The Startup Ideas Podcast - Manus AI replaces your AI tech stack? (Full Demo)

Starting point is 00:00:00 Everyone's talking about Manus AI, the Chinese AI app that basically can take your thoughts, turn your ideas into fully automated businesses and products. Now, I wanted to try this, but I didn't have access. So I called my friend Min Choy, who came on the podcast, and we had a crazy idea, can we build a business? actually the idea was a docusign killer, a multi-billion dollar business in a few prompts.

Starting point is 00:00:35 And in this episode, we go through it. And we show you the ups, we show you the downs, we show you what's good about Manus, we show you what's bad about Manus. But if you're here, if you care about AI, if you care about building businesses, understanding how Manus works is a must. I was so impressed with some of the stuff it was doing

Starting point is 00:00:56 and I was so not impressed with some of the other stuff it was doing. This video shows you all about that, the good, the bad, the ugly. I recommend you watch the entire episode, and you make the judgment call for if you can go and create a business fully automated with a few prompts on Manus AI that generates $1,000 per day. Enjoy the episode. All right, I brought a Min Choy today. Min has been going viral recently because he's been playing around with Manus AI.

Starting point is 00:01:39 And he's going to give us a first look into how to use Manus to actually build a business that works for you. Min, thanks for taking the time on coming on the show. What is the viewer, the listener? What are they going to get out of this episode by listening all the way through? So, thanks for having me, Greg. this is a very exciting podcast to join. It's my first time, so thank you. So this Manus has been going viral and very crazy in China,

Starting point is 00:02:10 and it just came over just a few days ago. And I got an invite so that I can go play with it. And I realized that this thing is just more than the typical AI that we've been seeing. And the thing that is different with this is that we've had attempt in the past that we wanted to make this agentic AI where the AI can actually go in, like, run tasks and run tools. And as you've seen on like cloud computer use and browser use and similar to that. And this is sort of like more advanced the next stage of that.

Starting point is 00:02:48 I think that we're getting closer and closer to sort of the glimpse into what the AGI is going to look like. So what I want to show you today is that I want to take. some of your startup ideas, Greg, and I want to see how far Manus AI can take it. And we're going to try to do this step by step in a very like a process-oriented way. And we want to see if this thing can really help entrepreneurs

Starting point is 00:03:20 or startup owners to really kickstart their ideas into action. And I think that this will show like what this type of technology can do for us in terms of growing a business. Okay, let's see. I mean, I'm curious. This is my first time getting a glimpse of madness. I hear big things. So, yeah, let's just, let's get right into it.

Starting point is 00:03:46 Yeah, let's start with some of your great ideas. I think that one of the thing that I read recently from your post, with something about DocuSign. I think DocuSan might be a little bit complex, but let's give it a shot and see what Manus can do for us. Okay, and while you pull that up, my thought on DocuSignman was basically that what's happening is, you know,

Starting point is 00:04:17 DocuSign makes, I think, like billions of dollars or something, thousands of employees for an electronic signature. And with AI, it's going to just be a lot easier to create software. we'll see by the end of this episode to compete with, you know, the dokey signs of the world. And instead of charging $10 a seat or whatever they charge, you'll be able to make it free or charge just a very small amount. So I think that there's an opportunity to build. I mean, I think multiple people could do this. Can make about, you know, at least $1,000 a day in revenue.

Starting point is 00:04:54 And so I'm excited to see if this could work. All right. So what do we? It says, hello, Min. what can I do for you? Yeah, so this is a very familiar interface that we see all time. You know, chat JPT kind of had this type of interface and everyone else kind of start copying that interface design.

Starting point is 00:05:12 So Manus also has a similar, you know, you got a little chat window with the, you speak with the agent. So you just kind of simply say what you want. And I like to start very simple request, like, you know, Let's say, create a docket sign clone. Quick break in the pod to tell you a little bit about startup empire. So startup empire is my private membership where it's a bunch of people like me, like you, who want to build out their startup ideas.

Starting point is 00:05:52 Now they're looking for content to help accelerate that. They're looking for potential co-founders. They're looking for tutorials from people like me to come in and tell them, how do you do email marketing? How do you build an audience? How do you go viral on Twitter? All these different things. That's exactly what startup empire is. And it's for people who want to start a startup but are looking for ideas or it's for people who have a startup but just they're not seeing the traction that they need.

Starting point is 00:06:21 So you can check out the link to startup empire.com in the description. Okay, so simple, like a super simple request. Yep, very simple. Yeah, start by there. The cool thing about this is that Manus is sort of a multi-agent under the hood, and it's got like planner, executor, that type of thing. And if you remember, like, very early in the days, when we used to have this thing called Baby AGI by Yovie,

Starting point is 00:06:54 I don't know if you remember. that kind of used to have that sort of that setup where you had like a task creator and like an executor and et cetera. So this thing does a similar thing and then what it's going to do is it's going to take your request and then it's going to try to research

Starting point is 00:07:11 into what that is and what it needs to do to create it. So even giving a simple request is doing as many things like on its own. Like it's planning, it's designing, it's executing and it's going to try to run things and then analyze their results and then try to kind of replan or update as needed if it's doing if it's going the right way so you will see a lot of things

Starting point is 00:07:40 there's a lot of going on it's doing a lot of planning that I'm researching right now so it's uh doing it's you know sort of the Googling right now under the hood and then it also checks out their website I think it also takes screenshots um and it tries to do so stuck on it. I did like run into one one interesting thing before was that it it got stuck on like CAPTCHAs and stuff and I thought that was kind of funny and it wanted me to like kind of intervene and like do something with it. So it has some sort of the human in the loop feature in there as well. So it will ask you for confirmation or you know additional contacts as needed. So this is interesting.

Starting point is 00:08:27 So if I'm understanding this correctly, you know, before Manus, you kind of had to go to a bunch of different places. I call it the AI cocktail approach. So you would go to maybe a chat GPT or a GROC 3 to kind of come up with the idea and create a PRD. And then you'd go to V0 to actually design what it would look like. and then you'd go to, you know, a bolt, a lovable, a cursor, depending where you are in terms of technical prowess, to actually go and build the idea and deploy it. What you're saying here is what's happening on the screen

Starting point is 00:09:06 is it's kind of doing all those things at the same time. Exactly. Yeah. It's actually, what it's doing is it creates a sandbox, like a virtual sandbox of its own. And it runs like, you know, command line executions. It runs the browser, runs the tools. Which is you on the right, it's right now it's browsing and just capturing stuff, capturing information.

Starting point is 00:09:33 I think what it's doing is scrolling it, it's scraping all the data and information you can get. So since I say docu-sign, it goes to doxan and it checks out like what, you know, type of information and the feature the product has, and then it will probably test it out and see what feature that it can capture as part of its plan. So, and remember, like, we just started with this.

Starting point is 00:09:58 Very simple to say, just go create me a docusine clone, and now it's just going and doing his own thing. And it's just pretty wild to see that where we are with this agency AI that is able to kind of do most of this task on its own, understands your request, and if it doesn't have all the information, it goes and research on its own. And I think that's like the key to a lot of this.

Starting point is 00:10:24 And like you said, that we've had many AI tools that we had to use like separately. And we've done a lot of copy-pacing in between. Now, a lot of that has improved a lot with under-cursor, lovable, you know, Rappellit and all that. But this is a little bit different because it does more than just coding. It actually does the research. It actually goes to the browser and it actually,

Starting point is 00:10:49 it captures the information from there directly. And then it takes all that context into his planning. And then it formulates a plan of execution, and then it goes and executes them. So this is a very interesting way. Now, what you see on the right side of the markup, the way he has that markup, this reminds me a lot from like the baby AGI days.

Starting point is 00:11:13 Baby AGI used to kind of do this in the command line where it shows like it's planning phase. and all that stuff. And I thought this was interesting. So it's doing like step by step on what it needs to do to create this docysine clone. And that's all I said. Just go get, create me a docusine clone. And it's getting all of that information.

Starting point is 00:11:32 And it's planning, replanting and executing. So it's very interesting to see. And it's going to take a couple of minutes to get to the end. And also sometimes the ask task as it's needed. It may have missed something like in the process. of doing this. So yeah, there's going to be a lot going on on the on the on the on the on screen now, but it's going to be pretty interesting what it comes out with. So have you ever had an instance where you're like create this app and you're looking at maybe like the

Starting point is 00:12:06 markdown like for example if you know if you go back to the markdown can you go back to the markdown while it's or or it's um yeah I mean you could like look at the two-dos. Oh wow. Wow. That markdown was just like a, it's actually the raw source code, but this is the preview. Cool. So I'm actually going to read a little bit of this because we do have a lot of listeners on Spotify and Apple for this startup ideas podcast. So it says here, research doc design core features, identify key functionality to implement document user flows and technical requirements. Now, there could be a case where you're like, whoa, whoa, whoa. I don't want you to do X, Y, Z. I don't want you to identify the key functionalities.

Starting point is 00:12:54 I just want you to, you know, maybe only focus on this one feature. Is there, have you ever asked Manus to do something and then kind of said like, oh, I made a mistake or you did something wrong? Is that? Yeah, you can actually talk to it in its middle of its progress. So which key functionality do you want to limit this to? Well, it's a great question. I'm going to pull up the docusign website right now. Because it looks like when I'm on the docusine website, it looks like they've created a lot of different products at this point.

Starting point is 00:13:33 So like, for example, they have the e-signature product, the payments product they identify. All I care about is the e-signature product. So I just want to confirm that we're only talking about the e-signature product. So let's only focus on the e-signature key functionality. Yes. That's cool. Well, that's a really, that's actually a really helpful feature because like if you're using chat DBT, for example, it's, it's in thinking mode. And when it's in thinking mode, you're kind of twirling your thumbs unless you stop it and then ask it to do something. Yeah. This is this is probably the one of the coolest feature that I've noticed on this particular product is that I can interrupt it in between without it like. you know, stopping its work that it's going to try to, as you see here, it's going to say, I understand you want to focus specifically on the e-signature key functionality, and it will adjust the approach to prioritize the course e-signature feature of Doc design.

Starting point is 00:14:36 So then it says, let me continue in setting up the project structure with this focus in mind. So this is like one of the coolest feature that I've seen on this, that you can actually kind of as sort of a human in the loop, like interrupt the process to readjust the planning or the setup. That's cool. I also just noticed that like it's very clean. Like I feel I feel like I understand what's going on. Like it's very pleasant to the eyes.

Starting point is 00:15:05 Yeah. A lot of the demos that I've seen, most people just kind of kick this off and just kind of walk away. And then just have a coffee or snack or lunch and just come back and just check like, you know, where is that? So it's kind of funny. And I know you've seen some video.

Starting point is 00:15:21 It was like with the guy, with a person that's on a Tesla driving. And, you know, the person is on his way to some coffee meeting and like, oh, you know, create, creates me some, you know, talking points for this coffee meeting. And it's just kind of driving zone and the Tesla FC is driving in. And also, a man as AI is preparing his, you know, meeting notes. It's kind of funny. We'll include that video so people could see that. Was that?

Starting point is 00:15:49 We'll show that video on screen. Yeah, yeah, yeah. Yeah, yeah. I don't like the video that much because it just feel like I don't know what's going on other than I see a car and screen. The screen's kind of small, so I don't know if there's doing anything, but I thought it was kind of cool. Just the fact that he was doing it. I think it was cool. How long is the, you know, how long do you anticipate this taking? Is it like going to be 10, 15 minutes, 20 minutes? Depends. You know, if it's something very simple, like some of the research stuff, it actually doesn't take that long. So I've done a research to say, find me all the research on this particular topic. And it'll go in and just does this Googling and searching and then they'll find it and then just kind of bring the report. Just like very similar to, you know, the deep research and the deep search, et cetera.

Starting point is 00:16:41 So while this is running, you know, what we can do is start a new session and say let's get like top Greg's startup ideas and see which is the most viable. all to run on Manus while it was doing the Darkozan. How is that? Beautiful. Yeah. I think I think for me it's it's most viable to run on Manus but also the one with the what does Manus think has the highest probability of success. So I'm interested to know I'm interested to see like what is how intelligent is Manis right? Like there's on this show on the startup ideas podcast I've given away I don't know a thousand plus ideas and the reality is some ideas aren't that good. So Some ideas are good and some ideas are really good. Yep.

Starting point is 00:17:26 And it's really the listener. Today it's the humans, the listeners who have to figure out, okay, this is a really good idea. Or you know what? Greg had too much wine and I don't know what he was thinking when he came, when he shared that idea. You know, you got some really great, great ones. I'm surprised that people haven't taken some of those ideas and put those ideas to work, you know, with all this AI tools. They do. but a lot of them just

Starting point is 00:17:52 they're like they're like they keep it to themselves and they just DM me and they're like I built this thing and it's doing like it's crushing it or I I guess if this was you know so easy then everyone will be all like rich right

Starting point is 00:18:06 all right so I ask I asked Mattes while it's doing its docicine creation to research into your startup ideas and the top and top ideas that Man is

Starting point is 00:18:21 has the highest potential. That's the way it comes up with and see if we can have some actionable, you know, startup ideas that we can also ask you to create while it's doing the DocuSign creation. Okay. I have an edit to this prompt. Sorry to do this to you, Min. Okay. But I would say, I think we should ask for ideas specifically that I've shared on X

Starting point is 00:18:47 and ideas that I've shared on the startup ideas podcast. and the Greg Eisenberg YouTube channel, I think we should just qualify that that's where we want. Or what do you think? Should we qualify it or should we just let Manus figure it out? Let's have Manus figure it out. All right. Yeah.

Starting point is 00:19:08 The thing with this type of agentic AI that I like is that it's easier to start with. If you notice on the other AI tools, people are running into issues because they don't know where to start. They don't know how to ask. And, you know, they're not maybe not as good at prompting or have templates and et cetera to, you know, get their ideas across. Could you click the browser, by the way? Sorry. Could you click the browser? Like, can it go more on the screen?

Starting point is 00:19:45 Okay, wow. So this is it actually. So this is, it's on our, it's on. on my holding company's website right now, which is, by the way, insane. I'm surprised it can you have to be. It's checking you out. So.

Starting point is 00:19:57 Oh, my God. It's going to crawl through your site and just check out what you got and, you know, grab as much of the information as possible. I'm just surprised, honestly, that it knows how to navigate the website because it's like we created a world. So it's kind of like confusing.

Starting point is 00:20:13 Yeah. It's using a tool called, a Billigest Puppeteer, which is like an automation tool. So it automates browser tasks. It's a tool that's been around for a while in test automation world. And it's using that to do a lot of these things. It's similar to what browser use and, you know, cloud computer uses. Interesting.

Starting point is 00:20:43 Yeah, see. All I, you know, I just have your name and you're just a very broad ask and it just goes into this research mode to kind of find out about you. That's it. Now it's going to your Twitter. That's crazy. But it doesn't have it. I'm sorry.

Starting point is 00:21:03 I should say Twitter X. Right. It doesn't have an X account though, right? So it can only see a couple, a few of my tweets. Oh, wow. So it knew to click because in my, in my bio, it says, it says click for free startup ideas. It knew to click that. Wow.

Starting point is 00:21:20 that's crazy. Yeah, it's a different type of agentic AI, I would say. And I know there has been a lot of thing going on just like the other day that people found out that, you know, Manus AI is really under the hood running like Claude. Yeah. Yeah, there was a lot of meme going around talking about how, yeah, this is just a rapper and et cetera. that may be very oversimplifying it, I think. What they've done is create like a whole framework under the hood, I believe, is that they got a, you know, army of agents under the hood

Starting point is 00:22:00 with many different fine-tuned AI models that is using for specific tasks. And that's why it's doing what it's doing. And I think it's, they've done a really good job, in my opinion, in terms of doing, have this, you know, type of setup of AI that can do all of this task and use all these tools and and you're more, you know, less of a, it's less of a hassle for anyone to kind of start using this because you don't know what to ask sometimes. I mean, you just kind of have this question and you're, you're thinking you throw a simple question that you're not going to get like the information

Starting point is 00:22:42 that you want. But this goes like step beyond that. It actually like, look at what you're, like, look, what you saw, it will just crawl to your site, check out your bio, check out your websites, and trying to understand you as much as it can, and trying to grab all the startup ideas that you have. And it says it visited your personal website, checked out your social media profiles. It's got a little to-do checklist that it goes through, and it actually goes and does it, which is kind of, you know, remarkable on where we are with these kind of tools. And I think this will help people who are non-technical.

Starting point is 00:23:19 And I think that, you know, AI tool like Manus AI will help close that gap. I think a lot of people who are just kind of, I don't know where to start. You know, I'm sure they watch all your podcasts and all other people's, you know, YouTube videos. But some people still seem very lost is what I noticed. And they're always like asking questions, like, where do I start? what can I do? How do I ask? How do I prompt what template to use?

Starting point is 00:23:46 Sometimes it does be too much for a lot of the non-technical folks. But I think that discloses that gap. Yeah, I mean, it's non-technical and it's also like this is onerous and a lot of work to go and do all this stuff. So if you can have madness running during the day while you're working or even if it works at night too, I mean, anytime, I guess. it just seems like it could help you even if I mean it just could help you come up with the ideas that you want to do and then put it out in the world allegedly let's see if it actually could do it by the way I just heard my doorbell ring and I was like my first reaction is like

Starting point is 00:24:26 is Manis at my door is Manis just like coming you know man is that you that'll be pretty wild like now robot shows up at your door and you know hey I want to ask you have a couple of questions about your startup ideas. They'll be crazy. I feel like this guy's like stuck here. Collecting Greg Eisenberg's startup ideas from his podcast, YouTube channel and website. Maybe it's just like a lot of,

Starting point is 00:24:55 that's a lot. Let's see. Let's see what happens. I feel like he's stuck. Because typically when I see using browser, I'll see like, you know, navigation in the browser. Oh, right.

Starting point is 00:25:09 Yeah, it was doing that before and now it looks like it's just stopped. Could we ask, Manus? are you stuck? Yeah. Let's ask that. Check out your videos too. Maybe Madness is like, I don't want to give these guys the startup ideas. I'm going to go and build these myself.

Starting point is 00:25:28 I don't want to. Are you stuck? Are you stuck, bro? Wow, there we go. Wow. I'm not stuck. He point the finger to YouTube page. Yeah.

Starting point is 00:25:39 Okay, blaming YouTube. Okay, Maness. My dog ate my homework too. Let me continue. researching Greg Ismerk startup ideas from multiple sources and compile a list of his most promising concepts. I'll focus on gathering specific startup ideas. Let's check back on docuSign. See where he's, see where he's at.

Starting point is 00:25:59 So he's creating the app now. So another cool thing about this is that you don't have to have a, like a project structure, as you see on other tools, like where, you know, people say go clone this, you know, template, you know, this boilerplate code, and you can use that to build your app and have cursor and, you know, Winserve and other tools to, you know, build that for you. Because, because their template is more optimized, it's already like skipped a lot of steps, so you don't have to, like, ask cursor to do it for you. And this one, you don't have to do anything at all. You just kind of say, just go in and create me this app and it'll just create its own project structure and everything. Now, I know it's similar.

Starting point is 00:26:46 to what, you know, cursor and windsor does as well, but it's just another easy, easier step for people who wants to get started with this kind of tool.

Starting point is 00:26:57 How worried are you that this is going to Chinese servers and how do you think, how should people think about that? How is it going to turn out? No, no, no. Like, I know that Manus is a Chinese company, right?

Starting point is 00:27:11 Yep. So, there is, is some concerns with people around, you know, having a Chinese, like giving data to Chinese companies. Should people be worried about that? How do people think about the fact that this is a Chinese company, not an American company? Yeah, I mean, I think that there's a valid concern around that. I think the one of the biggest thing is that if you are a Chinese company, I think you're obligated to give access to the government.

Starting point is 00:27:47 So because of that reason, and I know people are very reluctant to use this. And I think, you know, again, it's a valid concern. And I'm a huge, you know, security, data safety, person, privacy. So I don't want people to go in, like, just start throwing any personal information and give any kind of stuff on these kind of tools. but at the same time, I want them to see where other, you know,

Starting point is 00:28:13 competitions are at. You know, if we don't know our competitions, that we're going to be behind. And I think that, again, some people are calling this the second deep seek moment for China.

Starting point is 00:28:27 And, I mean, we're starting to see a lot of that lately. And I think that we need to get ahead of ourselves in these kind of tools. And we have the technologies. We just didn't have someone to put the technologies all

Starting point is 00:28:38 together and package it like what Manus has done. And then it's good that they have done it. And now that we know, you know, what can and, you know, cannot be done. And I'm sure there will be many U.S. companies that's now, you know, going out there and trying to, you know, build something very similar to this tool, which is great. And I think that, you know, we need options. We need, you know, different alternatives. And I know there are already a several open source project that popped up that builds

Starting point is 00:29:07 around what Manus has done. So I think that's great. And I'm a huge open source supporter, and I use open source for almost everything. So I think that, you know, there's nothing wrong with, you know, using the tool that is located in China. Just be very careful and mindful of the, you know, what type of data that you give to and give access to. Because some of these may ask you certain things, and you don't have to give those information. Just keep it big. Just, you know, do simple stuff like try it out, like go.

Starting point is 00:29:37 like go clone this website or something and just kind of see how the tool works and what you can get out of it. I think that's the important thing, the learning. I'm a lifelong learner. So I'm always trying out new tools and trying on new technologies. So people should not be scared to try them out, but always be mindful of the data that they share. Cool. That's fair. Yeah. I mean, All right. Let's see where we're at with the Greg Eisenberg startup ideas. Yeah, he's still stuck trying to collect the data about you. And this happens.

Starting point is 00:30:16 It's not like perfect. It's still in beta. There are a lot of errors still. But it's still cool to see how it was browsing your websites and all that stuff, which is neat. And you can go back and you can't go back and see what it was doing. and all the search that it got, it found your website, your X page, your YouTube channel, your LinkedIn, your Instagram.

Starting point is 00:30:42 It's scraping all your social media profiles and checking you out, basically. Because they want to understand you. I mean, because I specifically said your name, so he wants to know who you are and all your startup ideas. So it's going to go in like just try to find everything. Okay, wow.

Starting point is 00:30:59 Madness computer has encountered a critical issue you can choose to reset Madness's computer or start a new session. So what should we do? And this does happen. So when something like this happened, you could either opt to reset the computer or start a new session, but let's try to reset the computer. So it's going to try to reboot this sandbox and try to restart the task. The cool thing is it remembers where it left off. Now, it's not a guarantee that this will be able to fix whatever the issue.

Starting point is 00:31:31 did he ran into. So we'll see. So it's going to reset. So let's go back to docket sign and see where it's at. It's still doing his thing. It's still building his projects. It's kind of, you know, very, like, worry-free. Like, it's doing all the stuff for you. It's just, I just sit back and just kind of relax. Would it be annoying to ask Madness? Like, hey, Madness, what's your ETA? Yeah, let's try that. So what is that? just like every annoying boss yeah but remember

Starting point is 00:32:09 the AI is what is the word um ever uh like not annoyed intelligent assistant right

Starting point is 00:32:25 yeah okay so oh it says I don't know if you like it was trying to troll us or something as soon as I asked it he was like I've completed it's like I'm done

Starting point is 00:32:37 it's like, what's your ETA? Like, oh, I'm done. Like, so we're, like, waiting this whole time until I ask? I'm like, okay, all right, would you like me to deploy? All right. So now I'd ask you a question,

Starting point is 00:32:48 like, do you want me to deploy this to a public network? And I say yes. So, and what is that's going to do is, it's got his own public, like, similar to what, like, Bursal RepLid has. It's got his own little deployable website. And it's going to give you a subdomain

Starting point is 00:33:03 with their primary domain attached to it. So you can actually see. the website in action. And it doesn't make you sign up to any service when you do this, right? Not yet. Not yet. Yeah. I think that when you start asking questions, like, and I haven't gone to, gone to that

Starting point is 00:33:19 level yet where I wanted to like say, hey, set up a stripe and stuff. And only because like we discussed earlier, they would, you know, force me to give out some of my information. So I haven't done that. I didn't want to go that route yet. Maybe I'll clear it like a dummy account and just try out. But yeah, I mean, because the glass half full of that is, you know, ask it to set you up with the Stripe account and then all of a sudden they hand it over to

Starting point is 00:33:43 the Chinese government or whoever and then all your money is gone. Yeah. Yeah, for your audience, yeah, don't do that. Like I said, always, when you're on the internet, I always be careful of what you share. So that's why I always tell all my family and friends and colleagues. I mean, when you're in the real world too, right? If you, you know, you hire someone or you're getting to know someone and you're just, you're giving them the keys to, you know, would you give them the keys to your apartment? Like, maybe not initially. Yeah, exactly. Yeah.

Starting point is 00:34:19 Yeah. It's compared to the physical world, it's so much easier to get those stolen from you in the digital world. So got to be even more careful. All right. So now it's working to deploy and demonstrate the East signature. I'm kind of excited. Yeah. I don't know. I'm kind of, I'm optimistic it's going to work, but I'm kind of like, how would this actually work? Like, this is such a complex. Like, we asked it to do such a complex thing, like a multi-billion dollar company in a prompt. Like, come on, you know what I mean? Like, can't actually work. Exactly. Exactly. Yeah. All right. So Manus has encountered an issue with the deployment process. So it's going to try to, I guess, try to see if you can oh so it's not going to run it so he doesn't want to create it in his

Starting point is 00:35:13 own production environment that he wants me to run it locally that's fair yeah because i mean i'm not a developer but or i'm a bad developer let's say um actually i'm not a developer i'm not a developer and you know i would do that right like i would want to try it locally first before deploying it, right? Yeah. So it's still doing stuff. Oh, it's just

Starting point is 00:35:42 zipping it up. Okay. I'm going to ask Manus to try again to deploy. Wow. You're getting greedy, man. You're getting greedy. You're ready to terminal error

Starting point is 00:36:00 while I was trying to zip. I don't know if it was because I just kind of interrupted. It says, encountered on the right hand side, Manus encountered some issues while performing this action. No need to worry, it will handle the errors on its own. Yeah, yeah, that's another part of the cool feature that is able to reflect on itself

Starting point is 00:36:21 on the errors that he ran into and he'll try to figure out on itself instead of me copying pasting or clicking stuff to, you know, hey, there's an error. So that's, that's, these are a type of seamless operation or, you know, user, experience for this type of agentic AI. And I think that's, that's the next level. That's, that this is where we're getting one more step closer to the AGI, where we, where we don't have to like know more than what we need to know and just let AI handle the stuff that probably knows it better than us anyway on some of the things.

Starting point is 00:36:55 So. Well, yeah, it's abstracted, right? It's abstracted. Yeah, it's very abstracted. Um, very, you know, black box. Some, some may not, some may like that and some may not like that. But I think for the most users, you know, they'd rather have it, you know, black box. They don't want to worry and think about it.

Starting point is 00:37:13 This audience, this is a black box audience. Like the people listening to this are like, yeah, I don't care how it's done. I just want to push my ideas live and I want to push a lot of ideas live. Yeah, just give me the results, man, you know? Yeah. So yeah, so I convinced it to try to deploy. So it's again, trying again. See what happens.

Starting point is 00:37:36 Yeah. What's interesting about your style, men, is like you're a man, a few words. You just like tell Manus a few words, not long prompts. And that's your strategy. Yeah. And I do both. Just to be clear, I do simple prompts and I also do very, very, very complex prompts. Because I want to give like a very specific direction. but for your audience and my audience too on X, and I try to keep it very simple. Otherwise, again, most people are just going to get lost on what to do. And I want to, I like to demonstrate to audience that it's a very simple prompt that I use and I got this results. And that just kind of always makes people like, oh, wow, like that was very easy.

Starting point is 00:38:32 I'm like, yeah, like, this is the future I want to get into. I don't want to have to think so much to come up with a very elaborate prompt, you know, when I can just say, hey, I want this, just get it done. And I'm sure along the way, you're going to have a lot of questions and sort of like an iterative approach to getting to your results. So I think, you know, that's sort of the step I'm taking with this. And that's the sort of step I take usually for my audience as well. I don't try to overcomplicate it. And I think that's sort of the way these agency AI is going towards.

Starting point is 00:39:08 I think it's trying to take a lot of that load of thinking off you and trying to understand, you know, what you want. And maybe in the future, maybe they'll just know exactly what you want after a while, you know, like after working with you for a long time, it will probably already know your history of what you wanted and you don't even have to tell them again. I think that's sort of like the AI future that we're going to start to see. So you got me thinking of something I think that could be big and I don't think we'll have time to cover it today. Maybe we'll, maybe we won't. But this manis seems to be that it's not just about how can you go and build a product and launch it. But it's also probably very useful for growth tactics and actually marketing and growing whatever it is you built. So I'd imagine. that you probably could do things like SEO. I'd imagine that you probably could do things like help, you know, create a content calendar, writing, researching based on different styles, you know, getting, basically organic content,

Starting point is 00:40:16 that sort of thing. Am I right or wrong on that, man? Yeah, yeah. I think absolutely you're on, you know, right on point on that one. And I think, and I just got me thinking, maybe we should, you know, have Manus go to one of your site and just see, you know, how is my SEO on this website. Great. Let's pull up late checkout.agency because I know the SEO on that's probably garbage. It's literally a landing, you know, a quick framer landing page. If you go to late checkout.

Starting point is 00:40:45 dot agency, it's our design agency. Well, I guess you don't even need to go to it. We can just ask madness to go to it, right? Okay. This website. Okay. All right. Let's ask him. Let's take this web's URL and say, pre-tick or? I want to, here's what I would, I would say, like, I have a feeling that my design agency could be getting a lot more SEO traffic. I'm looking for help from you. Oh, I'll wait until you type. Okay. Help me improve SEO for my just.

Starting point is 00:41:24 Let's start a new session. Yeah. See, I'm a long-winded prompted, prompt guy. I'm a long-winded prompt guy. Like, I write novels, you know what I mean? Oh, really? Yeah. Yeah, I'm one of those.

Starting point is 00:41:39 I try to keep it simple. Yeah, I like it. Okay, so you're going to say, help me improve. Not my websites by design agency. This one. Yeah. Okay, yeah. Yeah, okay, that's fine.

Starting point is 00:41:52 Let's remove your name maybe. Yeah, exactly. Help me improve. SEO. But I want to be clear, I do want to be clear that, you know, basically this firm LCA, lay checkout agency, it works with like the drop boxes

Starting point is 00:42:11 and the grammarleys and the character AI all these software companies and sort of big companies that are looking to be AI first and transition to be AI first and building AI products for them. I want to, it's not just that I want

Starting point is 00:42:28 better SEO. Like I want the executives from these tech companies to come to website, right? So you want those tech companies come to this website. You see all the companies we work with, Character AI, Bolt, Salesforce, Slack. And look at all the executives we work with at those companies. I want more of those executives to come to this website via SEO. I think it's important when you're doing SEO, not just to do, it doesn't, if I got a million visits a day to this, I don't really care. I'd rather a thousand visits, but they're highly targeted. Yeah, there we go.

Starting point is 00:43:04 You said it better than I could. So for the listeners on Spotify and Apple, I want a more executive of AI-first companies to come to this website. Okay. So it says, I understand you want to track more executives to the late checkout agency website.

Starting point is 00:43:20 I'll continue my SEO analysis with a specific goal in mind. Very cool. I love how we're running into Zaire. We're software testing Manus AI in real time. Totally. Again, they're going to remind us. that, oh, it's in beta.

Starting point is 00:43:36 Yeah. Yeah. Our bad. We're just testing. I believe a lot of the softwares are all in beta, and we're just software testing for them. So there's no news there. They just remove the label beta. I agree with that.

Starting point is 00:43:53 I work with many software companies, and there's a lot of issues behind the scene that we just don't talk about. So, all right. Oh, no. It has ran into an issue. This guy is not going to deploy. Oh, so this is a new message for me, because I guess I haven't gone to very long context, but Manus's performance may decline with extremely long context. So that's what he's saying.

Starting point is 00:44:25 So I think it's run into a context limitation. So that's one of the things that I actually wanted to talk about on this episode was that there are some limitations. to madness is not completely magical and just works like everything and it's going to do everything for you and you don't have to worry or anything. The limitation I've ran into obviously is the context. The context has like especially if it becomes a very complex task and it and there's a lot of information that it has to process. It does run into this issue. And I think that this is probably the biggest issue that Manus AI team needs to probably address before it goes live.

Starting point is 00:45:10 Because I think that a lot of people are going to run into this similar issues, especially power user like me. I'm going to keep pushing it to its limits and we're going to run into this type of issue all time. And this is not the first time I've seen the error that it's gone into other than this context. That it does ask you like, oh, I ran an issue, I need to reset the computer, I need to do this and that, and just ask me if I want to go ahead and restart or start a new session. So basically starting a new session means like it may have run into like some kind of long context issue that it's not able to process. So you have to start like a whole new session. And that's kind of the downs. The negative part

Starting point is 00:45:55 about this tool is, is the context size so far. Good to know. Yep. So we were not able to complete this stock design website. So that's a bummer. I think that we probably could do a local deploy and try. Yeah. Let's try it. I mean, even the fact that we can do a local deploy is absolutely insanity.

Starting point is 00:46:21 Actually, it was trying to zip this thing for me, for me to download and it failed earlier. So let me check if it was able to finish creating the zips. I mean, it's create all the document structure, the code files, but it doesn't have to the zip. Yeah, it's so interesting seeing how different people prompt. Like, I would be prompting right now. I'd probably say, I'm just trying to get this to a local, to deploy this locally. I want to create something that's beautiful that I can show on the podcast.

Starting point is 00:47:00 And do you think that you can. make that happen. Like that's how I, because I talk as if I would be talking to a coworker. Yeah. I think that, you know,

Starting point is 00:47:14 um, this is probably quicker anyway to run it locally. Yeah. To see the results right away. Because like deployment is, it's not as a straightforward with these tools. Um, and I know Replit has done that really well.

Starting point is 00:47:28 Um, and I think, I think that's, it's got some good future and, you know, where the direction that it's trying to go. Uh, Their AI agent is getting better and better.

Starting point is 00:47:40 But Manus has to work on their deployment process as well. I think they're just trying to do too much. I think that's part of the problem is they're trying to have all of this kind of package, like all this services and products that kind of packaged into this one thing, including deployment. And obviously it kind of shows that deployment is not an easy, easy one that they have solved yet, in my opinion. I know there has been like other.

Starting point is 00:48:05 are very simple ones that they've done that shows this like if I do like a game like you know make make a airplane game like Peter flypetre.com right yeah fly dot peter dot com you're talking about the peter levels game yeah yeah yeah so peter levels basically made like a flight simulator using AI 3 j s oh oh maximum Daily usage limit. Yeah, there's a, yeah, so there is a limit. I believe it's 10. So I actually use a few before this episode so we can't do this one today.

Starting point is 00:48:57 Unfortunately. You know what's also cool? It feels like we have like four employees working at the same time. What's that? It feels, it feels, what's cool about menace is it feel, it really does feel like you have multiple employees working at that. It's like, oh, we've got this SEO, this marketing person. We've got this researcher.

Starting point is 00:49:14 We've got this. cracked PM slash developer. Yeah. Yeah. You got one guy working on docket sign, you know, one agent working on your startup ideas, and one, you know, working on your, on the, you know, improving the SEO for your LCA.

Starting point is 00:49:35 So. It's crazy. But another thing is that the, the problem that I see is scale. So, obviously, you know, AIS scale is a challenge for a lot of the companies. And the reason why they're very, right now they're invitation only. And with an invitation code, they can only have access to MANIS.

Starting point is 00:50:00 And they're limiting those codes too. And I've been privileged to get like 10 invitation code from them. And I actually give them that out to users to my, my X account. I actually asked for 10 more. I was going to offer it to your audience, say, hey, Greg's audience, you get 10 codes, if you want to try it out, but it didn't happen. So I think that the thing that I noticed is that very early on, when people were starting to get access to Manus, their web, you know, their web has been

Starting point is 00:50:44 hammered. And the reason why we're seeing a lot of errors today, actually, I was not seeing this much error in the beginning because there were as many people who had access. But now that more access has been given out and more people are on the system, I start to notice a lot more frequent errors. And I think that's part of the scale issues that they're going to have to address again before they go live. And do we know when they're going live? I don't know yet. I have not heard any, yeah.

Starting point is 00:51:21 And I think that they, you know, they're trying to tease early. It looks like they launched premier trip, kind of like what? It's been like six days now. Yeah. They actually launched like six days ago, but it didn't like go viral until like two days ago, basically. So when it came over to US and people in the US start to get access to it. And that's when it started to get like real. action and I was one of the early ones who got access and and it was working pretty good.

Starting point is 00:51:51 You know, obviously we've done, I've done stuff like pretty basic, you know, comparisons like doing the deep research or deep search type of thing making a, and as you can see on the left side, you know, I had more, but I deleted them because they kind of crashed. But, you know, build a simple SaaS website, you know, clone the apple.com. Obviously, apple.com is one of the, you know, well-designed. website. So I think it's a commonly asked thing like people like go clone apple.com and then, you know, do a casual, multi-clear game. But the research one works really well, obviously. You know, you expect that to work well. Simple games work well. Landing pages work well. And I think that's sort of

Starting point is 00:52:42 the ones that have been very successful with Manus AI so far. I think that the other one that it does well is something like this, like you're analyzing your websites for optimizations, scraping data. It can actually, because it is able to control the browser and go to go to this website and actually crawl through it, like clicking stuff, like you can actually scrape data using it. So I think that's one of the very easy, easy to use and probably frequently use a tool to kind of get information for, for the people. And as you get more complex, like doc design and stuff, like it does, it does have its challenges. But I like to push things to its limits. So just to wrap up, maybe let's just go through what we've done today. Let's go through the

Starting point is 00:53:40 DocuSign, let's go through the startup ideas, and let's see, let's see what we were able to do in, you know, 60 minutes using Manus. Yep. So we started with this create DocuSign clone, and the middle of it, we say, hold on, let's just focus on the e-signature. So we say, okay, just focus on that. And it replanned its project, and it set up all the code. And I didn't actually yet to see the code yet, but it looked like it's set up as typical NextJAS app, set up its routes.

Starting point is 00:54:24 And then it was create a interface with login page, register page, the routes, the passwords, the middleware routes. So it looked like it went through a lot of the important things that it needs, the basic ones at least. And once it got through creating this code, it got stuck on getting the deployment successful. So it got document upload, document management, and the signature field placement. So I'm actually excited to see if it actually runs, but it wasn't able to deploy. So what I would do is I would I would actually run this locally and then I can like send it over to see what that looks like. Again, one thing that I do when it asked me to run it locally is I do have to scan through the code just in case.

Starting point is 00:55:23 Totally. Yeah. I don't just want to download this. That's why I didn't want to do it on this recording. Yeah, that's fair. I don't want to look like paranoid. We're keeping it real here. Yeah, just trying to play safe.

Starting point is 00:55:38 You know, I don't know what's going to happen. And I do like to create this into like my own sandbox. I don't download this stuff into my local computer. I just create like a virtual sandbox in the cloud. And then I run it there just in case as well. That's cool. I don't want to do that on this session. But I will do that.

Starting point is 00:55:59 And then I'll show. show how that ran locally. Beautiful. And then let's go back and check your top start ideas with highest potential. Again, it got stuck. So the thing with this one is interesting is because research has been very straightforward for me

Starting point is 00:56:16 and it worked. And like I was mentioning earlier that since people got access to this application, I've seen a lot of these issues where it hits a wall. And this should have been a very easy, easy thing that should have completed, but it wasn't able to. So, and again, like, probably the time of the day is not the best.

Starting point is 00:56:42 I think a lot of people are probably on it and then asking stuff to do. So it may be running into more of this issue. I may try to run this again later, like late in the night, where it's the traffic a little bit lower. And then the other one is that we try to ask to create, to create an airplane game like Peter, fly.peter.com in 3JAS, deployed in public, and we reach the maximum daily usage limit. Again, this is in the beta stage.

Starting point is 00:57:14 There is a, I believe there's a 10 request or 10 sessions limit in the day. The cool thing is that even though it says this, I can actually go into another session and run it. I believe it's the session. that it matters. So I'll use the one that is like broken, which is like this one, I think.

Starting point is 00:57:36 Right? This one's still working. So this one's broken. So I'll use this one to say. I don't know if this is a loophole that I found, but when you reach a maximum limit, it sounds like a different session and it will, you can tell it to do something else.

Starting point is 00:57:53 That's awesome. Yeah. So now see, it's like, I'll help you create an airplane game. So it's just like a new session, basically. But the only, only difference is that it's got like all this other stuff in the context, so hopefully that doesn't

Starting point is 00:58:03 interfere with what I just asked. Right. Oh, my. Victor from Hugging Face actually did something similar, but he didn't specify fly that peter.com, but he just said create a, you know, flying airplane game where I can control the airplane and whatnot, and it just kind of, it looked like he did it in one shot. And the people are asking, like, was this one shot or was there like follow-ups? but I'm sure there was a follow-up.

Starting point is 00:58:31 It doesn't actually produce everything like in one go sometimes. And you may have to kind of tweak some of the features, especially like aesthetics I noticed. So you may just like throw like a very simple aesthetics. And you may have to say, oh, can you make this a little bit more pretty or make it more, I don't know, more objects in the scene. Because if you just ask you to like create like flying game,

Starting point is 00:59:03 you may just create like a sky and like a plane field. And you may have to give like specific instructions at a building, at a tree at lakes or something, something to make you more interesting. Okay. So yeah, we might even show a clip of of that one shot prompt. So just showing what that could look like. So Min just sent me a message.

Starting point is 00:59:26 Literally this is just right after the pod was, recorded saying our flight game had been created. So we basically one prompted a flight game. It looks like a more basic version of Peter Lovell's game, but it's pretty cool. Here you can see the plane flying and I believe you can shoot. Oh, maybe you can shoot, but that's the idea of the game and you shoot down these balloons, which is pretty cool. And you can play it. It's deployed. You can play it on your web browser. I think the next step for me would be how do you,

Starting point is 01:00:05 I mean, just make it look a little more visually cool. And also add multiplayer. I think one of the reasons why Peter Levels game, I mean, it has gotten, there's a few reasons why Peter Levels has done $67,000 revenue in the last 30 days. Part of it is his audience. You know, he has a big audience so he can distribute it.

Starting point is 01:00:28 But the other part is, it is fun. I know I tweeted about his game and a lot of people are like, it's not, it's such a stupid game. And it's like, I don't know, I was playing it for 30 minutes and I was enjoying it. Like I could have, I could have watched the White Lotus, but I was watching, I was playing that, enjoyed it. So Manis did it. It took one, one little prompt and we got a game working. So that's really cool and it was deployed. So we've gone over the docusine. We've gone over the game. we've got the SEO and we've got the research assistant

Starting point is 01:01:02 we've done this all in like an hour which is kind of crazy we haven't been able to successfully deploy you know we deployed the app basically but it got us almost there

Starting point is 01:01:16 like we just have to review the code deploy it run it locally make some edits and then finally deploy it but overall my take on this,

Starting point is 01:01:29 Min, honestly, is that it's, yeah, it is the closest thing I've seen to AGI yet. And it seems, it seems like it's close. It's not there yet. Like, I need it to, I need it to deploy.

Starting point is 01:01:44 I need it to deploy. But the fact that it feels like an operator mixed with like a, you know, replet mixed with a chat GPT, like I think that having, having this is super, super, super, super helpful for people who want to like automate, build their businesses, which, you know, and that's why I had you on the pod. So, Min, I wanted to thank you for coming on the pod.

Starting point is 01:02:07 And I wanted to ask you, you know, where could people find you? We'll include those links in the show notes. Yeah. Thank you for having me. And this was fun. And people can find me on X.com slash Min Choi. That's currently my main page. Cool. All right, we'll include that. Min, thanks for, I mean, you had the beta access. I didn't. So thank you for hooking it up for everyone. I think a lot of people are appreciative of that. And let's go build some businesses.

Starting point is 01:02:40 And I got an extra key for you so that you can have access to if you want. Oh my God, yes. Please do. And I'll play around with it if people want more madness content. Please do let me know. And I'll see you next time, Min. All right. Also, Min, I know this is your first podcast that you've ever done.

Starting point is 01:03:01 So thank you for sharing it with us. Hey, thank for inviting me. I've always meaning to do one. Just didn't get to that step yet. But maybe this will be sort of my kickstart into the podcast world. Absolutely. All right. Catch you later.

Starting point is 01:03:18 Amen.

The Startup Ideas Podcast - Manus AI replaces your AI tech stack? (Full Demo)

There aren't comments yet for this episode. Click on any sentence in the transcript to leave a comment.