nano Banana Pro, right?

• 21:58Speaker 01

  Yeah, the latest release.

• 22:00Greg Isenberg?

  Yeah, it's significantly better than the first version. The number one thing I noticed is just text is better.

• 22:08Speaker 01

  Yeah.

• 22:09Greg Isenberg?

  So it was so frustrating with Nano Banana that, you know, I'd created YouTube thumbnail and it would be like so close. But it would add like an extra O and I would be like, take out the O and it would be like, no. You know, it just wouldn't be able to do it. And there were some tricks around that, you know, creating a new chat using, you know, that image as a reference image. But with Nano Banana Pro, I'm just finding like, you know, 50% better outputs. I'm also using glyph.app to help get the most out of Nano Banana. Nano Banana, by the way, no affiliation with Glyph, no affiliation with Google, no affiliation with Anthropic.

• 22:54Greg Isenberg?

  Just tools that, you know, I'm using. That helps me prompt Nano Banana Pro a little bit better.

• 23:05Greg Isenberg?

  It's kind of crazy to think about like what like, you know, obviously, you know, obviously, the use cases is crazy to think about. There's like a bajillion startup ideas that I'm thinking about right now, specifically around Nano Banana Pro. You know, for example, I saw someone, someone created a infographics. Did you see this? This guy who created the infographics startup?

• 23:30Speaker 01

  No, I haven't seen that.

• 23:32Greg Isenberg?

  I don't, I don't remember like his MRR from it, but basically guy creates a, he basically, you know, all, so many people want to create infographics and like, would you pay 20 bucks for an incredible infographics? Like maybe if it helps you get 50,000 impressions on X.

• 23:50Speaker 01

  Right.

• 23:51Greg Isenberg?

  So he just optimized Nano Banana Pro for infographics, got a good domain name, created a good brand around it. And like, what are other categories for that?

• 24:03Speaker 01

  Yeah, yeah. Something I was using it for, you know, Black Friday's coming up or whatever. I want to do some like retargeting campaigns. I want to run some ad campaigns on Meta. And I saw this format, maybe this is a little sauce for, for people, like similar format to this like infographic approach. But I got these ads on Instagram and it was kind of like the one-page map to accomplish this. Let me, let me show you actually real quick. I'll, I'll just pull up some of the little ads that I created. Cause I actually thought they were pretty good. So my idea for the ad is kind of leaning into that infographic style. How

• 24:48Speaker 01

  can I like give people value like in the ad itself, you know, before I ask them to do something? So we've been doing a lot of these like free workshops or whatever. They've been doing well. My, my concept was, hey, let's take some like short clips or replays from the workshops and some key takeaways people should know. Let's run an ad, drive people to each of those, see which one, you know, converts, helps us build our And then, you know, convert people into the community or whatever. So this is like one of the ads that I that I created. So I've got one of these for each of the workshops. And then I've got sort of like a transformational ad that's like before vibe marketing, after vibe marketing as well.

• 25:31Speaker 01

  Like I try to see what's going on in like the direct to consumer econ world and figure out how I can apply it to to my world. They're testing way more ads than any other industry. They're learning really fast, borrowing some ideas from there and then translating it into like, you know, sort of the creator world is I think there's some alpha there. But yeah, what do you think of this ad on a stake? Do you like it? Do you not? Is it too much text?

• 25:59Greg Isenberg?

  To me, it's too much text and it's too busy. Yeah. And on the negative side, but what I do like about it is like I find like the recordings in the AI finds the moments to save layouts snap into place. Like the the titles look really great. The call to action looks really great. The visual style I think looks pretty, pretty good, like that handwritten style.

• 26:22Speaker 01

  Yeah.

• 26:22Greg Isenberg?

  So I think like what? This is like for me, one prompt away from being a really, really high performing ad.

• 26:30Speaker 01

  Yeah, yeah, I agree. Yeah, and I think just like those barriers, you know, like, oh, man, I'd love to run a campaign, but you know, I've got to go get a designer to make some good ads for me. They have to know how to design good ads and all this stuff like those just aren't blockers anymore. Like you can open up Gemini three, for example, and you can say, hey, go and research the top performing ad formats for me across these industries. Find the common patterns, look at my business and give me the hook, the angle and the visual style that I can go and paste into Nano Banana Pro. Like you, you've got the, the thinking and the testing and the data from

• 27:13Speaker 01

  all kinds of people that have gone and done it and scaled it and everything else. And you can take that knowledge in a snap, go create a good image and then launch a campaign that could potentially, you know, generate fresh sales or revenue for you. So just the speed you can do it and the barriers dissolving is just, I don't know, pretty mind blowing.

• 27:35Speaker 01

  So let's check on our progress. So this is the family view. First impressions here, like it maintained the aesthetic perfectly. Like down to the font. You know, it's not your typical build a SaaS dashboard AI look, you know, at all. Like a lot of those always look the same. Like, I don't know if you've seen like Claude artifacts and stuff like that, like that sort of vibe, emojis and everything, like none of that. Like this looks really good. Here's kind of your progress sort of thing that we talked about.

• 28:15Speaker 01

  We've got recent activity, the different family members here as well. It went ahead and built out a lot of these subviews in this prototype. We've got the updates, keeping you informed with the latest estate news. This is a really nice touch. We've got document storage, which is cool. Milestones.

• 28:43Greg Isenberg?

  Just as you're clicking around this, it's like, why doesn't this exist?

• 28:47Speaker 01

  Yeah, it's a really good idea. Couple pages aren't built, but yeah, you get the idea. You can post an update, sharing the news with your family. This is a great idea. It kind of reminds me of like, what was, what's that platform like Carta or whatever? Like for your company, like fundraising and financials and stuff like that. There's also been a couple like family office as a product startups that have come out as well. Kind of keeping all of that information safe and stuff. So there's some, there's some good sort of examples out there to pull from for this.

• 29:28Speaker 01

  The only thing is like, for this, I would say, what's the recurring kind of, kind of use case, I guess. Like, one way to think about it would be, um, okay, the estate clears, what, what's next in the journey, right? Um, do, do you need financial advisory or financial help? Um, do you have some sort of like estate law play or integration that comes next? So like, this is one step in the journey. Um, I would say to really improve the concept, it's like, what's the recurring use case after? That, that's the next phase of life after this.

• 30:09Greg Isenberg?

  I'm gonna do a whole episode on vertical apps like this and how to structure them.

• 30:18Greg Isenberg?

  But the, the hardest part of building a vertical app is figuring out what is the workflow, figuring out what is the social aspect, um, and then obviously figuring out, uh, what is the vertical? And once you have these people in the network, then the workflow might change, but, you know.

• 30:41Speaker 01

  Yeah.

• 30:42Greg Isenberg?

  There's some, there is a workflow there that you can, that, you know, you just have to figure out what that is. And if you don't know what that is, like, you can show this to a family, right? You now have a prototype, show it to them, get feedback. Um, you could, you know, on Idea Browser, we have pro features that give you agents to help you figure that out. Uh, you could, you know, just take it one step at a time to suffer on retention initially. And then, you know, once you have customers, just like build, build as you go.

• 31:13Speaker 01

  Right, right. I think also, uh, you know, maybe the first customer isn't necessarily the family. The first customer's maybe the, the probate attorney.

• 31:25Greg Isenberg?

  Right, yeah.

• 31:26Speaker 01

  You know, like, they've got the clients coming all the time and, uh, you know, they can, it's kind of like the B to B to C model, if you will.

• 31:37Greg Isenberg?

  Yeah.

• 31:38Speaker 01

  So, all right, let's see what AI Studio is doing real quick. And, uh, let's get a gauge on, so something that I've noticed is there's, there's a couple of errors here.

• 31:51Greg Isenberg?

  So what do you do when you see errors like that?

• 31:55Speaker 01

  Fix error. How can you make this work? No, you know, for for me, it's yeah, just kind of a process of like trying to dig deeper into what the root cause is. So I use the terminal for all of the work that I'm doing. So if we think back to that cursor setup, I may say, hey, Claude, ultra think about this problem. You know, if you type in ultra think it'll change colors and it'll use more, you know, power to kind of help to dig in or solve the problem. Other tactics that I've used with Claude, because that's like my daily workhorse, is I'll say, hey, if I'm really stuck, I'll say,

• 32:39Speaker 01

  hey, spin up specialized subagents that are going to go and find the root cause of why this thing is breaking. I need like a Q and A tester. I need a senior sort of like engineer focus on this or whatever. And then it'll spin up these specialized agents that'll identify different areas that they're going to go and research in the code base. And then it'll come together with like a comprehensive sort of analysis for me. And then I can say, hey, all right, cool. Plan this in terms of like a step by step process that we can go through to fix it. If it's still stuck, that's where I'll use cursor agent with, you know, GPT or Gemini or something like that for kind of an outside perspective. Now, one of the the things that

• 33:24Speaker 01

  Anthropic is kind of talking about with Opus 4.5 is that its ability to kind of stay on track is really powerful. Sometimes when the code base grows, it's harder to kind of manage the context to find what that single problem or whatever is causing this breaking the app. So I haven't built something full with with Opus 4.5 yet. I'm thinking that its ability to work through the bugs without sort of getting lost is going to be a lot stronger. And I wouldn't maybe need ultra think or subagents or maybe even those additional agents on the side. So I'm really curious to dig into that and see.

• 34:05Greg Isenberg?

  Which is a big deal. It's a big deal for your the health of your heart.

• 34:10Speaker 01

  Yeah, for sure.

• 34:13Speaker 01

  So here's our prototype within Gemini here. So little bit of a different vibe, more like less dashboard, more sort of like digest or updates or a space for the, sorry, it updated the, updated the landing page a little, oh no, it's just a sizing thing, sorry. Okay, so a little more of like a social vibe here, like sharing an update or connecting with the family. It's got the AI features like built in, like polished with AI, like if I want to update

• 34:54Speaker 01

  the family, I'm not sure if that's needed, but you called it that there would be AI integrations within the build. So that's interesting. Let's see, documents, similar idea to what Claude came up with, with like Document Storage. We've got the timeline here, I kind of liked, I think the timeline is one of the core aspects here of like getting that quick snapshot. I liked how the 4.5 Opus had that front and center as soon as you log into the dashboard. We've got the family and we've got settings.

• 35:37Speaker 01

  My take is I feel that Opus went a little bit deeper in terms of thinking through the product. I mean, this looks good, it's clean, it's not bad, but I think I like the, like the other version a little bit better.

• 36:01Greg Isenberg?

  Yeah, it feels a little more refined, a little deeper.

• 36:08Greg Isenberg?

  By the way, both of these products are outstanding.

• 36:13Speaker 01

  Absolutely.

• 36:14Greg Isenberg?

  MVPs, and we're only testing this with very few prompts. So it's unclear that at prompt 25, who would be winning.

• 36:26Speaker 01

  Right.

• 36:27Greg Isenberg?

  But I think if you look at, based on the two prompts that we've done, I think it's clear that Estate Clear on 4.5 beat Gemini 3.

• 36:38Speaker 01

  Yeah, yeah. I've got one other concept here for a test, just to try to make sure that we're doing this in a fair way. All right, so anti-gravity, you know, Google's agentic IDE. I'm curious if we put the same prompt into the Gemini 3 Pro model in anti-gravity, if it is different than what you get in AI Studio.

• 37:14Greg Isenberg?

  I have a feeling I know the answer to that, but I'm, I, I, let's try it.

• 37:19Speaker 01

  All right, we'll see what happens.

• 37:20Greg Isenberg?

  My hunch is that it's, you're gonna get worse design out of anti-gravity.

• 37:28Speaker 01

  Okay.

• 37:29Greg Isenberg?

  But, you know, I've been wrong once, and I've been wrong before. I've been, I've been wrong lots of times, so.

• 37:35Speaker 01

  Okay, let's check it out. And by the way, like, anti-gravity is really cool. Like, definitely recommend people check it out. So I'm just gonna paste in the same prompt, and let's see what happens.

• 37:53Greg Isenberg?

  So why should people use anti-gravity over cursor?

• 37:59Speaker 01

  Well, it's a good question. I mean, at the end of the day, they're both VS Code forks, you know? So they're, they're both kind of based off of VS Code, which is open source and, and free.

• 38:15Speaker 01

  However, I like some of the things anti-gravity is working on. To be honest, I've just started using it and testing it and things like that. But they've got some like Chrome stuff built in here where it can access the browser in a really easy way and it can even access, you install a Chrome extension. So if anyone's done vibe coding in the past and you're trying to like squash a bug, you know, you open up your deployment, whether that's locally or hosted or whatever. And you know, your coding model's like, hey, like navigate to it on Chrome and then open up

• 38:56Speaker 01

  like the console and the dev tools and figure out like, tell me if this API connection's working, copy paste the responses, like that whole debugging process is pretty painful. So with the Chrome extension that anti-gravity connects to, it can access that data for you programmatically. So it's accessing the DOM, it's seeing sort of the data behind the scenes. So, you know, I suspect it will greatly minimize the back and forth in this debugging process when it has a very tight browser integration and can access data through the anti-gravity extension. So I think that's super interesting.

• 39:42Speaker 01

  That's kind of the first thing that I've really kind of picked up on and noticed. I suspect, given the speed that Google's shipping, we're going to see a lot of interesting things here, like some of the landing pages I've built here, like I'm pretty sure you'll be able to have like Nano Banana integrated within anti-gravity and like some of these other tools, like, you know, like you want a killer illustration, great, like let's spin that up with Nano Banana and put it on the page.

• 40:10Greg Isenberg?

  That's where it's going to go crazy, right? Because you see what's happening with Google is they're creating VO3, they're creating Nano Banana, they're creating all these like, it's a whole creative suite of killer use cases that are pretty independent, but once they're able to, you know, bring that into anti-gravity and, and just use all the horsepower from all those killer use case products, I think it's going to be absolutely madness. It's going to be really awesome.

• 40:42Speaker 01

  And man, like.

• 40:45Speaker 01

  Taking that even further, it's like, oh, like, let's make a launch video. Let's make a podcast.

• 40:53Greg Isenberg?

  Yeah.

• 40:54Speaker 01

  You know, there's so many ways that it can extend into the ecosystem. I mean, you know, we talk a lot about like bio marketing stuff. Ooh, let's set up a Google Ads campaign to drive traffic to this. I mean, like, the ability to stay interconnected and grow lifetime value. No one can match that with this ecosystem that they have, which is, it's wild.

• 41:20Greg Isenberg?

  So what's happening?

• 41:22Speaker 01

  Okay, so we put in the same prompt here as well. Right now, actually, I think it is generating a mock-up with Nano Banana.

• 41:33Speaker 01

  So it's actually generating an image with Nano Banana instead of going ahead and building the page from scratch. So, okay, here's what it's doing. It's generating a custom dashboard mock-up image first to make the page look real. Then I'll build the HTML file. Ooh, wow. So it used Nano Banana. So it's integrated to create a high-fidelity visual mock-up that we can see. Pretty, pretty nice initial mock-up, I would say.

• 42:10Greg Isenberg?

  Totally. Really nice, like those chunky buttons.

• 42:14Speaker 01

  Also, that's kind of like how, how like a real team would work, right? Like, okay, like, let's create like a high-fidelity mock-up. Let's make sure you like it before we go and write all the code, you know?

• 42:26Greg Isenberg?

  Totally.

• 42:27Speaker 01

  Anti-gravity may surprise us here.

• 42:31Speaker 01

  Okay, so here's another thing, really fast, really fast, is something I noticed in Anti-Gravity. Let's, let's open it up. I'm sure.

• 42:44Speaker 01

  The hardcore developers and everything are gonna be like, what are you doing? But this is how I do it. All right, so I've opened it up in my browser. Let's check it out. So this is AntiGravity Gemini 3 Pro. Keep families informed during probates. Stop the endless phone calls. A state clerk gives you a real-time dashboard to share updates, documents, and progress of family members instantly. It's got the image that it created. So again, this is really cool how it's able to utilize NanoBanana within the workflow, call it as a tool, and implement it into your design. Like, that is really neat.

• 43:26Speaker 01

  So some similarities here between, you know, some of the other ones in terms of showing the features and stuff like that, the pricing, et cetera. So I think, you know, my take would be outside of this image, it feels a little basic. So I think your instinct that AI Studio will have a better initial design output from one prompt was correct.

• 43:55Greg Isenberg?

  I think what was cool about AntiGravity and this whole sprint that we did with it is if you scroll down, the mock-up. Like, for me, how that mock-up is and how this is wireframed out, there is some alpha in there. And then, you know, maybe you go back to Opus 4.5, or maybe you go back to Gemini 3 Pro on AI Studio and then iterate there.

• 44:20Speaker 01

  Yeah, yeah. Yeah, like, what do you like from each model, like, or whatever? You know, what can you learn from each? How can you sort of use it across the spectrum here to arrive at what you like at the end of the day? So.

• 44:38Speaker 01

  Really cool. Really cool. So going back to kind of like my setup a little bit, there are a few skills that I recommend everyone create with Claude Opus. So a skill is just like a set of instructions that the model is going to reference when it does a certain task. Okay, so I do a lot of like website optimization for the vibe marketer.com. I want to figure out, hey, how can I convert more visitors into customers? And we've talked a lot about this, but like it comes down to really good copywriting. I think that, you know, that's a struggle for like 90% of business owners is knowing what

• 45:20Speaker 01

  kind of copy to write for their business. They don't want to feel, you don't want to feel too cheesy, too salesy, but you also want to leverage the principles of influence and persuasion in the right way, you know? You don't want to have this empty brand speak and you also don't want to be like, hey, make this much money, do this like right away. There's a, there's a fine balance, right? So I call this elevated direct response and I build a skill around it. And every time I write copy for my website, Claude references this skill and it does a great job at, you know, producing, you know, this, the style of conversion focused copy.

• 45:59Speaker 01

  So the way that I did it is I found some people in my space or in our space that, that I like, that I look up to, that have, you know, built some pretty huge businesses with community and education and things like that. So here's an example. I have the perplexity MCP set up in Claude code. So I say, hey, use the perplexity MCP, go research Cody Sanchez and Alex Hormozi and like the biggest sort of like education or information based businesses out there and break down exactly how they're writing their copy, how they're positioning their products

• 46:40Speaker 01

  and services and how they're talking about what they do. What are the main takeaways that you can learn? So I did that and it kind of came up with a few different, you know, baseline insights. The Contrarian Educator. So Cody Sanchez starts out with like a contrarian point of view or a contrarian hook. You know, so got that from, from her. When I did this research on Alex Hormozi, I found that, you know, he's got sort of these offers that you can't refuse. And he's always sort of stacking the value in terms of like what someone is going to get, like with this big promise that you're making. So those are great learnings. What I did was I collected that into kind of

• 47:25Speaker 01

  this elevated direct response skill or playbook. And then what I did is I fed Claude Code a bunch of examples of my own writing. So things that I've created, a bunch of tweets, even like transcripts of YouTube videos that I've done. You name it. And I said, hey, distill this into a brand voice skill. So it broke down the way that I talk, the way that I write, so that it feels natural. And you can see some of the, the things here that it came up with. So contrarian educator. So boring is like the antidote to like shiny objects out there. What's the real practical ways? People are going to get value from some of this stuff.

• 48:10Speaker 01

  You know, I'm really focused on compound growth while operating on the bleeding edge. So I don't like to chase everything. I like to figure out how I can build systems around these tools and processes that are going to pay dividends for a long time. Direct response DNA. So, you know, as a, as a small business or a creator or whatever, like we don't need to worry about like this empty brand speak. We want to get people to take action in a classy way. So I've got a direct response DNA. Systems over hacks. So that compound long-term thinking. And then like a creator first language. Like you always talk about like learning how to write for the internet. I think like that's the epitome of creator first language. Like you want to talk naturally, you know?

• 48:55Speaker 01

  So blending what I learned from these folks with my own kind of DNA kind of led me to, you know, creating like my own voice skill in Claude that it uses every time. So I rebuilt like my entire website using this and it's been working pretty well. So definitely like leverage skills and with the tool use and the context ability of 4.5, it's going to do a really good job with those. So I boiled all that down also into like a landing page architecture that I utilize. So I've been, you know, pumping out a lot of landing pages on my website lately. Like we've been doing these like workshops.

• 49:39Speaker 01

  I wanted to create like a lead magnet around those so that I could gather emails. I wanted to redesign the homepage and I use the same architecture that Claude Code was able to reference on each and every page using my voice. So this is sort of an overview of the architecture that I use and probably a lot of other people use whether they know it or not. So, you know, we want to have like an impactful hero section. You know, what is this getting you? What's sort of the transformation or the outcome? We go through the problem agitate phase. So this is sort of like what's the issue you're facing? How do you stoke the pain to make it feel like you really need something?

• 50:23Speaker 01

  And then you're coming in with a solution. So problem agitate solution is kind of a classic framework for conversion. We're providing the solution with this like value stack, you know? Took that from sort of studying Hormozzi's stuff where we're trying to make it feel like we're giving you so much value that it feels dumb to say no, right? And then we follow up with social proof, the transformation, kind of backing up and reselling this sort of major outcome that you're going to get. Having a secondary strong CTA and then, you know, if you need like a footer or anything like that. So taking a step back, I know that's a lot of information. One, research like.

• 51:07Speaker 01

  The leaders in your space, people you look up to, people you think are doing a good job. Nail your own sort of brand voice based on how you naturally speak. Combine that into a voice skill. Okay, and then you can optimize that into sort of like your landing page architecture. That's driven toward generating a conversion.

• 51:29Greg Isenberg?

  And from your experience playing with Opus 4.5 in the last 24 hours. You're kind of, you know, I know you shared some of the landing pages and copy with me. You're basically suggesting that you can get way better results.

• 51:46Speaker 01

  Yeah, you can get way better results with with less prompting and less work in between. So do the research upfront, set up the skills, grow one prompt into the system and you'll get a great result. So doing the boring stuff upfront, if you will, doing the research, building these skills out. Maybe you have two or three and then then attacking the project with just one clear prompt can get you a long way. So I'll show you what that means and maybe we can even run it live and show people what this looks like. But there's one final skill that is a must have with Opus 4.5.

• 52:26Speaker 01

  Now, everyone's seen all the Gemini 3 designs out there and it does a fantastic job. I think it's awesome, but don't sleep on Claude 4.5 Opus with the front end design skill. Most people don't know that this skill exists. I didn't know it existed until Claude posted like a blog post about it on X and I read it. And you can install it with two simple prompts. I wrote an X post on this, but basically all you do, you enter this first one in. This adds sort of this anthropic plugin marketplace into your Claude code environment. And then you've got plugin install front end design at Claude code plugins.

• 53:09Speaker 01

  So what this is going to help Claude code do is avoid all of that typical AI design stuff. You know, we've seen it everywhere. Everything looks the same. You've got the same gradients, the same text, all of that. So, skills are just like long sets of prompts or instructions. So, in there, Claude's own team built this out. It's like, avoid the typical AI stuff, build production-grade designs and interfaces, etc. So, got all the instructions that you need to build out. So, I ran one prompt with this. I was just imagining kind of like a made-up offer. Like, what if I held like a workshop where I taught people how to like,

• 53:51Speaker 01

  build conversion-focused landing pages that look really good, or something like that? I put in a two-line prompt and, you know, it sort of one-shot of this, which I think it was a good first pass for Claude with the front-end design skill.

• 54:08Speaker 01

  It's got, you know, a clear headline. It's got sort of stoking the pain in a way. It's got kind of like the transformation. It's got, you know, some features, if you will. And then, you know, it's a very clean and simple design. Could obviously work on this more and ask it to do a lot more things. But this one-shot with one, a one-sentence prompt is far better than what most people are doing out there.

• 54:35Greg Isenberg?

  Yeah, and the copy hits. The visuals don't look vibe-coded at all. It's easy to scan. I can imagine on mobile that this would probably convert, you know, pretty well.

• 54:51Greg Isenberg?

  You know, it don't have too many notes on it.

• 54:53Speaker 01

  Right, right. I think like, what I would do, what I would say is, you know, I need a better CTA kind of top-of-the-fold. Like, what action do we want people to take? Social proof would also be really good as well. But like, you know, those two elements, and you've got something that you can literally create in two or three minutes that's optimized for conversion, that sounds and looks good.

• 55:18Greg Isenberg?

  Yeah, and I think that the big piece that people miss with vibe-coding is they vibe-code stuff, but then the copy sucks.

• 55:27Speaker 01

  Yeah.

• 55:28Greg Isenberg?

  So then people, you know, they're, they're converting at 1% or less than 1% and they're like, "Why?" And then, and they come to the conclusion that, "Oh, vibe coding, you know, doesn't work for me."

• 55:40Speaker 01

  Exactly.

• 55:41Greg Isenberg?

  Where it's like, "Well, you know, in a lot of ways, the content is the UX." So, and what is the content? It's the words. And so if you can create great copy, you're gonna probably be able to convert, even if the design isn't drop dead gorgeous.

• 55:59Speaker 01

  Yeah, absolutely. I mean, uh, look back at the old school sales letters and stuff like that, you know, from like back in the day, or like those old long form newspaper ads. They aren't necessarily beautiful. It's, it's all text, but they know how to influence and talk about those pain points really, really well. And I think you point out a really good, a good point here is like, everyone's focused on, uh, the design aspect of, of the aesthetic, which is important, and we don't want like something that looks the same as everyone else, but you know, 98% of people that are vibe coding or vibe building are missing out on this whole copy angle, for sure.

• 56:41Greg Isenberg?

  So, you know, that's the episode, Opus 4.5 versus Gemini 3 Pro with some bonus anti-gravity. What's your, you know, TLDR on, on this whole experience?

• 56:54Speaker 01

  Yeah.

• 56:54Greg Isenberg?

  And, you know, should people get started with 4.5 today?

• 57:00Speaker 01

  Yes. Uh, 4.5 Opus, I think, is gonna be an incredible model, just based off some of these initial tests that we did and, and that I was doing last night. When you combine it with that front-end design skill, it's able to one-shot some pretty incredible interfaces and, and designs. Um, I think if you level up that design, like we were talking about, with actual good copy that's geared toward conversion, like you're gonna be, you're gonna be unstoppable. So like, just to review the copy, review leaders in your niche, review direct response, add context of how you talk naturally, define your, your elevated direct

• 57:44Speaker 01

  response skill. So if you use that in combination with the design skill, uh, I think you'll be really pleased. Um, and then- You know, the things that I liked here about AI Studio and Anti-Gravity, Anti-Gravity, really cool. It's using Nano Banana Pro. I think Nano Banana has been awesome to play around with. AI Studio, absolutely cooking right now with the releases and the updates. So it's a playground out there right now.

• 58:12Greg Isenberg?

  Thank you, James. Thanks for spilling the sauce, coming on here. I'll include links where you can follow Boring Marketer, AKA James, in the show notes, his YouTube channel, his X account, and his community, thevibemarketer.com, which I think, you know, I think you get like a free toolkit or something if you sign up, right?

• 58:38Speaker 01

  Yes. So we've been doing these workshops. We've got basically these experts that we've sourced from our community that, you know, we're hosting to kind of spill the beans on how they're using all these tools to build some pretty incredible things. We've done, you know, AI video editing and scaling content. We've done AI search and SEO. We've done Claude code, et cetera. And I've taken sort of the best clips from those. You can get them on thevibemarketer.com/workshops. And, you know, go grab it. Free, no gatekeeping. See if you like it.

• 59:12Greg Isenberg?

  All right. Well, thanks again. And dude, never a dull moment in this industry, right?

• 59:20Speaker 01

  I mean, last week and this week, like, I need a break. I've got whiplash from, you know, looking at all the new releases and stuff. So I don't know if this is the new normal or not, but it's a crazy time to be alive.

• 59:34Greg Isenberg?

  I mean, I'm definitely tinkering this Thanksgiving, that's for sure.

• 59:38Speaker 01

  Oh, yeah, absolutely. Thanks for having me, Greg.

• 59:41Greg Isenberg?

  Appreciate you.