# Inside $180B Co-Founder's AI Agent System

Channel: Greg Isenberg
Video: https://www.youtube.com/watch?v=oDl-A2Uez58
Duration: 31 min
Language: English
Words: 5915
Transcript page: https://viewrankai.com/tools/youtube-transcript/oDl-A2Uez58

---

[0:00] Sam Altman predicted the one person, one billion dollar startup powered by AI. And I think we're starting to see a glimpse of it. My friend, Furqan, he used to be the co-founder of AppLovin. AppLovin is like a hundred and seventy-five billion dollar company. And what's cool about Furqan is he is always tinkering. And today he's doing a little bit of a show and tell. He hasn't done this anywhere, but he's working on this agent platform called Nebula. And he wanted to show it to me and he wants to show it to you because it's a platform for you to take your ideas and build a one-person

[0:33] business powered by agents. So, think about creating a blog that creates content for you three times a day based on X trends. I think that's a glimpse into where the future of building a one-person business powered by AI looks like. So, today I'm excited that Furqan came. He shared his product. He shows how it works. And what I hope is it gets your creative juices flowing for how you can create a one-person business powered

[1:01] by AI agents. Uh, let's get right into it. [music]

[1:11] [music] You are in for a special treat, everyone, because Furqan, he really is my go-to guy when it comes to tinkering with new technologies. He's um I've known him now for, you know, over 10 years. And this is a guy who when he speaks, I listen. So, thank you, Furqan, for coming on the show today. Um Furqan, by the end of this episode, what

[1:37] are people going to learn? Uh like you said, I'm a tinkerer. So, my nights and weekends are really just playing with new technologies. Uh you know, the last few years, AI and agents, can't can't pull away from it. So, I'm going to show you like some of the power that's already there in the world and um how you can leverage it and how you can

[1:57] use it to just accomplish more. Um get to get things done that are in your mind and you you don't know how to do them. And I I feel like um [clears throat] capability-wise, we're we're in the age of abundance. So, I hopefully I'm going to show you a bit of abundance. That's what I want to hear. All right,

[2:14] let's get into it. Sweet. Uh so, I'm going to show you like basically like I was saying, I've been tinkering for, you know, many years now around AI systems, LLMs, agents. The last few months, though, it it it kind of did become more obsession than just tinkering. Um you know, and mostly because I had built up all of these agents to do very, very useful things for me like, you know, like you, like I do a

[2:41] lot of stuff. There's a lot of Slack. There's a lot of people. There's a lot of like activity going on. You can't keep up with it. Um So, you let it go. You you delegate. You move on. But then there's just like things I do want to get my hands in and and and how do I do more of that? And

[2:55] so, I built up a bunch of agents myself. I had kind of like an opinion on how I wanted them to work and what kinds of things they wanted to accomplish. Like, where should you just go full send and where should you dial back and ask me? And then I was like, wait a minute. As I'm telling people, this is pretty useful. And the obsession was just like maybe I'm just going to make it a product that I can use. So, I'm customer one. But I also think other people can use it and it's very useful. It is rough. So, this is, you know, one of those I'm showing

[3:23] you something that's we're going to see some breaking points. But I do think I can show you kind of some of the the cool ways that that I'm approaching the problem. But um I'm going to screen share right here. So, yeah, this is uh this is Nebula. That that's that's kind of what I've been calling it. And uh you'll notice first that it looks a little bit like

[3:43] Slack. And it's got these channels here. And I think my goal was like a lot of work happens in in Slack in this kind of messaging experience. And uh I wanted to just mimic that. Except everybody in here is an agent and can help me get work done. And you know, I'm an engineer. You know, I I spent a lot of time in the technical side. I got things like Claude code and cursor and codex that I leverage to make my coding so much more powerful, so much

[4:12] more impactful. Um And you know, I wanted to make all the other work feel the same. Um and you know, a lot of it to me lives in the cloud. Uh it's services that we use like GitHub, Slack, Linear, Notion, Google stuff. And uh like a lot of work just happens there. And And I think flow-wise, it feels similar to how I engineer things when I'm developing. But

[4:35] there aren't the tools in the same way. At least in the AI front. At least, you know, what I felt that that we're solving that. And so, to me in many ways, this is like Claude code for everything else. Like, you know, for the non-engineering tasks, for all the other work that I want to get done. Um And so, we mimic Slack. You have these kind of channels. You can, you know, kind of create things. Uh we'll do, you know, some sort of a test where we can, you know, connect to, you know, Google Slides test. Uh kind of show you like how you could, you know, kind of do

[5:02] that. And so, um if I was just going into a channel and I'm like, you know, I want to connect to Google Slides. Uh can you create a new slide for Um and you know, this idea is Nebula's this agent. It you ask it to do stuff. It will do things. It will try to figure out, however, to do it. And uh it has all the knowledge of the internet. It can search. It has a browser. It can find things. It can look up documentation. And then we gave it the ability to write code. So, it will write code for you that it can, you know, um

[5:44] you know, help help accomplish tasks. So, even even if you don't know how to write code, it knows how to do that. It can execute it. And so, in this case, it did make this presentation that's a brand new one. Um and I'll kind of pull it up here as we're editing it. And so, it now made this presentation. I am not going to

[6:02] touch the presentation directly. Um and I'm just going to have it like start modifying and doing things. And so, if I was like, you know, I'm on a podcast with Greg and I'm showing him Nebula. This podcast is for startup {slash} founder {slash} team leads that focus on building and producing great companies. I want to do to create a three-slide deck um outline on Nebula and what it's

[6:40] useful for. And so, this part is Yeah, yeah, go for it. Yeah, I was going to say like this is sort of a glimpse into the future of how we're going to interact with apps, I think, right? I think so. Um you know, obviously text is a modality that we're very comfortable with. I'm I'm very, very interested in audio and screen share and live synchronous. That's kind of to me the next part of stuff that's going to come here. It's like I not only want to type asynchronously, maybe from my phone, but I also want to just get on a call and spend three minutes explaining my entire thought process and

[7:15] then Nebula can go off and work. And you know, we built an engine behind the scenes. That's kind of like the main thing. The text is the input to the engine. But you know, I do think here. And And so, you can kind of see that it's taking control of this presentation. It's now starting to edit it. It's saying that it's going to create an update slide one. There's a bunch of hidden stuff here like it, you know, created its own to-do list. It, you know, told Google like, hey, replace

[7:41] all the text with this for this slide. You know, like these are things that if you're writing a program for it, it's actually doing all this stuff. It's doing API requests for you. It's kind of making making all of these things happen that an engineer would do. And you know, we're here and and and now kind of had all of these. And uh great. And And so, now this is a kind of like a basic slide deck. And so, let's make a fourth slide and add an image that shows the power of Nebula. Make that image the

[8:14] entire slide. So, now it gets a little bit more complex, right? It's got to go and and understand the context of what we've been talking about here. It's going to make a fourth slide. It's going to generate an image. Um you know, it it comes up with the prompt that needs to be done. In this case, it said a powerful visualization of AI agent network. It's a glowing node. It kind of took some, you know, direction. It had an aesthetic. If I was very specific with how I wanted it to

[8:40] look, it would just listen to me, right? Like and and and and try to generate that. And um you know, the idea here is like cool. Like a lot of this you can kind of do with Claude and ChatGPT. You could do some of the research. There's maybe web search. Okay, now we're connecting it to services. And that's kind of step one of of of an area

[9:03] that it can kind of operate. Um okay. Like it can manipulate these things. It can do it. Um it can connect to image or video generation things. It has Python. So, you it'll get a little bit more advanced if I push it a bit more. Um so, it did kind of create an image in

[9:20] here. You can see a file was created. Uh it has its own file system. So, you don't have to be on a computer somewhere. It generated this image. You know, style-wise, don't love it. But I could tell it, hey, I don't love this style. Like go do something else. Um and you know, we're going to see it create the fourth slide

[9:37] here. And then kind of kind of go from there. And you know, you can see it's actually writing Python right now. So, again, we're not engineering, but this thing is. It wrote some code to, you know, take these files and upload them to Google Slides. There's, you know, an engineer somewhere that would be writing this integration for you or you'd be connecting some

[9:59] no-code service. Just live, it'll kind of figure out how to do it all and and take care of it and you know, in a second here we'll see this kind of image pop up here. Yeah, a little failure here and it'll correct itself. It'll say, "Hey, let me try something else. Uh let me try a

[10:13] different way to do it." Um and you know, this is part of that AI system is like AI is not perfect, but could you just tell it to keep trying until it works? It it it kind of can and it will keep trying to do things over and over again until it finds a pathway to accomplish it or at some point it's like, "Hey, I have no way to do it." And you know, okay, so like we're we're trying for a third

[10:37] time. Let's see if it gets it and uh I think we'll see an image pop up hopefully here. Yeah, it says created a file. Something's something's happening. Stuff's happening, right? It's it's got some files in here. Right, it wrote it wrote this like Python script. Uh like again, this is code that Nebula wrote for itself. Like, "Hey, this is

[11:02] the file that we have. Here's the presentation and I want to kind of create this image and go do it." This is code that somebody would write 16 by 9 roughly this, you know, kind of all of the requirements that you would have. Uh it's complaining about the size of it. Um cool, we have an image here. It wasn't the image that's there, but it

[11:23] tried. I could push it more by the way. I could just tell it to kind of keep doing it and that'll be there. I think some of the power happens work is not synchronous like this, right? And so, one of the biggest things I wanted was it you know, I can get a lot of this in other places. I could write scripts, but now I'm like, "Okay, cool. Now let's add a new slide every

[11:45] day with more information about Nebula. We want to get this presentation to 15 page 15 slides uh in a week. And so, it has scheduling, right? It will actually go and say, "Cool, what is the thing that you were doing here? What was the context? Let me pull all of that out of this piece of work. Let me create a recipe for that so that we could

[12:13] reproduce this dish over and over again. And then write the you know, the trigger, you know, it wrote a cron. If you're technical, you know what a cron is. And you know, we can go over here to the triggers and see there's a daily Nebula presentation update. And so, every day it's going to add a new slide. Goals to reach 15 slides in a week by adding two

[12:34] slides a day from current slide four. And here's the execution steps. And it'll just run every day at 9:00 a.m. And now this is hands-off. And um you know, maybe a slide deck is not the approach for it, but for example, if we wanted to make a blog, that's what I would do. I would you know, go and edit the style and and I can actually show

[12:56] you that that workflow as well. Um where we you know, we can kind of quickly create a blog and every single day it can kind of produce those results. I can dictate where to get the information from, search it from Twitter, search it from the internet. Here's how you think about the analysis. Here's the visual style of the images of the blog and how we want the text to work. Uh and then you connect your post-talk to it and every day you tell it to optimize itself and and and we can

[13:23] do that now, you know. I mean, that's sort of the dream for a lot of people, I think, is they create a business in a box, you know, maybe it's content, but you know, it could be like an email newsletter every single day, you know, you search on X, you search on you know, press releases, Google News, things like that. You have a style guide around how you write. Uh and then every single day you you know, you're pushing out content and you sell you sell, you know, make money via affiliate ads or maybe you sell ads and stuff like that, but I think this is you know, an interesting like

[14:05] when I see this, I'm that's kind of like where my head goes. 100% and and that was actually one of my starting points is like, "Okay, why do I want to create these scripts and agents that are {quote} intelligent?" Um well, I want to automate my work. Well, if I just extrapolate that to the end, it's like I want an automated company probably. Like I want to create some direction or guidance and I want to work with intelligent systems to kind of go do that. Um you know, and um like

[14:38] great. And so, I started thinking. I'm like, "Okay, what's like the smallest company project that I could do?" And uh a a blog is kind of one of the things I landed on. It you know, I can think of a you know, content direction. I can think of source of information. I can come up with visual style, editing style, as well as you know, the ability to connect to my system. In this case, I'm using Ghost. And then, you know, from there I'm telling it to run every day and then what am I going to do? I'm going to look at the search console and post-talk and optimize keywords and just

[15:16] do that every day, right? And and and I think that was one of the North Stars that I actually started from was, "Can I just have it run a company, a project just on its own like autonomy?" And I do have a blog that I used as my kind of like testing grounds for building this. And it it's now 15 days in a row been doing three posts a day. I think the

[15:34] blog has gotten to about 100 hits a day. I I I just set it up. Like I I spent less than 30 minutes on the setup and then, you know, kind of from there it was good, you know, uh to go. And and if I spent more time, it would do that. Someone in the comment section, I can

[15:54] just hear it so we can just address it. Someone in the comment section is going to be like, "Well, if everyone's going and creating these business in a box blogs and stuff like that, you know, is there still opportunity or is it going to get commoditized or what does the world look like in you know, a few years when anyone has the power of

[16:15] something like Nebula?" For sure. Um I think as we get more advanced, we there are things that are no longer that interesting. Um you know, there was a time period where just having a website was a competitive advantage, right? Like having a dot com. I'm a little you know, I got the gray hairs, you know, dot com era. Like literally being a dot com was an advantage cuz you created the accessibility. And then, yeah, like being a content creator or a blog you know, blogger was an advantage maybe 5 or 10 years ago. And yes, what's going to happen is you know,

[16:50] everybody gets access to these things. Now we flood it. Well, the basic version of it is not going to be useful. I'm going to have to apply the same logic to kind of the next level of things. My content is going to have to be superior. My deliveries going to have to be superior. Maybe I'm going video. Maybe I'm going more advanced, you know, and I'm going to build agents to help me do that. I can make a blog critic agent that just loops against. Every time it produces a post, I can say, "Hey, ask

[17:19] the critic. Make sure this is a nine [clears throat] out of 10 on these metrics. And here's how we determine that and then test your thing and learn the next week." And so, I think we're just going to go more and more advanced um you know, in terms of you know, what what's kind of there. And so, I connected to this like Nebula demo Ghost blog. Here's my Ghost admin side. I told it to make a test draft post. And it it's there. It it's connected to the

[17:46] system. Now it's up to me to create creativity, you know, like, "Okay, cool. This blog will be VR-themed specifically about new apps and games coming out in VR. Can you do the research from the top VR influencers to find the latest and greatest games? Produce a post and an image." So again, if I get much more advanced with the instruction like this is not advanced. This I'm just typing this very quickly. If I got like very fine-grained. I gave it a paragraph of stuff that I care about. If I'm kind of going to go and and do a lot more, then it will be better. And you can kind

[18:34] of see it starts working in parallel like multiple things start happening. It created these to-dos of things to do. It now has like five different searches going on at the same time. It's you know, dumping all the info. For now, again, this is UX that I think will improve over time and on what it should

[18:52] look like. Right now, it's just verbose. Great, I can see all of the work that's happening. But this is like real work, right? Like and I can give it significant specificity around my focus area. You know, I could tell it to design my blog differently. I could tell it, "Hey, I don't want it to be looking like a blog. I want to integrate it into my website and connect my GitHub." And it it can take these parts and connect them together. I think that's the power that I wanted is this system that can live in the cloud. It has the code execution, the file systems, all these things that I have in

[19:24] my cloud to but it just lives on the internet. I start connecting it to different services. I get more advanced with the system. It starts managing multiple schedules, multiple things, multiple optimizations. Um I I I feel like we're still like I said at the start, this is an age of abundance and so, we're not taking advantage of the abundance yet. I do believe that once we get and we're taking advantage of it, maybe it'll be too much and we'll go back into the age of you know, organic or the age of, you know, taste. Um so I don't think that, you know, this never ends, this cycle of

[19:58] like a lot of stuff go to the kind of top more popular things or, you know, crafted better. Maybe we go more human-centric. Tons of stuff this helps me get done. I can manage my calendar. It has an email address so it could just reach out to people on my behalf and and and manage conversations. So if I'm doing lead gen, if I'm doing a trip, and I want to reach out to hotel or something like that. Uh we just wanted to give it the right package of things that you normally hire somebody to do and then I think you're just figuring out like how do I get it to do more? And

[20:32] you know, I think if you spent $1,000 a month and had uh AI team, it sounds a lot, but I do believe you'll produce five or 10,000 dollars of value for yourself if you just point it in the right direction. So that part we've always had to do that. We have to point the thing at the right direction. And I think that creativity will never get

[20:52] lost. That's where humans come in. All the other mundane stuff in between, like this research, writing the post, generating these images, going and scheduling all of these things, like I think that's what kind of goes away and and that's already capable now and I think that's what that's why I ended up building this. It was like I was like, "Dude, I got this power in my hands. How

[21:10] does everyone get that?" So I agree with you. I think uh it's really about you know, how do you point it to the right thing? And that is often the hard part. Uh one-person business, I think a blog, a newsletter, those are there's a huge opportunity now for the next 12 to 18 months. What else comes top of mind if you're trying to build a one-person business in the age of AI? Like what do you how what are you brainstorming and how

[21:42] are you how are you thinking about that? Yeah, so in in a company, you know, a blog might be less than 2% of the entire company of work, right? Like it might be like, "Hey, we have a blog, but we have 99 other things that we do." And I think about all of those workflows, like where where is the like creativity needed? This is where I got to put the most talented humans in charge of and arm them with

[22:12] tools. And then what are the things that they produce? And so you know, the reason I wanted it to make this feel like Slack was cool, I got my blog. You know, now I'm going to be like, you know, making my lead gen channel and starting to kick off like lead gen work, right? Like go and research these, do it every

[22:32] day, go craft emails, go send things. And then I'm going to be like, "Well, we have our product analytics work that we need to do. So I'm going to connect my PostHog, right? I'm going to be like, you know, connect to my PostHog. Um you know, create an agent that can you know, analyze my

[22:55] you know, web traffic. I'm you know, like I'm just like, how do I just spawn up many of these agents? And in in different channels, like here it says, "Cool, like let me connect your PostHog." But but that's what I'm thinking about. Like I I think a lot of work is not uh it it does get more complicated, right? Um you know, and uh it does become a thing where it's like there's

[23:22] many many more things to do. But I I think a lot of them do come down to directive and workflow. Um you know, the whole no-code movement I was super fascinated with. I was always the engineer that I'm working with every team in the organization, marketing, business, sales, whatever, to like help them get the power of what

[23:43] engineering had. It was a lot of work. It was hard to commit resources and and do these things. No-code and SaaS kind of came out and and you know, really unlocked that and we and we saw that. And and I just think that the next thing with AI is is that it will elevate that to every corner of the

[24:02] company. I I just feel like it's it's kind of getting to the stage where, you know, there's no longer a limit here. It's just like what what work do we want to put them through, you know, like you know, kind of like like like that that's the experience that that I'm thinking about. So you know, I got my blog. It

[24:22] it's coming up with all these things. The reviews are actually while we were talking and doing something else, the reviews should be in here. Um you know, it made an image. It came up with something. We didn't give it any direction. We can definitely increase the, you know, editorial quality here by just being much more fine-grained with

[24:42] our directive. It actually went and did research, you know, for me. It it produced this. I could just be like, "Hey, go publish this, right? Like you know, looks good. Let's publish. Make three posts a day." Now our blog worker's going. We're going to go work on the analytics worker. This agent's going to have stuff. You'll you'll see different agents show up in

[25:05] the chat here. There's an agent creator. It's just going and making this thing. Now it's building custom stuff. Like So I think like I I see a lot of like inside of companies how work happens, what what's going on. What does it take to go do this? I mean, times have you asked somebody on your team, Greg, to like go connect and add analytics to our website or you know, then then it's

[25:27] like, "Cool, go make the dashboards." And then go do this and at the end, what are you trying to do? It's like, "I want to see how many people came, how many new people, what's the retention?" It's like, what if we can get to that level? What what's the unlock of our creativity? I also think there's you know, when you think of agencies and service businesses, like a lot of the time they're delivering this service, right? So there's tons of content agencies that churn out blog posts for a monthly fee. There's tons of analytics agencies that'll set up your PostHog and give you reports and do

[26:00] research. So I also think that you know, for for people listening, there's an opportunity to use something like this and basically do client work, but the service is instead of having literal humans do it, you you you have I mean, you're going to have some humans manage it, but a lot less humans, maybe a 20th of the amount of humans, and then you have these agents go and actually create the the the service, right? 100% Like I mean, you know, a lot of people are like, "Oh, well, humans will be gone then, right?" It's like, "No, like I think we still decide what we want to do, right? Like some point

[26:41] somebody has to direct things." And I I think people like, you know, notice I know the word PostHog. There's a lot of people out there that might not know that. So okay, like like somebody's still going to like have some knowledge and direction and directive. And I don't think AI replaces how we go and get our results. I think what it does is it allows us to take a a direction we want to go and progress us towards that faster. Like we are creating the circumstance of where we want to be, you know? Um and you know, while while the analytics agent was being set up, it published the post. I

[27:22] think uh we should be able to see it at this URL now. Right? We got one. It still looks like a demo blog. Cool, we're live. And uh it now set up the trigger. So it's going to do it three times a day, right? It's going to run in an hour. It says it's going to run at 6:00 a.m., 2:00 p.m.,

[27:42] and 10:00 p.m. And it has an agent attached to it that it knows all the knowledge of everything. You know, like I'll move on to the next thing and you know, I'll come back and add more to it and you know, I I I think the experience of continually upgrading and iterating my processes to get more advanced. I'm showing you very like this is like day one of your company, you might set up the blog, you might set up the content thing, or, you know, your internal kind of like workflows. But then your company gets more advanced and you're going to add more things and you'll end up with like 20 or 30

[28:14] channels. Like you know, a lot of the stuff to even build Nebula, like I'm using Nebula itself. The change logs that get produced, the images that are kind of in different places, like styles like that we want to kind of focus on when we're trying landing page tests and the analysis. Like every day there's like an experiment analysis agent that, you know, tried three different variants for our landing page and just told us the results. And then we tell it like, "Hey, these attempts

[28:41] suck. Do something better. Go like this. These sites are great over here. Go look at these sites and research those." And then try that. And then the next day is very very different. Um and and and so I just found that like a lot of time gets spent in creating the workflow. Like I love n8n, don't get me wrong. I have many self-hosted instances of that over the years. I like tools like Zapier. They're very instrumental in, you know, a lot of work being much easier. It was still pretty tedious to do. I kind of, you know, I just landed on can I just tell it? Can I just tell

[29:12] it what I want? Cuz that's what I want to get to. And I just scratched my own itch here and you know, wanted to you know, wanted to go from there. Well, I love it. I think it's it's a glimpse of where how work is going to be worked on and it's a glimpse of like the opportunities in these one-person businesses and and then optimizing your internal company. So I think this is really cool. Um dude, that's why I had you on. I knew you're always tinkering and and thanks

[29:41] for this Is this Is this live yet? This is live. You can just go go um and use it. Uh, I have not hooked up billing yet. I won't until the cost are significant. And so go use it. Go burn tokens. Uh, tell me what's wrong. I'm happy like I I want I want all the feedback cuz you know, like I scratch my own itch. I I know what I can do with this. The question is I can I take the UX that's useful for me and get it to other people and it is that that's fun. This you know, there's a lot of people that tinker and

[30:14] then that that's kind of the hobby and then I always tinker till I I want like I want a lot of people to use the thing that I tinker with. That would be the net end outcome is a lot of people find this exceptionally useful. And I think you're going to find bugs. You're going to find things you don't find useful. Just tell me. I'm I'm happy

[30:30] to iterate here. I appreciate you for a con. Thanks for for sharing the product, your thinking, firing people up about some of these uh, ideas they can do and um, I hope you come back on and share more more of projects that you're working on and tinkering on in the future. Anytime. Let me know. I mean, uh, you know, I'm I'm always down to share, you know, happy to share what I'm what I'm

[30:53] up to in the evenings. You're the best. All right, thanks, man. Bye.

---

About this transcript
Read from YouTube's own caption track and laid out by ViewRank AI (https://viewrankai.com).
ViewRank AI finds the videos already beating a creator's own average on Instagram, TikTok and YouTube Shorts, transcribes them from the audio itself in more than 60 languages, and turns what worked into new ideas and scripts.
Free transcript tools, no account needed: https://viewrankai.com/tools
How to read any video this way: https://viewrankai.com/llms.txt