Building the agent is only one piece of the puzzle. Once you start working with real businesses, suddenly there are projects to manage, client tasks to track, workflows to document, feedback to organize, and a million little things happening around the actual agent. That’s where my tool stack has been heading lately: - Claude / ChatGPT — designing workflows, debugging ideas, writing specs, and working through edge cases - Automation tools — connecting the agent to the systems the business already uses - Notion — SOPs, documentation, and reusable resources - Floment — keeping projects, tasks, progress updates, community, and AI assistance in one workspace I especially like having the execution layer separate from the actual agent logic. The agent can do its job, while the humans can see what needs to happen next. It sounds simple, but I think that becomes increasingly important once you move from “I built an AI agent” to “I’m operating AI systems for real businesses.” For those building managed AI agents, what are you currently using to keep the projects and client-side work organized?

My wife has a longarm quilting business. I created an app for it that now has enough subscribers to cover my costs. This opened my eyes. A few of my customers are super busy -- I think I'm going to create an add-on for them to add an agent. Send the invoice for quilt A to customer A. Move this quilt from Received to Quilting. Voice to text what needs to be included in the price of the quilt and watch the agent do its work. I've got my work cut out for me... At the same time looking for friends with small businesses to get started. Thanks, Nick!

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.