Check out this video I did w/ Greg!

Corey Ganim just had me back on the Build With AI podcast to break down exactly how I’m building and selling managed agents for $5K/month. The part that still feels like the future is that my agent, Dewey, now handles most of the fulfillment himself. He builds the client’s agent on Orgo, turns discovery calls and Slack context dumps into skills, onboards the agent into the client’s Slack, and handles customer support after launch. I’ll literally be out on a walk, watching Dewey solve client problems from my phone. Here are the biggest lessons from the system: 1. Agents building agents is already here. Dewey recently built a $5K/month client’s agent and onboarded it into their Slack himself. 2. Build is becoming commoditized. The valuable skill is knowing which questions to ask, understanding the client’s business, and pointing the agent at the right tools and problems. 3. Every agent should have its own identity and resources. Dewey has his own email, phone number, computer, memory, and card. He can sign up for software, pay for tools, communicate with clients, and complete work without waiting for me. 4. Customer support can become part of the agent’s job. Dewey sits inside iMessage and Slack conversations with clients. When something breaks, he can investigate and fix it directly. 5. The stack is simpler than people think. You need a harness like Hermes or OpenClaw, a strong model, an Orgo computer, Agent Mail, Agent Phone, Obsidian, Honcho for memory, Composio, and Latitude. The Agent Bundle packages the agent’s card, email, and phone for around $20/month. 6. Templatize once, deploy forever. Once you build your ideal agent stack, save it as an Orgo template. Then you can clone that exact infrastructure for every new client instead of rebuilding from scratch. 7. Nobody pays $5K/month for an agent just because it’s cool. The agent needs to make the client money. The strongest model I’ve found is helping a business build an agent they can resell to their own customers. That turns the offer from B2B into B2B2B—and makes it much harder to churn.

I just built a full AI employee from scratch in this video. Everyone’s hyped on agents but barely anyone’s actually showing how to build ones that can really work inside a business. Here’s the entire stack I spun up live (no holding anything back): • Cloud computer running Hermes on Orgo • Its own email (AgentMail) • Its own phone number (AgentPhone + iMessage) • Telegram as the main chat interface • Every tool & connector hooked up through Composio • Credit card so it can actually spend money • Obsidian vault as its knowledge base / second brain • Latitude for observability so I know when shit breaks I made one main orchestrator agent (named it Hubert) that stays in charge 99% of the time and just hands tasks off to specialized sub-agents underneath it. One giant bloated agent is a nightmare to debug. This way everything stays clean and purpose-built. Full live build, every prompt I pasted, every terminal I opened… it’s all in there. And I’m giving away the complete templates for the orchestrator + every sub-agent I build going forward. I'm giving you actual employees that can do real work. Watch the whole thing here: PS - the template is free here on Github: https://github.com/nickvasilescu/nicks-stack

November 2025, I had one month of runway left. I was living in a hacker house in Berkeley with 15 other people, working out of an electrical room under the stairs, trying to build my AI agent business at the time called ComputerUse.Agency. Before that, I had been running an AI edtech platform that was doing a few grand a month at one point, but by then it was trending to zero. So I had a choice. Keep trying to save the thing that was slowly dying, or go all-in on something bigger. My now co-founder, Spencer, was building the early days of Orgo, and I thought to myself: “What the hell? Let me try selling computer use agents to businesses as AI employees.” The next morning, I booked seven calls. By the end of the week, I had my first paid customer: a $3,500 implementation for an AI agent automating distribution workflows. And the whole thing was built on top of Orgo. Orgo was originally meant to be more of an AI researcher tool for computer use agents, but I was using it differently. I was running a business on top of it. At some point, Spencer and I looked at each other and realized I had more revenue than he did. We were like, what are we doing? We should just work together. Fast forward to January 24th. Spencer was landing in San Francisco, and I was supposed to pick him up from the airport. I was already running late, but there was this new thing called Clawdbot. Out of pure excitement, I pulled out my camera and made a quick video explaining what Clawdbot was and how to set it up on Orgo. The first 10 minutes, it was crickets. At the time, I had no following. I would get one or two likes on most tweets. Truly, nobody was watching. But then the video started moving. It went on to do 1.5 million impressions on Twitter, then another million on Instagram, then another million on TikTok, YouTube Shorts, and everywhere else. That post was the first video to ever go viral for Clawdbot, or OpenClaw, as it’s now known. To this day, I’m still on the front page of OpenClaw’s website, slight flex, I know.