# Making $$$ with OpenClaw

Channel: Greg Isenberg
Video: https://www.youtube.com/watch?v=i13XK-uUOLQ
Duration: 52 min
Language: English
Words: 9294
Transcript page: https://viewrankai.com/tools/youtube-transcript/i13XK-uUOLQ

---

[0:00] How can you make money from OpenClaw? Like how can you spin up these OpenClaw instances, these sub-agents, these digital employees that can go out and make you money while you sleep? Is it even possible? Well, in today's episode I brought on Nick and he shows a tactical tutorial for how to spin up multiple OpenClaw machines in a virtual [music] instance, how you can be automating tasks on Upwork [music] and these boring business automations, and how you can actually make money from OpenClaw. If this doesn't get your creative juices [music] flowing for the future of SaaS, how people are going to make money, and how to actually use

[0:38] OpenClaw [music] from not just a cute little use cases, but actually money-making uh opportunities, then I don't know what [music] will. I had such a good chat with Nick, it got my creative juices flowing. I think it will yours, too. And this is I think one of Nick's first podcast, so give him a like and comment to juice him up because he shared that

[1:00] sauce. [music] The starter by the podcast. It's sippin' time, baby. [music] I couldn't be more excited to have Nick on the pod. He's one of my go-to people when I have questions about OpenClaw. Nick, by the end of this episode, what are people going to learn? Yeah, people are going to learn that OpenClaw is more than just a personal assistant. You can actually deploy this into businesses, you could drive actual outcomes, generate revenue off of OpenClaw as an opportunity. Um and yeah, we're seeing it on X, like people who are deploying OpenClaw for um kind of executives or um individuals who are super busy. Uh they're making

[1:47] thousands of dollars, you know, setting OpenClaw up, getting it up and running for these people, and managing it for them. So, I think there's a huge opportunity here. And yeah, just excited to jump in. Cool. And before we get going, I need you to make a commitment to me and to the person listening or watching, which is I need you not to hold back any sauce. I don't want to know just about the opportunity. I want to know how are people doing it tactically. And by the end of this episode, what I want is for people to take away like I want people to know how they can actually

[2:18] make a dollar from this. And is that a commitment, Nick, that you are willing to make to us? Absolutely. Absolutely. I I'm not going to hold back anything. I I'm I've in fact, I think OpenClaw is is a is a tool that allows us to be able to do the things that we have always been able to make money from, like automation with AI, but do it even better. And I'm going to show you how to get it all set up so you can do that and the wedge to get going. So. Let's do it. Yeah. So, I guess jumping right in, as far as like

[2:51] getting set up with OpenClaw, you can see here, you know, this is Orgo. This is our startup. You don't have to use Orgo to get started with OpenClaw. Just full disclaimer, this is what I'm using. And what I'm going to do is I have a project here. Uh you can see I have a couple a couple projects and I have Greg, I set you up a project. I hope I hope you enjoy your, you know,

[3:12] five computers. Um and so you can imagine, Greg, you let's say you're a a business owner and you have a busy life, you know. Um you got all you have the podcast going on, you have all these businesses you're running, the agency, the Idea Browser, all this stuff. And and you need you need help automating some stuff. So, what I'm going to do is I'm going to come in, I'm scrapping, Nick. I'm going to come in and I'm going to help automate some things in your in your business, in your life, um you know, as a busy executive. And I'm going to get you set up with

[3:43] OpenClaw. So, when you open up uh computer here, I you can see I have it open. This is the the ClaudeBot um computer I made for you. If I actually just type in OpenClaw TUI, this will open up OpenClaw in the terminal, and you can see I I actually already started like, "Hey, I'm Greg Eisenberg." And it's all ready to get set up. And so, actually what I could do is, um, I could invite you to this project, and then you'd be able to do this as well. Like in your terminal, you'd be able to spin this up, and now you're talking to OpenClaw. So, um,

[4:16] super easy get set up. Once again, you don't have to use Orgo. You can use whatever you want. You can use I know, uh, Manas just dropped their, uh, their own version of like one-click deployment OpenClaw. Um, also Kimmy launched their version as well. X is down right now, so we can't actually pull it up on Twitter or anything, but uh, Kimmy launched their version. And so, uh, there's all these options as far as getting started. You could use a Mac Mini, whatever. So, the key here, Greg, with OpenClaw and actually creating money from it, is to have the wedge to know what is the specific use case in a person's business

[4:50] that we're going to automate like first. Because for When when you see OpenClaw on Twitter, it's very much a personal assistant. It's exciting. It's fun. But, all the demos that go viral, including me, I get it. I I I'm I'm I'm I'm guilty of this, too. All the All the demos that go viral are a little bit, you know, kind of toyish. They're a little flashy. But, the the real power is in finding the thing that actually, you know, drives business outcomes, saves time for a business. Finding that and and building the automation around that. So, I have something running here. This is my OpenClaw doing looking up products

[5:31] for, uh, a business that I, uh, deployed for This is a a promotional distributorship. And what this is doing is it's looking up products and actually downloading all the product information, and then like parsing all that information. There's all these reports it needs to download and then uploading that into a Zoho CRM. Um so it can essentially, you know, create a central source of truth for this client. So this is a perfect example here of like actually creating a agent you that OpenClaw deploys to be able to automate

[6:09] something end to end. Um so just just to recap are we all good so far? Yeah, so a few things I I just want to talk about. So one thing is when you showed, you know, that Orgo screen, you did you had like five machines running. So what's interesting is, you know, I've got my Mac mini going, you know, I've got one instance. So using something like this is cool um because you can have multiple instances going, right? And you can see them all in one screen and one view. So that's really cool. That that was sort

[6:42] of an aha moment for me. Yeah. Absolutely. Yeah, it's like everyone, you know, as far as where you deploy your your main OpenClaw. You can see here I like I starred the main one. Uh and so that's like you can have that wherever, but what people don't realize is OpenClaw can spawn sub agents. And I think this is going to be huge for people who start like right right now we're at the phase of having one

[7:09] OpenClaw. It's going to happen quickly. You're already seeing on it on Twitter memes about like, oh, what if you have a you know, 10 Mac minis or all the Mac Studios are being bought out. So this is happening faster. You're going to want 10 OpenClaws, you know, 100 OpenClaws. Right now you can have one OpenClaw and just have it spawn up to I think eight sub agents and each sub agent could have its own computer. And you can do this like this is why this is like kind of where Orgo shines is you can spin up multiple computers for, you know, each

[7:37] individual sub agent of your OpenClaw. And in this case here I had it looking on Upwork for actual things that we could automate with Open Claw. This is like a little hack here as far as like, well, I want to make money with Open Claw. Well, uh oh, I don't know any any business that I could reach out to that I could automate stuff for. A great place to start is Upwork because there's jobs on

[7:58] Upwork that are literally posted. They're They're asking you They're like, I want to pay 500, 1,000, 1,500, 3,000, 20,000 dollars for this AI workflow and you can I spun sub-agents and viral on Twitter. I spun sub-agents to go find all these jobs and then build out little demos for each of them and and we picked the best one and okay, let's let's apply for that proposal with that. So, that's a little tidbit there on on

[8:22] Upwork and all of that. So, which is which is kind of hilarious cuz I mean, Upwork, you know, is designed for human beings to complete work, right? It's not designed for machines, let alone multiple machines, to complete work. Um but I mean, as long as the the quality of work is good, um you know, customer's going to be

[8:43] happy, right? Yeah, and I think like it's good to you know, it's good to treat it as the as a starting point. Like, you know, if you can save time preparing a proposal for a job on Upwork, it's like, um what is that worth, you know? And if you could do just a 100x volume, uh what is that worth? So, there's a couple things on that of like the parallelization of work with Open Claw. So, there's like, could you have 10 Open Claws working on a given task and it breaks up that tasks into 10 sub-tasks? And so, each Open Claw does one of those sub-tasks. That's one way of having

[9:18] parallelization, but another way is to have 10 Open Claws working on the same task, uh just 10 different instances of it. And that was kind of like what I was doing here is, you know, four different instances of the one Open Claw that you know, or four different Open Claws doing the same thing of looking up different uh jobs on Upwork that they can apply to. So, that's kind of an interesting topic there. Um But, yeah. So, like as far as Open Claw goes, it's it's it's uh a huge opportunity. I just want to like throw

[9:48] this in here. Andreessen Horowitz talks about computer use agents. I view Open Claw as a computer use agent. You know, you're giving an agent a computer, and it's able to do it's able to use that computer. It's like it's a computer use agent, but that's half the story. The other half of the story is for it to be able to like click around, actually operate a graphical user interface on like legacy softwares and systems. And so, um you can imagine like you know, in here this this automation I built, this is navigating a legacy platform for this client that doesn't have any clean APIs, and it's able to

[10:23] click in, download reports, and actually, you know, be the universal API uh to be able to solve problems that you couldn't previously solve without computer use agents. So, I think there's a huge opportunity here. And Andreessen Horowitz, they talk about it, and they say, "We believe that the properly uh to properly verticalize computer use agents and assist companies in adopting it will be a major area of exploration for

[10:45] startups." And this [snorts] is like this to me this screams Open Claw. You know, can you create a vertical use case for Open Claw for a business and actually assist that company in adopting it? I think that's that's the huge opportunity here. Um So, going back to this like workspace we have set up for you. Um you know, with with with all the people setting up Open Claw, you could set it up as easy as you know, I invite Greg

[11:13] to this workspace. I create him a new computer. We can just do it now. Uh Open Claw 2. I select how much RAM. Let's do Let's do 8 gigs. Launch that. [snorts] Open that up. And then all we need now to get you set up is to get the um let me get the the curl command for Open Claw. I copied that from their website. And then, as this computer loads, we'll be able to then literally just

[11:46] paste it into the terminal. And once I see the interface pop up, boom, okay. So, now I'm going to hit enter. And now we're off to the races installing Open Claw. So, like it's as easy as that. And I think there's this is this in and of itself is like a workspace where you can invite people and get them set up with Open Claw or Clawd Code. I think this is like a huge a huge opportunity as well of like just there are executives right now that are like reaching out to me

[12:17] like law firms, insurance companies. They're like, "Can you Can I just like pay you to teach me how to use this stuff?" So, like that's its own whole thing as well as far as like if you're savvy enough to even know how to install Open Claw and get it set up in the first

[12:30] place. Um [snorts] I just see there's a huge opportunity around like just helping executives, businesses adopt it. Um So, yeah, you can see that it's as easy as this to get set up. And then, as far as like what specific things can we can we automate with Open Claw? There's a couple it it it it takes a little bit of a design thinking approach. So, when you go into a business, let's say you find a project on Upwork and you want to you want to automate that with Open Claw. Or let's say you go into a business and you're talking to the executive, the decision maker, and it's

[13:05] clear that they have things that need to be automated. Well, as far as like design thinking goes, like you need to have uh a clear way of like first mapping like all the different possibilities. You can see here this is something I did in the past of like there's all these different things that you can automate and you want to map them all two very simple metrics. What is the value that we can create by automating this thing? And what's the relative effort, cost, and time? And so we ultimately want to start with, okay, we want to automate things with OpenClaw that are high value and

[13:36] low effort, cost, and time. And that's like your your your low-hanging fruit. Um and so you start there. And so like for for this client, this was like that this was that. This was like, okay, we're looking at products on this website. We're downloading them. We're parsing all the information. Uh that's the low-hanging fruit. So, start with the design thinking approach of like, okay,

[14:00] simplest, fastest to deploy. And then you need to map out like the systems design around how like how is this thing going to be automated, all right? So for this for this client, she's like, okay, I send an email to a to a client of hers, right? She sends an email to a client and she has a a presentation link with all these products. Okay? And and all those products, she needs to look at all of them up and get all the information on them and then upload them into Zoho. So then your next step after identifying the opportunity is to literally like map this out. I use Figma. You can use

[14:35] whatever. But map out the the actual workflow process of like, okay, step one, step two, step three. What is this automation going to look like tip to tail so that we can do the whole thing. Um because with OpenClaw and Computer Eyes, now now is now you can do that. You can do you could do things from tip to tail. It's not like um you know, it used to be where you'd have to like go into a website and click a button and then it'd be able to do some 50% of the whole thing, but then you'd have to copy that and paste that somewhere else and

[15:03] do it on your own. Like we can do it tip to tail. Um So, quick recap. Install OpenClaw into a computer. Identify the next Identify the the low-hanging fruit opportunities, the highest value opportunities, and And begin to map out what that even looks like to begin with. Couldn't you you know sort of this is meta but couldn't you use open claw to actually do some of the prioritization on the automations and actually I mean you as a human being did the Figma but couldn't you actually just use the open claw or cloud code or something like that to to help you with that. So for example

[15:44] like if you go back to the the Figma. Mhm. Like you could walk into a business and basically say hey I want to figure out what we can automate here and you do customer interviews with different people on the team. You record those customer interviews. You get the transcripts. You upload the transcripts and then you say hey based on that then you're like you can actually say you

[16:12] know you give this as a reference image. Basically say like hey I want to figure out which which automation opportunities have the highest amount of value lowest amount of effort cost and time. Give me the top three and then create you know Figma and I think there's like a Figma MCP even uh that you can use and you can say like hey like can you map this thing out

[16:35] based on these customer transcripts. Does that make Does that make sense or am I Oh absolutely. Yeah. No that's that's that's the way to do it. Like I whenever I do any kind of call with a client or cut like potential customer oh my gosh Gemini for for Google Meet is amazing. You just have it take take all the notes and then actually that's that's how I even got cuz I don't know about I don't know about you Greg but sometimes when you're in these calls you kind of you know this this this industry you know you're in a new industry you're helping this customer you don't

[17:06] understand the domain expertise the the lingo and so you got to go back and and like okay like what what was it that they said and so have the granola or Gemini notes or whatever and then literally ask it to like, okay, what's the step-by-step workflow, and then map it out. It just helps me to map it out

[17:23] visually. Uh but you could literally ask it, yeah, like you said, um based on this transcript, what does the the automation workflow look like, you know, step-by-step. And if you don't want to use, you know, Figma, you can also even say uh you know, do output in Mermaid uh code, and then you can use that Mermaid code and insert that into an Excalidraw or Teal Draw or something like that. So, uh a little pro tip there. Nice. Nice. Yeah, yeah. And the yeah, and the Figma MCP is pretty cool,

[17:55] too, yeah. Definitely check that out. So, yeah, so then once you figure out what the workflow is, right? Um this is where like you have to actually um be able to know, okay, how much how much can I really ask like, how much can I just say like to open claw right now, hey, like build this like, hey, build this thing, and you just describe the workflow versus genuinely using something like Claude code to build out like what that workflow would look like with, you know, Python APIs, a genuine automation pipeline and process that your open claw can actually just trigger upon um whenever it's like contextually

[18:39] relevant. So, for instance, this this whole pipeline here of like going to these websites, looking at this product information, downloading the information, parsing it, uploading it to Zoho, the trigger of all of that is uh you know, the open claw being CC'd in an email, and it seeing that email it has a link that is relevant for this type of workflow to be triggered. So, that that is like the thing that's like the listening event that open claw can do with like a cron job that it sets up to just like, okay, listen for this trigger, and then once that trigger starts, it can then activate the whole Python script

[19:16] workflow automation, everything that you would need downstream of that. So, you're not relying too much on Open Claw's like um abilities in and of itself. You're more of so creating specialized AI workers under each underneath the Open Claw that it can call individually, if that makes sense. You know, you talked earlier about sub agents. I think a lot of people are confused about what is a sub agent versus a task and stuff like that. Can you just clearly explain that? Yeah. Um so, sub sub agents are um I I I there's a couple ways to view them, right? So, like in the context of cuz there the and the reason I say

[19:56] there's a couple ways to view them is cuz there's a couple ways of using them. So, in the context of like Open Claw, you can ask it to spin up five research sub agents that all go and research some given task. And and like and you know, like I said earlier, you could you could have it parallelize that task across, you know, splitting it up across each sub agent or having each sub agent actually go and do the same task, you

[20:18] know, across five different instances. But, the next thing around sub agents is that you can actually, like you said, um maybe think of them in terms of skills. So, if you're familiar with Anthropic skills, um you can have like these specialized instructions and rules along with actual code that you can provide to your agent for it to be able to go and do a given task. And this is really nice um because it you know, it it gives you a very more purp a very more powerful general purpose agent that can do many of your specific nuanced tasks um across various domains. But, the thing is it's like

[21:00] I want my general agent to be freed up and uh to more so just be the orchestrator. And what if the the general agent, this one, right? The the one I have starred here, can just call a sub agent like worker number four here to do a given skill that you have created. So, if your skill is that it goes on Twitter and finds the most viral ideas and it bookmarks them, um rather than having your main agent do that and now you can't talk to your main agent for the next 20 minutes cuz it's working on that, can it call that skill into a sub agent and have the sub agent

[21:35] do that? That, I think, is where things get really interesting and and in terms of the context of like deploying open claw for businesses, I would think of everything that you have in terms of an AI automation opportunity around workflows, skills, tasks, etc., I would actually just create that as its own like specific sub agent with its own skill that that your open claw could

[21:59] then call. If that Does that make sense? It does. It does. Um it's it's bit you know, I think the the basic idea is like you know, in layman's terms, it's as soon as you have your um your open claw instance, you know, do something, they're busy, you know? It's like they got a they've got a mug of hot coffee and so you and your your job is you want to leverage this as much as possible. So, you don't want, you know, your agent to hold a a hot coffee. So, if if you ask it to do to move this desk into this area, you know, it it says, "No, I'm holding a

[22:42] cup of hot coffee. I can't do that." So, what sub agents do is it basically creates leverage for your open claw. And it basically says like, "Okay, I'm you're going to create a set of sub agents who are going to be good at XYZ thing and that way it frees up your your main agent to to, you know, as you say, orchestrate, to basically be the manager of the sub agents. Uh, and you know, what that could mean is, uh, like looking at, um, quality of work. It could mean, uh, checking for certain things and

[23:18] stuff like that. Exactly. Exactly. I think that's going to be huge, you know, when when you start working with these businesses and and and customers who want things to be automated, once you show them what's possible, their eyes light up, they get all these ideas themselves. These are high agency people, you know, they they come up with creative ideas that they want to start implementing. And and and then what you realize is there's just a a huge a huge list of things that can be automated and they're excited about that. And and so actually like the the ability to, okay, first solve a vertical specific workflow

[23:53] for for a customer, and then that opening up their mind and then they then being like, "Oh, I wonder if I could could I text this thing and it does this?" This is kind of where like the whole open claw moment, um, is really powerful. It's like it's it's the it's the it's the assistant-like capability. It's the, you know, I have it I have it here. It's like, what a lot of people might get confused about why is it that open claw so special? It's it's the ability that that has its own computer, it's running 24/7, you can text it, and you can schedule tasks, and really

[24:27] if if we just removed open claw from this part here, and you just called this a really good employee, it it would just make sense. You'd be like, "Oh, works 24/7, can code, can schedule tasks, I can text it, and they have their own computer." Um, so I think that's like kind of why open

[24:45] claw is exciting for a lot of people. And if it's not, you know, if if some people think it's it's overhyped, you have to kind of look at the whole picture, I think, and and then you're able to really gauge it. So, I I'm certainly bought in on this on this idea that you know, it could potentially it could be be a really good employee. I think there's also cases where people aren't setting up their open claw in the right way where it ends up being a bad employee. Um, and I think you know, that's sort of like the the issue with that is, you know,

[25:16] sometimes you have a bad employee because the manager, the coach essentially is is not doing good job at giving the right context at the right time. So, I think you know, do you have any tips and tricks around um, besides spinning up sub-agents, like how how could people listening to this, if they want to go after this opportunity of um, essentially verticalize, you know, open claws, uh, and automating some of these flows, how could people actually, you know, take their open claw from a bad

[25:49] employee to a good employee? Yeah, I think it comes down to let's maybe we should walk through. So, I know you have I was actually looking at this. So, idea browser. So, for everyone, if you don't know, Greg has this amazing product, idea browser. And I love this trend to this idea today, TikTok trend tool that catches viral waves before they peak. So, I was actually looking at this this morning. I was like, wow, this is actually something that you can maybe turn into a skill for an open claw to

[26:21] create a specialized skill around this. So, let's just do a live. Let's see. I I genuinely don't know how far can we get? Can we build this out now? Let's see if I copy all of that. And now I'm here in the open claw that that we set up for you. And you can see it just got set up. It's it I just told it, "Hey, I'm Greg

[26:39] Eisenberg." So, we're getting started. That's it. And let's just say I want to build a um a a specialized skill to be able to do the following. And I'm just going to paste that entire um idea browser idea. And I'm going to ask it as far as like creating these automations, creating workflows, or doing anything with OpenClaw, my number one tip is always ask it to ask you questions. So, what do you need from me

[27:12] um to be able to build this out? Um let's create a plan. And so, a lot of people need to remember OpenClaw is like a uh almost a little bit of a wrapper around like Claude code in a way. Um so, let's see. Okay, cool. This is a big vision, Greg. I like it. Let's break down um

[27:34] a realistic build as an OpenClaw skill. So, now it's saying, "Okay, I need data access. I need the scope. I need the niche focus um that'll shape what we build a lean skill." So, the first thing that we can maybe do is here in like Orgo, we have this playground mode. And you can ask the playground agent here to do things in this computer in this this computer environment. Um so, one thing I might test first is like can we get can we get this agent to even just spin up TikTok and just scroll TikTok and identify what is on the For You page of TikTok. So,

[28:16] let's like maybe start there. Does that sound good? Yeah, absolutely. Let's do that. Open Firefox. Go to TikTok. Scroll I'm going to say scroll TikTok looking for [snorts] what the most common videos are on the For You page. Give me a summary. So, let's see how it's able to do this. So, this is using our our playground

[28:45] mode. And boom, opens up Firefox. It's going to go to TikTok. And for those listening, I'm just going to talk through a little bit about what this agent in our our playground is doing. It's It's visually interacting with the screen. It's, you know, clicking into Firefox. It's opening up the browser. Now it's typing in

[29:09] tiktok.com. It's going there. And let's see. This is always such a magical experience, just watching a computer navigate the web like a human being. It's amazing. You know, this is There it goes. Uh it's on It's on the It's on the homepage. And now it's going to It's going to actually scroll TikTok. It's going to probably take a screenshot of this, get the context of based off that screenshot of what the video's about. You can even see it It has hashtags movie, hashtag for you page. So it's going to be able to infer a lot of things. Boom, it

[29:51] scrolls. It scrolls. It gets a pop-up. It's going to close out the pop-up. Um but on your point, Greg, Dario Amodei, the CEO of Anthropic, he just had a podcast with Dwarkesh. And it came out a couple days ago. And you know what's really interesting what he said in that in that in that podcast. He said He said this idea of his around this data center full of brilliant you know, scientists and Nobel Prize winners, essentially his

[30:24] concept of what AGI will be like. He says the constraint to getting there is computer use agents. The ability to have an AI that can operate a computer like you and I can, but better, you know, interact with the visual interface, also be able to do things under the hood, kind of like Claude code.

[30:42] Um this is the constraint, he said. And I mean, it makes perfect sense. If if it can do anything that you and I can do on a computer, that seems like it can go pretty far. Um Open Claude is like a Chat GPT moment, I think, for for this kind of idea of computer use. And and and as far as like building these computer use agents out, you can see this is this is clearly working, so we know this is possible. Um you can build A lot of people might get confused

[31:12] with Orgo when they come to our site. They see computers for agents. They're like, "What does that mean?" Well, I think they get it now. It's like, "Okay, you want your Claude bot to have its own computer." But also, we provide, and I'll show this, we provide the dot in our docs, like where actually provide the programmatic APIs so that you can create custom computer use agents that um do a given task very well. So, you can bring any model. You can get Kimmy 2.5 is like the super cheap um you know, Chinese model. It's very good at

[31:43] computer use. And you can give it the ability to click, drag, scroll, type in the keyboard, spin up a computer. Um and you can create specialized, really fast performance, low-cost computer use agents um using our docs. And I just say that to say like as far as, you know, this this thing that we're doing here, creating a skill around scrolling TikTok, um I think that's how we can we can actually give it a shot as

[32:09] let's just We see this is working now. Let me just grab the Orgo docs and let's start building this skill out. If you didn't see here, I'm at the Orgo docs. I click this thing called LLMS full.txt. This is like all the instructions for the LLM to be able to build on top of Orgo. And what I'm going to do is I'm going to wait for I I probably I'm going to wait for this to finish this its task, and then I'll be able to tell it um But [snorts] while this goes Greg, you have any thoughts? Um well it just you know sort of a thing I was thinking

[32:44] about is it sounds like when whenever you're trying to you know do a new automation, you start by thinking about what is a lightweight skill that I should create. Is that correct? Right. Exactly. What's the MVP? Yeah. So you start with like a lightweight skill. Um you test it and then from there you're probably like hey here's what went wrong, here's what could be better,

[33:11] that sort of thing. Right. Exactly. Just fine-tuning, you know, debug like I think the design thinking process around all of this is super important of like okay if I want to build a car maybe the first thing I do isn't to build the frame of the car or you know, to build um you know, the whole body of the car. That's not the first thing. The first thing I should do if I want to build a car, well why do I want to build a car? Well I want to build a car to go to from point A to point B. Oh okay. So really maybe I should start by building

[33:46] a skateboard. How can we accomplish the task to get the get the dream out the dream outcome and um and sometimes that means like starting with something that's completely different than the end state. Um so this is done here. I think it interrupted itself. Probably a context thing. But now we can actually what we can do this is all live so we're you're you're seeing this in real time. You can [snorts] literally there's a couple ways

[34:17] to go about this. You can actually install Claude code into this computer and have it build out uh the automation in here or we can just ask this agent to do it for us. So let's see um I want to build a computer use agent that does this exact thing. Uh, but more programmatically

[34:41] using the Orgo API docs. And I paste that here. What do we need to get started? And we send that off. All right, here we go. So, we need an Orgo API key. Here's the architecture of what we'll build. Okay, this looks good. Um, Orgo key, [clears throat] Anthropic key, it has all the code here.

[35:06] Cool. Um, you're looking at a TikTok video. Extract the username, video description, the category, the appropriate like count. Boom, boom, boom. Okay, cool. So, [snorts] I have all these things already and don't worry, I'm going to delete these keys, so I'm not worried about leaking or anything. I'm going to copy my Orgo API key. I'm going to paste it in there. And I'm going to say

[35:32] Orgo API key. I also have my Anthropic key. Let me grab that. I'm going to paste that here. Can we build this out? And so now, we're going to have our our playground mode build out this computer use agent to be able to go do this thing that we just tested out. We know it works. We know we can do it. Let's turn it into something that could be more programmatic, kind of like a skill, and let's give it to Claude bot, so it

[35:56] always has access to it. The dream. The dream. It's literally any idea you have, you can just build it. And that's sort of the arbitrage opportunity, right? Especially like in our world, of course, like we're so used to this now, even though it's only been like 2 months. Uh, but, you know, the opportunity is the vast majority of people on this planet and businesses would love to have better automation and would love to you know, have computer use agents working for them, aka really good

[36:39] employees working for them. Um but they don't know how. And so I think that which is which is cool that you're like you're showing us like some of the best practices on on how to do it. Exactly and and I think this is also like I can I can imagine, you know, the the whole audience of this podcast, we're all pretty tech savvy. We know how to do things like vibe code and and and you know, play around with Claude code and be able to do these things and we take it for granted in terms of what that

[37:08] value is worth. Um as far as like open claw and the opportunity around that, I mean, open claw started going viral on Twitter around two to three weeks ago. Only now is it starting and I'm starting to see it's starting to go viral on Tik Tok a little more mainstream. So, um yeah, I I just mean, you know, people are catching on and a lot of people still need help with getting, you know, up and running on this type of stuff and what you might think is oh I mean I have a basic understanding of open claw and and Claude bot and Claude code. Uh and you might under under write

[37:45] that. A lot of people find that valuable so um being able to help businesses adopt it or just people in general, I think it's super good opportunity. Yeah, I think my only advice for people would be to fo- focus like don't be everything to everyone. Like don't don't help any every business, help real estate agents for example or like pick a vertical that maybe you have some unfair advantage for some particular reason and that unfair advantage doesn't necessarily mean you have 20 years of experience. It might mean just that, you know, you want to build something for uh real estate agents cuz your mom was a real

[38:25] uh real estate agent. So, you you you know you know the customer, right? Um so, I think that's that's the way to do that to do this. Absolutely. Yeah, it's it's um whatever you know, that's your advantage. And I mean, I guess as far as like some maybe I this doesn't apply to everyone. Obviously, if you're in this industry, then go for it. But like, you know, probably things to avoid, things that have have a lot of like red tape, like health care, finance, you know, I recommend maybe starting something Yeah, like you said, um you know, you could do even manufacturing or or uh there's a lot of

[39:04] distributorships out there who's you know, they distribute uh merchandise. Um just like the the demo I was showing earlier of that computer use agent working. Um so, yeah. I I think as far as, you know, doing doing what you know, and and starting there, and then the market will tell you. You know, the market will pull you into specific verticals. You'll start seeing ways that as you build these specific This is a great point. As you build it out these specific workflows around these verticals of like uh let's say you do, you know, let's say you do the manufacturing thing. And you

[39:36] do manufacturing for doors. Um over time, you're going to have a workflow for almost like every kind of thing you could imagine in that industry. And if you have the agents all built out, can you imagine you have a workspace and you invite uh you know, some some new company into this workspace that uh for for automations, for manufacturing, for doors, like luxury doors. And you invite them and they have all these AI employees in the workspace in Orgo set up, ready to go. You just see them all here, and they're all ready to go. It's like you feel like you just hired not a person, but a team. Um

[40:15] I think that's that's that's a very near In fact, I don't think there's anything stopping us from having that right now. It's all about just, you know, who's going to go out there and and put in the work to actually do that. Uh and if you do, I think it's I mean, it's it's

[40:29] pretty clear. Yeah, I mean, and that's that's why I truly believe that, you know, agents are the new SaaS. Like, you know what I mean? So, yes, I agree with the like the vision you painted. I think that, you know, in the past, you know, we created software that we would sell to these businesses, and then they would have people actually, you know, press the buttons, touch the knobs to to make it useful. Now, you don't you're not going to create software and then invite them to the

[41:00] software. You're going to create agents, and you're going to invite them to the agents, and then the agents are going to do work that creates value for these companies. So, that's the mindset shift, and you know, it's it's only recently actually that people have been, you know, I think over the last like 2 weeks, I would say, 2 3 weeks that people have been like on X talking about this. Um

[41:29] how agents are the new SaaS. But, I I do think that, um like over the you're going to see over the next 2 to 3 months like some really big winners. Um and you're going to start to see it work. So, I'm excited for people listening because I think that um this is the a type of audience that

[41:47] will act on some of this stuff. And it'll be interesting to see what what happens. Yeah. Yeah, I I I think it was it was it Sam Altman that just said, you know, every company is turning into an API company. Yeah. And that's interesting cuz interfaces are, in a sense, dying in that way of like, you know, you won't interact like the ultimate interface, for whatever reason,

[42:11] seems to be chat and text message. And it's happened twice now of like Okay, the chat GPT moment was a chat box and now it's the open claw moment which is like a text message or telegram. So it's like okay, chat has happened twice. Um and that just means okay, so we just want to wait for our agents to be able to use all the tools that we use and we don't really care about how it does it. It just needs to be able to do it and and it runs in the in the background. Um

[42:40] and does it under the hood. Um So here, okay, I started uh I built you can see that this agent in the playground built out the TikTok agents.py inside the computer. So now I asked open claw, "Hey, um I built a TikTok agent.py in your desktop. Can you take a look?" And it's re It says, "Okay, I've read

[43:03] it. Here's what I see. Uh there's a skeleton for, you know, using Orgo um plus uh Anthropic's API. Go ahead, Greg. No, you keep going. And and it was and it was um you know, all all the actual TikTok logic trend detection, all this stuff. Um it's like okay, maybe we should build that

[43:25] out. And it's like oh you you got the API keys hardcoded etc. etc. So let's just say let's use this script, build on top of it or whatever you need to do. And let's spin up a Orgo VM inside of the Greg Eisenberg workspace to accomplish this um automation with TikTok. Let's demo it just working. We can spawn a uh sub agent and VM in this workspace. And let me just give

[44:07] it a API key just in case it needs that. What really blows my mind about this whole thing is that you know, I was going to say we were we're building a business in a very short amount of time, but it's really like we're building an asset. Like the amount of assets that people are going to be be building um using tools like this is is going to be

[44:33] crazy. Right? Yeah. It's insane. Honestly, it comes down to like I honestly like it comes down to taste now, good ideas. Um [laughter] cuz like if you have a good idea, you could just just build it. And then yeah, there's there's going to be like, "Oh my goodness, what's going to happen with all of these assets, like you said, that people are just going to build and build and build?" There's going to be so many assets. I think is this what is this what we mean when we talk about the um the abundance that AI will bring, you

[45:06] know, of solving all these problems. Yeah. Well, I think what ends up happening is uh you know, unfortunately, there are going to be more and more layoffs as AI helps with productivity. At the same time, I think there's going to be a renaissance, the golden age of entrepreneurship, and people creating assets, products like this, one-person businesses, and uh

[45:36] that's how I see it playing out. Yeah. Even even it maybe may we don't know officially, but maybe it's already happened with Peter Steinberger, the creator of Open Claw. You know, he he just um officially announced he's joining OpenAI. Like I think it was just him who built Open Claw. How much did he get, you know, acquired for? I think it was a

[45:58] lot. Um so that's that's I mean, that's that's cool. I think it this is the best time to be a builder/tinkerer to get creative. Um I I'm excited to see what people build with open claw and computer use agents in general of like it's just there's so many things, you know, whether it's a a super fast chess computer use agent or if it's something that's genuinely driving an outcome in your business. Like I just think there's so many things that can be built. Um playing around with these tools, getting familiar,

[46:32] learning how to how to leverage them. Yes, AI is going to be replacing a lot of jobs. But also, it's going to enable a lot of people to do things, you know, that they've never been able to build before and now they can do it. So, um yeah, I'm I'm just Oh, here it is. Okay, so you can see hm it spun up this

[46:51] computer, TikTok Trend Hunter. And my screen's just refreshing. Uh let me just click into it. And and I could just tab back and forth a little bit to see okay, VM is up, it's opening Firefox. Let me wait for the agent loop to start. Here we go. So, it's spun up its own computer. This is insane, Greg. It spun up its own

[47:13] computer. Open claw did. And now it's it's using its own Python script that it just made just now. We took it from my Idea browser. And now it's going to go do this thing. [laughter] Um that we just built out. I don't know how long this took. Last like 10 minutes. Kind of just, you know, in between we're

[47:31] talking, having our coffee. It's like [laughter] this is insane. I don't know. You kind of it makes me it gets me giddy. It's like [laughter and gasps] Uh and it's going to figure this out. It's like, you know, it's going to debug like okay, what's going on? Why why am I on the ads.tiktok.com? Let me reroute myself. I'm sure it's going to figure all this

[47:52] out. Um but it's just cooking, you know. Crazy, dude. Crazy. Anything else you want to cover before we head out? Yeah, I think um as far as other things to cover, I mean I I just want people to start thinking about these tools, you know, yes, they're they're once again, they're great personal assistants, but if you start thinking of Open Claw as an N8N, or [clears throat] you start thinking of it as a um you know, like a Lindy AI of like, you know, people there are real businesses right now. Like we can go to Upwork right now and find jobs that are being posted around, you know, things like this this

[48:38] is what you do. You just go to Upwork. Upwork's great cuz you get to see what the market's asking for. And you just type in uh robotic process automation, you know, this old outdated way of of programmatically automating tasks that it's like clunky and it it breaks and it's not intelligent. If the button isn't in the exact UI space that you delegated it to, it won't work. And you go here like posted yesterday, Android RPA automation, posted yesterday,

[49:09] automation pipeline for client upload. You go here, you could just do let's let's find $500, $1,000, $5,000. Let's look at all these projects. Okay, this one, boom, right here. Um $1,000 budget. I'm looking for experienced automation engineer to build desktop automation computer use uh for my software business. We sell a specialized dynamic PDF. You take all this context, give it to Open Claw, give it to Claude Code. How much of it can you build out as a demo based off of this context

[49:42] alone? Send a proposal. You have your first customer right here, $1,000. Um get get get some case studies, leverage that. Maybe go deeper into this industry that this person's in, start building out specialized workflows using Claude bot Open Claude for all the different vertical use cases in that, create a workspace of it. Um I think that's where we're at right now and I'm excited by this. So, um yeah, I I guess we'll just see where it goes and yeah, okay, this needs a little debugging, as to be expected. We spent 10 minutes on it, but I think you get the gist. Um and yeah, I'm excited to

[50:20] see what everyone builds. From your lips to God's ears, baby. I I am I'm I'm I I think your approach makes complete sense. Um it's the exact approach I would use, totally recommend it. People get your hands dirty, get tinkering. I'm excited for what you build. Um Nick doesn't do a lot of podcasts. Um I think I was only able to find him do one live stream before. So, show him some love in the comment section. Uh like the video, um show him some love and um

[50:55] Nick, I hope you come back on. Uh share more use cases. I'm going to be sharing more use cases that I'm using that my you know, I haven't done uh too many publicly, but I'm going to be sharing more of my use cases both on virtual machines and on my own Mac Mini uh for my Open Claude stuff. So, get ready for that, folks. And uh Nick, wait, is there anything Is there Is there anything else before before we go that you want to that you want to

[51:23] share? I just want to share with you, Greg. You don't know this, but I've been a long-time follower. This is my YouTube Rewind 2025 top 0.5%. So, if you're watching this and you love Greg's podcast, you love his videos, you get building on top of it, you put cool stuff out there, you know, you join your you join your top YouTube channel on

[51:48] your on your we your rewind of the year. I love it. I love it. Nick, you're a legend. You got to come back on. You're one of us. You're one of us. So, I appreciate I appreciate that. Thank you, Greg. Thank you for having me.

---

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