The Startup Ideas Podcast - The $1M+ Solo AI Agent Business (Full Course)

Episode Date: May 12, 2026

Nick agreed to personally set up your Orgo in a 15 min call: https://startup-ideas-pod.link/orgo_ai I sit down with Nick from Orgo to break down exactly how to run a one-person AI agent business that can realistically clear a few million dollars a year. Nick walks through the offer, the verticals worth chasing, the full software stack, and the live setup of an agent that manages other agents. We focus on tactics over theory, with specific tools, pricing, and the playbook for landing customers as a solopreneur. By the end, anyone with solid AI fluency will have a clear path from offer design to fulfillment. Timestamps 00:00 – Intro 02:54 – Designing the AI Agent Business Offer 06:38– Selling an AI Employee, Not an Agent 07:26 – Industries to Target (and Two to Avoid) 14:54 – Content Is Overpowered and How to Get Customers 17:51 – The Customer-Facing Tool Stack 20:49 – Building Agents Stack 25:51 – Model Picks: GPT 5.5, GLM 5.1, Kimmy, Opus 4.7 27:08 – Nick’s Stack 28:14 – Why Obsidian Is the Second Brain Layer 30:22 – Live Walkthrough: Spinning Up a Cloud Computer in Orgo 33:53 – Cloud Computers vs. Mac Minis 38:37 – Building Agents and Structuring Workspaces for Customers 43:56 – Watchdogs, Observability, and Reliability 45:28 – Closing Thoughts on the Solopreneur Era Key Points Sell unlimited agents, unlimited usage, and unlimited support to remove friction; most customers actually use one to three agents. Avoid healthcare and finance to start; focus on legacy verticals like marketing, law, insurance, manufacturing, wholesale, and real estate. OpenClaw agents go for around 5K a month; Hermes agents can go for 10K a month. The full stack: Granola, Trello, Loom, Superhuman, Asana, Codex, Hermes, Orgo, Composio, Agent Mail, and Obsidian. GPT 5.5 is the recommended default model for tool calling; GLM 5.1 and Kimmy work for lighter tasks; Opus 4.7 fits long-horizon coding. Use agents to set up other agents — pair Cloud Code or Codex with MCPs like Perplexity, Context7, and X MCP for live docs. The #1 tool to find startup ideas/trends - https://www.ideabrowser.com LCA helps Fortune 500s and fast-growing startups build their future - from Warner Music to Fortnite to Dropbox. We turn 'what if' into reality with AI, apps, and next-gen products https://latecheckout.agency/ The Vibe Marketer - Resources for people into vibe marketing/marketing with AI: https://www.thevibemarketer.com/ FIND ME ON SOCIAL X/Twitter: https://twitter.com/gregisenberg Instagram: https://instagram.com/gregisenberg/ LinkedIn: https://www.linkedin.com/in/gisenberg/ FIND NICK ON SOCIAL Youtube: https://www.youtube.com/@nickvasiles Instagram: https://www.instagram.com/nickvasilescu/ Personal Website: https://www.nickvasilescu.com/

People are charging $5,000 a month per customer to build and manage agents for them. This is a startup idea I wish more people would do. The customer doesn't touch tokens or models or any infrastructure. They just get a digital employee that knows their business and it gets better every single week. In this episode, Nick from Orgo breaks down exactly how to build this business. The tools, the stacks, how to onboard a customer in 30 days, and how to actually sell to busy executives, agencies, and law firms. We also share the full implementation playbook, Hermes, Clod Code, memory layers, skills, all of it.

This type of episode isn't shared anywhere on the internet. This is the alpha that people keep for themselves. I'm giving it to you for free. Enjoy the episode, and I can't wait to see what you built. I couldn't be more excited to have Nick from Orgo back on the pod. Nick, by the end of this episode, what are people going to get out of it? Greg, everyone's going to learn not only how to run a solopreneur agent business, but every gap, everything that they're going to do wrong from the beginning.

I'm going to save them all the time from having to learn from those mistakes that I made along the way. And at the end of this video, you're going to know what offer to bring to the market, how to get customers, how to fulfill, what's the stack for the agents that you're going to build out. And yeah, I'm excited to just die right in. So, Nick, this isn't going to just be like a pie in the sky. I want a billion dollar idea here.

This is how you can take advantage of AI agents to build a business that maybe does a few million dollars a year, but not just the idea, right? You're going to actually share all the tactics from A to Z so that by. the end of this episode, someone could obviously like and comment and subscribe, but, you know, go and start one of these businesses, right? Exactly. And like, I think the big thing is for everyone who's watching the pod, you're probably already affluent with AI and you don't give yourself enough credit.

And the amazing thing is like 99% of the world has, you know, there's like many people are so behind on AI and you may not realize. how valuable your skill set is. Like, oh, if you can set up Claude Code, if you can set up Hermes agent, if you can set up OpenClaught, that's a very valuable skill that a lot of businesses don't have time for,

and you can monetize that. All right. I'm intrigued. Let's go. All right. So let me start by, I'll share my screen. Okay, so let's just dive right in.

Let's go into the offer. So when you're starting a one-person agent business, you need to remove all the friction for your customers. They don't want to think about tokens. They don't want to think about computer infrastructure, security, you know, breaking it when, you know, fixing it when it breaks. They just want it to work. And so the biggest thing is you need to create abundance in your offer.

And what I have found in my own personal success with this is offering unlimited agents, unlimited usage, unlimited monitoring, support, security, ongoing changes, etc. And the key here is you might flinch because you're like, well, how is that even feasibly possible? Well, the way to do this is to realize the point, it's not that the customer is going to actually need unlimited agents. They're not going to need unlimited tokens.

But they might think they do. In reality, they might think they need five agents, 10 agents, 100 agents, when really one, one, two, maybe three agents goes such a far away and you can get a lot of juice for squeeze out of just properly taking the time to set one or two of these up and that's where you're, you know,

that's how you're going to essentially control your costs, you're not spending too much money on tokens and you're going to charge 5K months for this and this is the offer that I've been running and it's been working really well. And yeah, like customers don't really need as many agents as they might think they need

and you're just going to show them as quickly as possible the magic behind it. So this is the offer that I've been running off the rip. And I guess I'll read a little bit. I wrote some of this stuff down. The big thing here is the point is not that the customer needs infinite agents. They don't need infinite tokens or infinite computers. Most customers, they just need one, maybe two, maybe three. They just need a seamless experience.

Like that is what you as, you know, as your big. business as the solopreneur agent's agency, you're going to come in and you're just going to remove all the friction. And the minute that things start to break, like the business owners that you're going to be selling to, they're going to become so reliant, so dependent on these agents that if something does start to break, it is very painful for them. And so in this video, I want to make sure that I help you make it very clear on how to prevent those small gaps so that when something breaks, you have something in a way to fix it before they even realize it. And, yeah, if a customer, if they want constant improvements, how do you keep up?

How do you fulfill? We're going to be going through all of that in this video. Cool. Yeah, so, I mean, my big takeaway from this is you're selling an AI employee, you're not selling an AI agent. People need less agents than they actually think that they need. and you want to think about unlimited, you know, you don't want to use the word tokens basically at all. And you shouldn't really word too much about usage.

Exactly, exactly. Because for them, it just, it ruins the magic. The minute you say like, oh, like you're going to be paying for X amount of credits and then they're always going to be wondering, like, oh, how many credits do I have left? And you're going to be like, oh, and then it's usage space afterwards. It's like the more clarity, the more simplicity you can create in the offer that it's just straightforward and easy, the faster time to yes, the faster you can get building and the faster you can just have a happy customer. So yeah, that's the offer so far. And so then the key here is you want to go vertical.

So as always, you want to clarify, you're not a commodity. You're not just selling, you know, cloud code. You're not just selling chatypt. you're selling a vertically specific, industry specific agent. You're doing it fast. It shouldn't take longer than 48 hours to get up and running with the first agent for your customer. And you need to talk in terms of time, not time saved, but actually outcomes for the business. So like how much revenue can you generate for the business or how much, you know, always,

always business outcomes rather than time saved. I feel like time saved is a little overused. and people are kind of immune to that these days. So that's the offer. It's pretty simple. And I'll just dive into like what we're seeing in terms of our own experience of like running this offer. I believe that as a one person business, you can sell these agents into industries and really just kind of be not only selling the agents, but also just creating clarity around AI. Like I think if you're watching this pod, you understand AI pretty well.

You probably have a better understanding than most people. And you might not give yourself enough credit of how valuable that is. And to be the person who can create clarity around all the noise right now, that alone is valuable. And then to be able to couple that with the tools to help solve problems in these businesses, it's like you're going to become so irreplaceable for the business that, yeah, it's really just going to be like you and the agents are going to be what drives the value. So I have some industries here in red. I have health care and finance because I don't think that these are necessarily the best industries to start off in.

They're very high regulatory burdens and red tape. And so I actually recommend these other industries that we're seeing work really well, which is marketing agencies, law firms, insurance agencies, manufacturers, wholesalers, and real estate agencies. the reason for these industries that you might notice is that they're relatively, you know, I would say maybe legacy industries, not necessarily like, you know, new fast-growing industries, but they want to be fast-growing. They want to adopt AI and they have a lot of pain to be able to use it as a tool to essentially just grow their business.

The common pattern with all of them is they want to be a full-stack AI company, Meaning they want to be fully automated with AI. That's the dream outcome. We're not there yet. But you can certainly come in and start solving the problems from the executive level. And then it'll ripple its way throughout the rest of the business. And I'll dive in on some of the common patterns. But how are we feeling so far?

Yeah, I think those are all people businesses. So there's a lot of people. When you have a lot of people, there's a lot of waste in terms of efficiency and there's ways to automate things. That's one. Two is those, a lot of these companies want to be AI-Native is another way to say what you're saying. But they don't know how. They might have pieces of their companies that have become AI-native.

They might work with Deloitte. They might work with, you know, different AI transformation agencies. But to assume that these companies are 100% AI native is insane because they're not. And then the last thing here is these categories are large, right? Like law, it's really large. Insurance agency, that's really large. Manufacturing, that's large, wholeseters large.

the key here is once you've identified a category that you want to go after, then you have to figure out what is the subcategory or sub-niche that I want to go after. It's too hard to just focus on wholesalers. And the way to think about it from a framework perspective is, you know, pick a category and then you can do like, you know, real estate agencies in Florida. So that's like, you know, a geography is one way to do it. Or you can pick a specific type of real estate, you know, professional. So it could be commercial real estate, you know, agencies in Florida.

So there's different ways to think about how you can niche down. And that's going to be really key here because if you want to create an irresistible offer, you know, a big way to get the attention of someone is to be like, oh my God, this person is really speaking to me. Exactly. And honestly, like, even a little bit of like some maybe some contrarian advice from my end is like you don't have, I have a feeling as though you don't have to start super niche from the beginning.

In fact, you can always niche down after trying a marketing industry, trying with law firm, I'm trying all these different industries, seeing what works well for you, where the market pulls you, and then going super vertical. But I really love like the concept of like it's a design thinking principle of diverge and then converge. So like, you know, try many different things as long as it's not, you know, for too long because you don't want to get into this constant cycle of trying something new and, you know, you never get to focus. But once you find the thing that clicks for you, whether it's you're able to resonate. with the audience really well or you're just getting pulled into that market more. Like, yeah, go super niche, go sub-nish and use that as your wedge to kind of like infiltrate the rest of the market. Yeah, I think that's spot on. So, and then as far as the common

things that we're seeing, right? So with all these industries, what you'll find is the people you're going to jump on calls with, the people that are going to likely beat the decision makers and I mean, the ones purchasing your service or your product-type service. These are the executives. These are the decision makers. And when you abstract on all these industries, the decision maker at the end of the day has very similar problems no matter what the industry is. They have too many emails, too many meetings, too many follow-ups, too many open loops.

They have context over so many different projects and places and people to keep track of. And so just out of the gate, if you can anticipate this, you can have something that you put together that, you know, maybe from a template perspective solves a lot of these issues. And then you can cater more specifically into that niche, into that vertical for that industry. If it's a, if it's a law firm and you have a partner who wants to buy your services, you can have all of these things out of the blocks for your agents that you set up, which I'll show you how to do also in this video. And, and then you could also cater it for that particular industry.

So, oh, yes, we have an agent that does, you know, following up with people, projects, et cetera, but it also manages your cases. It does demand letters for your law firm. It does all the different things and skills that you would need for, you know, maybe a matrimonial law firm, for instance. So that's the abstraction layer on no matter what, you're going to be solving. a lot of executive problems. And then the key is to layer in vertical specific solutions as well. Okay.

So there's that. That's the market. So we talked about the offer. We talked about the market. And I have some side things as well about like how to get customers at the end of the day. I think everyone should make content. I think if you if you can jump on a call,

this is just a little tidbit. If you can jump on a call with somebody and they know who you are and what you sell without you having to tell them and they're warm to begin with, that's the ideal position to be. You never want to be in a position where you're having a cold call. You never want to sell to a cold audience. And in the beginning, you might have to. So starting for free even is sometimes worth it just to get case studies and get referrals. But content is like overpowered in 2026.

So I do recommend that. I mean, that's how we met. That's how we met. It's like midnight, can't fall asleep. I'm like doom scrolling Instagram. I see Nick's face pop up showing me, you know, how to use OpenClaw. And I was like, this is a guy who has some sauce and I need to have him on the podcast. So the other thing about creating content is not only is it helpful in terms of getting your face in front.

of customers or your offer in front of customers, but it also helps you, you know, get known, get on podcasts, hire the right people. So there's a lot of advantages in an AI world when you can use AI to automate a lot of the research and a lot of the, just help it, you know, the editing and things like that, just do it. Like I hate to say it, just do it. You got to just do it. It's just like, It's the most leveraged thing you can do. It's like content. And then if you think of other like leverage things, it's like, okay, AI or you could also have leverage with talents and software.

But yeah, it's it's incredible. And I think like the trend of 2026 is content is king. And I'll tell you a little bit of a tidbit as we go into this next segment. But I don't know about you, Greg. I have been going on walks. and what I'll do is I'll go on a walk and I'll send off a long horizon tasks to my agent via telegram. I have my own, you know, Hermes agent is what I use these days. And it's, I'm just like, I'm just in awe with what the world we live in today. Like how amazing, I can go on a walk

and there's work being done on for our business and on customers and, you know, for their agents by my agent. And I'm just like, if you extrapolate that over the next six months, 12 months, like the most leverage thing you could do is post a piece of content that reaches a lot of people and then have this robot that helps you fulfill for the thing that you're providing as you go on a walk or right before you go to bed or when you wake up. It's just, it's amazing. It's an incredible world we live in. So, yeah, let's dive into the stack, shall we? How do we build these things. Okay. So as far as the tools that you might need to fulfill for your service of providing agents for businesses, first or foremost, I use granola. I love granola. I use it for every

meeting. They have an MCP. You know, you can give it to your agent and it just has context over everything. And what I do is these meeting notes from granola, they automatically get synced into requests on Trello. And so Trello is the customer-facing like essentially project management con bond board that I use. And so, you know, there's a backlog list. There's a to-do list.

There's a doing list. There's a done list. And the customer can just simply drag and drop what they want into the to-do list for, oh, I want my agent to be connected to my calendar. I want it to have access to this other platform.

I want it to create content for me. I think I could just add these requests at one at a time. And the key here is these agents can at this point do so many different things. It could do so many things that you almost need to create, you know, prevent scope, create by limiting one to two requests in under 48 hours because there's a lot. And you could do a lot, but you just need to be careful that you don't. you know, end up drowning in a fulfillment nightmare. So that's why Trello is helpful in terms of scoping.

Loom is awesome. Your customers are going to want you to send them updates, you know, send an update at 2 a.m. Send an update at, you know, different times of the day of you implementing new things for the agent, whether you improve the memory or you improve the obsidian vault that it's operating off of. Loom is awesome.

And then I just use like CaliLink. I have a horrible funnel, but you can do a lot of, you can get a lot of bookings. Just Caldly link, personal website, drive traffic there, create content. These are like pretty much the customer facing tools. And then I have, I don't know about you, Greg. Do you use superhuman? The email tool? Yeah.

I don't, but people tell me I should. Oh, my God. If you have a lot of emails, you're going to have a lot of emails with customers. Oh, man. it's superhuman is amazing. It has a bunch of shortcuts. I love keyboard shortcuts. And you just fly through emails.

And it's not like it's AI generated. Like it makes you write the email and you have AI help you. But it's just a very focused, focused platform. And then lastly, Asana. I use Asana for internal facing. So not customer facing. You know, if I want to keep track of some specifics around details of what needs to be done. Yeah, that's the software stack.

Okay, let's dive into the agent side of things now. So for building agents, the irony here is, if you don't know how to build an agent, please don't worry. I got you. We're going to use agents to build agents. And so, Cloud code, they have a new desktop app. It's awesome. Open AI is Codex.

They have a new desktop app. It's awesome. And you can actually use these to build the agents for your customer. And as far as what agents to use, you have a couple options. You're not going to sell clot code to your customer. You could or codex. I mean, you could. But I highly recommend using Harmi's these days.

I find it to be the most reliable. It allows you to pick any model. The reasoning here is tomorrow there's going to be a new model that comes out. It's going to be infinitely cheaper. And it's going to be Opus 4.7 level intelligence. And it's like, you just want to have. the flexibility to quickly switch whatever the agent that you're running, whatever model it's running, be able to switch that quickly. And you don't want to be married to a platform,

married to a tool, married to an infrastructure. So Hermes, I really like. Have you played it around with Hermes at all? I think I saw some videos. Yeah. Yeah, I have, I haven't, you know, quite made the shift yet. But I've done an episode on it with my friend Imran. So go check it out if people are interested in learning about how to set up Hermes. We called it Hermes because we're fancy like that in the episode. And then we got, you know, the team at Hermes, you know, quickly corrected us. They did?

Oh, wow. I like Hermes. Yeah, Hermes is a little more fancy. If you sell Hermes agents, you can charge 10K a month. Exactly. So open clause commoditized already. It's 5K month. It's okay.

So you pick your harness here. So this is the agent that you'll sell and you need a place for that agent to live. You can use something like hosting or you can use orgo. You can use whatever. I obviously am biased. But orgo is really nice because in one workspace you can have all your agents, you have your agent managing their agents, and I'll dive into all of this and getting set up. And then lastly, you need the tools for the agents. Some things out of the box that I install for every agent,

no matter what, outside of just giving them a computer and the ability to use it, is Composio. Have you heard of this company Composio? I have, but can you give a one-liner for folks who haven't heard of it, heard of them? This company allows you to, this connector, they allow you to have one connector, one MCP essentially, that connects to thousands of other apps, whether it's Gmail, Slack, Notion, what have you. And with one connection, you can manage, you can have access to all the tools that you would need to send an email via Gmail or push something via GitHub or pull a message via Slack. It's incredible.

And it handles the tool, the tool calling, and the authentication, which is huge because security is like the biggest challenge of setting up these agents. Like, by far, the biggest time sync is getting authentication set up for the customer. Because you have to, what's your username and password for this? And if you email it, it's like not secure. So then you use something like Composio, done. So it handles that. And then it handles security.

in that sense as well. Everything's managed their platform. And then it handles the tool calls. So if you have Composio set up with all the connectors, you can just take that one connector, take it to any agent, and it has all the same connectors. So I really like this company. I don't have any affiliation, but I love their product.

Really great. Next up is agent mail. This one is I give every agent an email. It adds a nice personal touch. So, you know, let's say you're an executive. I give you an agent. You name it Mia. And Mia needs her own email.

Agent Mail allows you to give Mia an email so that she can send and receive emails. And that's really fun because it turns into like truly like a personal assistant. And then lastly, Obsidian. You have a video on Obsidian. It did really well. Obsidian. super important because at the end of the day, these agents need context. And the more context you can provide in a nicely wiki-styled structured format and

markdown files for the agent, it will really just thrive in terms of understanding projects, people, things that you're doing, so on and so forth. So this is the stack. And as far as models, I guess final touch around models, today, by far. the best model to use for something like a Hermes agent or an OpenClaw is GPT 5.5. It's so efficient with the tool calls. It doesn't eat through tokens like Opus 4.7 from Anthropic does. And Open AI is very generous around letting you use your paid plan with any model,

with any harness like Hermes or OpenClaw. and then and you just get a lot of usage out of it. So I recommend 5.5. If you want to use open source models that are a little more affordable for lighterweight tasks, GLM 5.1 from ZAI is in my experience like the best open source model to be using. Kimi comes in on a close second and these are both more affordable. And then Opus 4.7 finally, if you have some long horizon coding task, Opus 4.7 is really great for that.

And you can actually have your agent connect to Claude Code and be able to do these long coding tasks in Claude Code and then bring that back to the agent. So, tidbit there. I don't know if you can do this real quick, but could you give a one-liner on... Because people are going to... Sorry, let me take a step back.

People are going to look at this list and they're going to be, oh, my God, I don't know if I should use Codex or if I should use Cloud Code, if I should use OpenClaw, if I should use Hermes, should I use hosting or should I use Orgo? Should I use this? Can you go and just quickly, you know, what's NIC's stack and like with a one liner of why you use that tool over the other tool? Yeah. Codex because it's more generous and it's simplest and they have the best desktop app.

Hermes because it doesn't break and it's self-evolving. OpenClaw is not as self-evolving. Orgo, because we give your agent a computer so it can live in the computer, it can operate the computer. We're not just a headless VPS server in the cloud. And I'll dive in on that. Composio, you need this. Everyone needs this. Agent Mail, everyone needs this.

Obsidian, everyone needs this. That's a hot take, by the way. Obsidian, everyone needs this. Oh, yeah. Yeah. Just, I mean, explain why you should use obsidian over, say, notion. So here's my obsidian vault. And Greg, I've been building this vault since November of 2025.

Agents. I mean, what do you say? When something's outdated. Like super old. 2025. That's forever ago. You know? So I've been building.

this vault since 2025 November before Open Club, before Hermes. And it has everything about people, projects, everything. And I'm so crazy. I have a limitless microphone. Even that, daily transcripts get pulled from that into here. This is genuinely a second brain. Like people say obsidian that's a second brain and then, okay, they show it. Okay, that's kind of cool. They use it for some research. No, no, no. This is a second brain. And when you have something like this, it is quite literally, you get to experience what personal AGI might feel like in the next three to six months from now. I'm sure everyone will experience it. But I feel like I'm getting to experience it sooner because I just have such well-organized markdown files. It's incredible.

It's incredible. So it just gives your agent context on. what it needs to know given any given tasks. And it feels like it just never forgets and it understands you. And I think that's at the end of the day, like, we just want an agent that understands us and helps us with our business and just has perfect context over everything we do. Enough said. Yeah. And then 5.5 is the best. I would just use 5.5 to make it easy.

Yeah. GPD 5.5. So as far as that's the stack. Now, in Orgo, we give the agent a computer to live in. Greg, let me invite you to this. All right. So I just invited you, Greg, into this workspace in Orgo. And we're just going to quickly spin up a computer here.

And I'm going to spin up a computer. I'm going to say Greg's computer. I'm going to launch it. and it launches pretty fast with really fast desktops. And now that we're in this workspace here, in this computer, I can now install the agent inside of it, actually.

So the agent can live inside of here. So if it's open cloth, it's Hermes agent, in this case, it will live inside of this environment. And the key here is, regarding to getting set up, we have an Orgo MCP that is what I use

for setting up agents. And that little story I told earlier about going on a walk and be able to get work done on a walk, it's because my agent is using a Orgo MCP to connect to my customers' agents that live on Orgo. And so what ends up happening is, Orgo is like this workspace where my agent and other agents and myself can all collaborate on these computers

where these agents live and get them set up and configured that way. So here I have a, I don't know, can you see my telegram chat? Yeah. I had my agent last night. Actually, I kicked off a task. I told it to go ahead and build out some CLI and skills for Orgo. But I'll start a new chat here.

And I can actually just tell the agent, I'll grab the computer ID from Orgo. So let's grab this computer ID. and I can give this computer ID to the agent. And I'll say, set this computer on Orgo up. Computer ID quoted here. Let's install Hermes agent into the VM. So the reason why I tell everyone not to get stressed out or scared, about setting up these agents is you really just need another agent to set it up.

In my case, I'm using another Hermes agent to set up a Hermes agent. In another case, you could, I'll spin up another computer here. In another case, you can literally install something like Claude Code into a VM on Orgo. And you can actually just run Claude Code from the terminal here and tell Claude Code in natural language, hey, let's set up Hermes agent. So just real quick, you know, cloud code, install command for Linux. You find that real quick. And you just run this in the terminal here, and you would literally install cloud code, run it from here, and have it install Herbys into this VM.

So the answer to all of our problems, Greg, is that more agents is the answer. If you're confused on how to set something up, have your... agent do it. And yeah, so I'm just going to install cloud code here. It's going to get that going, and we'll be off to the races. This will be a dumb question, but why are we doing virtual computers versus doing local computers, you know, buying Mac minis and doing that whole thing? It's actually a very, very good question. And the reason is we want the ability to be able to be able to be able to to work on our customers' computers from where we're at. And if you are using a Mac Mini,

I can't even imagine the nightmare of having to go in person and debug something that's like at a hardware level or something on the Mac Mini bricks or an update or what have you. Orgo gives you cloud computers to be able to manage these agents. And with that, you can do so many more amazing things, both from a perspective of just scaling your business, being able to access all these agents on one platform, via one connector,

and have your agent connect to all of them. That's really like the biggest thing. It's just from a fulfillment perspective. It is just like the easiest way. And then also just a security perspective. These are isolated cloud computers, and you can delete them. And under a second, you can create a new one.

And with that, there's a lot more standard. box environments that you could just protect you and your customers from like a blast radius that might otherwise be more dangerous on a personal Mac Mini. And so say I have 100 customers, am I creating, like how am I structuring that? Am I creating like separate like projects with these computers in it? Like what is from a best practices perspective in terms of security and just, you know, good UX, how should people think about sending that up?

Yeah. So in this case, it would be exactly like you said. Like, if you were a customer, I would just make a workspace for your business. And I would say, you know, this is what's to like idea browser, right? And we would create this workspace and each of your agents would live in this workspace. And then I'd have other work spaces for other customers. and I'd be able to manage all of that, you know, on, on orggo. Yeah, one platform.

Cool. Yeah, I think what's also cool about this, just how visual it is, like showing this to a customer and being like, I know you think, you know, it's not secure. You might think it's not secure or you might think, you know, but this is, you know, a visual sandbox environment, right? Like it just feels like the cell. Like you just like, you talked about loom before, but like showing looms of this, I think it's just going to light people up. Yeah, exactly.

And also like, you can also out of the box on Oregon, like we have this playground mode here. So like this is our, this is just all of the latest models from, you know, Anthropic and Kimmy and chat GPT. And so as far as a demo, when you tell a customer like, oh yeah, like we can we can have an agent like operate a computer and do. do things for you and essentially you're describing Hermes agent or you're describing OpenClaw. Even then, they might have a hard time imagining like what does that look like? What does that feel like? And so when you just give it a computer, you're able to just give it life and you can tell them like you can say like, hey, look up what is idea browser and search it on Google. And this actually becomes like a really good demo. Like for for you and your customer like,

to be able to show, look, oh, the agent is controlling a computer and it's doing research and it's doing real work. And you can just quickly show a demo in Orgo. It's like super cool. This is cool. Yeah, like even me as like a co-founder of Idea Browser, I'm like looking at this and I'm like, yes. Yeah. Yeah, it's awesome.

And we have some, I'm making Jordan some agents. I don't know if he told you. I'm making him some idea browser agents. He's using them. He's stress testing them. But everyone needs agents. So it's, yeah, it's really cool. And then as far as the telegram setup here, like, you can see my agent is literally using

Orgo MCP to get this Greg's computer set up right now. And it's installing Harmie's agent. Part of this, some of these things take time. It's running a long process. It might take five, 10 minutes. So I'll have to bore you by sharing that. But the concept of use agents to set up other agents, it's very real. And I can also dive into practices around that and how to make sure that your agent knows how to set up other agents.

Yeah. Does that sound good? Let's do that. That sounds great. So to have your agent have context of how to set up other agents, it actually needs, I wish I would have added them here. a few MCPs go really far away. One of them is the perplexity MCP. With perplexity, you can give your Claude Code or Codex

real up-to-date knowledge on things like Hermes. And so the key here is like you always just want to have any sort of setup process, initialization process, grounded in real context of what is the docs for setting up Hermes agents today. and how do I connect my Hermes agent to iMessage? If you have something like perplexity, you give your agent the ability to see how to do that

and be able to set it up perfectly. Exa AI is another great MCP tool for like real-time web search. Another big one actually is Context 7. This one is awesome for getting up-to-date docs from like GitHub, from like Hermes agents GitHub, so they can see specifically the docs of how to get set up. You just need some sort of context layer

to loop in the best practices and up-to-date docs for setting up these agents. And kind of like one final recommendation would be the XMCP. So Twitter released their own MCP. And I find so many amazing setups on Twitter for OpenClawn Hermes agents

that there's many times I just want to use that context for setting up an agent for a given task. And you could actually use this, this to your cloud code or give this to your codex and have it use this context to help you set things up. Or you can use all of them too. So, I mean, is there any downside to using all of them? No, I use all of them. And so like maybe even in here when you look at my telegram, you might notice, oh, I guess it's, it's, I didn't ask it to pull in up-to-date context.

Mine has skills already built in place to be able to set these things up just because I do it so much. But in general, the more the merrier, like context is key. And I like to have subagents spawn. I'll tell Codex like, hey, or Claude Code, hey, spawn five subagents, one subagent for perplexity, one for XO, one for Context 7, one for Firecrawl, one for XMCP. because I like to pull from different resources and then those all come back to the main agent and we get the best practices. So that's how I do it.

Cool. Let's see. Okay. So this here is the, I should have ran this in the terminal below, but I'll go ahead. I'll just run it in this terminal. And what we're going to do here is do that, run Claude. We could just like spin up multiple terminals. Yeah.

You can... Oh, wait, let me see. Okay, I think I just copy this here. So, okay. Oh, command not found. Okay, I'll debug this later. This is also why... This is mainly why I use the Orgo MCP.

I'm just like, I let my agent do all the work. Actually, you could also come here into the playground and say, install cloud code into this computer and just have our agent do it because I don't want to debug what's going on in the terminal right now so then just have this agent do it and do it that way.

But yeah, once you have it set up from here, I can now ask my telegram agent so I'll stop this here. You can just imagine one that's done, your agent's set up, and I'll start a new chat. And I'll ask, like, how many orgo VMs do I have in my work spaces? And my orgoclaw is able to actually manage all of my customers' agents from, you know, just this one agent.

And it can upgrade, fix things on the fly, you know, and all from one spot anywhere on that. If I get an email from a customer that something broke, we can just send off an agent, send off a message to Orgo Claw and have it go fix it. Boom. You can see here, 27 Orgo VMs across your work spaces, all 27 shows running. And then it dives in onto all the different customers and all their agents. So last point that I want to make around getting these things set up is the watchdogs.

So the gateways are what make these agents connect to a platform like Telegram or a platform like WhatsApp. And sometimes these gateways crash. OpenClaw has a lot of gateway issues in my experience.

Hermes is a lot better. And so a key here is you want to make sure that you set up a watchdog. You could literally just tell your agent set up a watchdog. for whenever a gateway crashes, that it auto restores it. That's super important just from, you know, reliability perspective. A second thing is you want to make sure that you have some layer of observability or alerts.

So I have agents email me. If I set up your agent, your Mia agent, and Mia has an email. Mia emails me from her email. when her cron job breaks or her skill failed or something happened. And I'm alerted about it. And I can go in and then debug it and fix it, which is super valuable because once again, for your customer,

you don't want them to have to worry about like doing all this themselves. So make it as simple and easy as possible. Handle everything tip to tail. And yeah, I think, I guess the big takeaway here is it is hard to set up ClaudeCode even. Like people are like, Claude Code is going to kill OpenClaar. Claude is going to kill Hermes agent. And in a general sense, it's getting better at doing a lot of these general things.

But to be able to go in and create a specific agent for a specific industry in person and have it tailored to their workflow, it's like you're underestimating how much value that is. and you can really create a lucrative business by yourself, you and your agent, building other agents for other businesses. Yeah, and I think it's an amazing time to be a solopreneur for this. You can and you will. So, Nick, thank you for sharing the playbook for how to build a one person, agent-led business, sharing how to actually do it in such a clear way.

I love chatting with you because you're, you give the sauce, but you also explain it super clearly. Nick is a criminally underfollowed account on social media. You know, he's getting some followers, but I think he needs to be bigger. So I'll include links for where to find Nick in the show notes in the description. And Nick, I'll see you in a few weeks in San Francisco. And let's have a, let's have some coffee and have a good time. Thank you, Greg. Always a pleasure. Thank you so much. And I hope to, yeah, we're going to see you soon. We're going to get some coffee. We're going to do some sip in time. We're going to do some

IRL sipping time, which is my favorite. It's there's nothing like it, you know? I actually have been trying to cut down on my like Zoom meetings and stuff like that. There it is. There's nothing like being in person, sharing ideas, sip in, and figuring out what we can be building in a time like this because there's so much and sometimes the hardest part is figuring out the right

idea, the right time, the right playbook, the right steps, the right order. And this has been helpful, Nick, and definitely got my creative juices following, so I'm sure others are very thankful as well. So thank you, Nick. And I will see you next time. Thank you, Greg. Talk soon.