I know you see all the tech bros showing off their AI operating systems like that's the only way to create an AI team - but I've cracked a simple code that makes AI teams simple for non-techy women.
If you've watched those videos, you've seen the dashboards, the dozens of agents talking to each other and the screens full of code. It looks impressive, and it also makes it look like an AI team is something you'd need a developer, a spare month and a very technical brain to build.
That's what puts so many women off. They're organised, they run their businesses off a to-do list, and they've decided AI teams aren't for them.
Before, I'd sit in one chat window, having one conversation at a time. Now I go through all seven projects, give each task an update, send it to the agent, and come back an hour later to see where it's at. Then I move it to the next phase. I can do that from my phone or my computer.
I don't manage that with a dashboard. I manage it by updating tasks, and it works because the structure underneath is right.
The Incuv8or AI Framework
This is the whole thing. Six steps, in this order.
THE INCUV8OR AI FRAMEWORK
1. BUILD YOUR AI BRAIN
Your business, written down where AI can read it.
2. MAP YOUR ORG
The AI Org Mapper turns your brain dump into a COO, departments & the
skills you need, & saves the chart in your brain.
3. BUILD YOUR COO
The one employee you talk to. It knows your org chart.
4. ADD EMPLOYEES ONLY WHEN THEY PASS THE TEST
Your COO drafts each one with you: a folder with an agent file &
skills index. Anything that fails the four-part test is a skill in
one shared library.
5. HAND OUT THE WORK FROM YOUR TASK MANAGER
Same statuses on every list, a field for the employee, a dispatcher
that picks it up.
6. ADD ROUTINES WHERE THEY'RE NEEDED
Only for jobs that run on a schedule.
One rule runs across every step. Nothing goes live without your approval, and every correction becomes a rule the employee keeps.
If you can write a to-do list, you can run this. The work goes in as a task, and it comes back as a task.
Why the big systems put non-techy founders off
An AI operating system asks you to build everything at once. You need the dashboard, the database, the agents, the connections between them and the code that holds it all together before any of it does anything for you. If one piece breaks, you need to know which one and how to fix it.
The Incuv8or AI Framework works the other way round. The foundation is key. Get the data right, and everything else becomes easy. Your AI employees read your business from your AI brain every time they pick up a task, so if the structure and the information are right, the rest is just handing out work.
What you need before you start
- The Claude desktop app on a paid plan, with the Claude Code tab.
- Obsidian, for your AI brain. It's free.
- ClickUp, for step 5. Any task manager with custom fields, statuses and comments will work, but the steps say ClickUp.
You don't need to know how to code, and you don't need a dashboard.
Step 1 - Build your AI brain
Your AI brain is your business, written down where AI can read it: who you are, what you sell and your clients. Mine is an Obsidian vault, which is just a folder on my computer, and every AI employee reads from it before it does anything. That's why it comes first. Everything you build after this reads from it.
The full setup, with every prompt, is in How to set up your AI brain in Obsidian. When it's done, open the Claude desktop app, click the Claude Code tab and start a new chat. Click the + at the bottom of the chat, choose your vault folder and paste this.
Read my AI brain. Then tell me what I sell, who my client is & what's
going on with them right now. Tell me which files you read to answer.
What you'll see: the right answer, with the names of the files it read. If it's vague or wrong, fix the documents before you move on.
Step 2 - Map your org
Before you build a single agent, work out what your business actually needs. I use a skill I built called the AI Org Mapper. It asks you how you run your business, one question at a time, and turns your answers into an org chart: a COO at the top, your departments underneath, the employees each department needs and the skills each one uses. It saves the chart in your AI brain.
Install it from How to map your AI org chart before you build any AI employees. Then start a new chat in the Claude Code tab, attach your AI brain folder and type this.
Hey Claude, I want to use /org-mapper to map out my AI org chart.
What you'll see: your org chart, with your top five things to build. The first one is always a COO.
Then put the structure in your AI brain, so your AI team can read it. Mine looks like this.
ORG
├── AI ORG CHART.md - the map
├── COO/ - the one I talk to
├── DEPARTMENTS
│ ├── Business Operations
│ ├── Clients
│ ├── Marketing
│ │ └── [Employee]/
│ │ ├── agent.md - who it is, what it connects to,
│ │ │ which model it runs on
│ │ └── skills index - the skills it uses
│ ├── Sales
│ ├── Product
│ ├── Education
│ ├── Technology
│ └── Personal Life
└── SKILL LIBRARY - one skill per process, shared by everyone
I have eight departments because I run multiple businesses. I am developing software, I have an educational and coaching platform, and I have my freelance business. My products and my services are two separate departments: Product is the projects, side pieces and software I build, and Clients is the services I deliver as a freelancer.
My org chart is a little more complex. However, for most of you starting out with just one stream of business - like selling digital products, coaching, or providing online services - your departments will be fewer. That's what the AI Org Mapper is for. It builds yours around how you actually run your business.
In the same chat, paste this.
Read my AI ORG CHART.md. Set up the ORG folder in my AI brain to match
it: a folder for my COO, a folder for each department on my chart & an
empty skill library. Don't create any employee folders or write any
agent files yet. Show me the folders before you create them.
What you'll see: the folder structure, empty and ready, with your departments rather than mine.
Step 3 - Build your COO
Your COO is the one AI employee you talk to most. Most COOs wear 20 hats, so it was the easiest and fastest way to get AI doing real work in my business. You brain dump to it, and it hands out the work. It knows your org chart, so it knows your departments and who should hold each job.
The full build, with my COO template and every prompt, is in The First AI Employee I'd Build as a Non-Techie Founder: An AI COO.
What you'll see: a COO folder in your AI brain with its agent file, which you've read line by line and approved before it takes any work.
Step 4 - Add employees only when they pass the test
Once your COO is working, it drafts each employee on your top five with you, one at a time. Each employee is a folder with an agent file and a skills index. It doesn't build them on its own. You test each one with a real job and approve it before it takes any work.
Before any new employee, run the four-part test. A job only gets its own employee if it needs its own context, different permissions, a different model or to run at the same time as the others. If it doesn't need any of those, it's a skill in your shared library. The test is mine, built on the three reasons Anthropic gives for adding another agent in When to use multi-agent systems (and when not to), plus two points from their Claude Code docs. Their advice is the line I work from: "Start with the simplest approach that works, and add complexity only when evidence supports it."
You're my COO. I'm thinking about a new AI employee for [THE JOB]. Run
it through my four-part test: does it need its own context, different
permissions, a different model, or to run at the same time as the
others? If it passes, draft its agent.md & skills index in the right
department & show me before you save. If it doesn't, tell me which
employee should hold it as a skill.
What you'll see: either a draft agent file and skills index for you to read and approve, or the name of the employee that should hold the job as a skill.
The whole test, with examples from my own team, is in Do you need another AI employee?. How to write the skills themselves is in How to Build a Claude Skill.
Step 5 - Hand out the work from your task manager
Now you want to hand work to your COO without opening a chat. In ClickUp that's three things: the same statuses on every list, a dropdown field called AI EMPLOYEE, and the dispatcher. The field says who. The status says whose turn it is. The dispatcher is a small script that checks ClickUp every 10 minutes for tasks with an AI EMPLOYEE set and a "w/ agent" status, and starts Claude on each one with that employee's agent file.
If you haven't connected ClickUp yet, open Settings, then Connectors, find ClickUp and click Connect. You sign in on ClickUp's own screen. Then paste this.
I want to set up ClickUp so I can hand work to my AI COO & the employees
I've approved.
Look at my lists & suggest one set of statuses I can use on every list.
It needs to include "w/ agent to do", "w/ agent for edits",
"w/ [MY NAME] for review" & "w/ [MY NAME] for desktop session". Then walk
me through adding those statuses & a dropdown field called AI EMPLOYEE
with an option for my COO & each employee I've approved. One step at a
time.
Statuses and custom fields are set in ClickUp itself, so you'll do the clicking and Claude will tell you exactly what to click. The prompt that builds the dispatcher, and how to keep your ClickUp key out of the chat, are in Step 5 of the COO post.
Step 6 - Add routines where they're needed
Not everything should go through the COO. Work that has to happen on a schedule becomes a routine: a timer that wakes an employee up to do its job.
Mine are a morning brief that's ready at 06:06, an inbox assistant that sorts my email every hour, a meeting notes routine that checks for new notes every 30 minutes, and a knowledge base updater that writes the day into my AI brain at 22:37. Everything else goes to the COO as a task.
Look at my AI org chart & my ClickUp. Tell me which jobs have to happen
on a schedule & could be a routine, & which ones arrive whenever &
should go to my COO as a task. Give me one line on why for each. Don't
set anything up yet.
Add routines once your employees are doing the job well when you hand it to them. If you want to see one built from start to finish, it's in The Morning Brief.
What it looks like in my week
I update the task with what I want. I set the AI EMPLOYEE field to the COO, and I set the status to "w/ agent to do". Then I walk away.
When it's done, it's back in my inbox at "w/ samantha for review", with the work at the top of the task and my brief kept underneath. If I want changes, I comment on the task and set it to "w/ agent for edits". If I'm happy, I close it.
Meanwhile, the routines do their jobs without me.
The catch, and the fix
The catch is that this only works if the work is in the task manager. If you explain what you want in a chat, or in a voice note that never becomes a task, your AI team never sees it.
The fix is one habit. The brief goes in the task description, every time, and anything you'd add later goes in a comment on that task.
The second catch is that it's tempting to skip steps 1 and 2 and go straight to building employees. That's how you end up with twenty agents you don't use, reading a business they don't know. If you've already done that, build your AI brain and map your org first, then run the four-part test on the team you have, using Step 4 of Do you need another AI employee?.
What this looks like as a business
Every founder you support has seen the same videos and decided AI teams are too technical for them. Setting up their AI brain, mapping their org, building their COO and the few employees they actually need is a systems job. You're paid for knowing what to build and in what order.
Start with one
This week, do Step 1. If your AI brain is already set up, run the test prompt in Step 1, then go straight to Step 2 and map your org chart.
If you haven't got your AI brain set up, that's the foundation for all of this: start here.
this is the free stuff — imagine what we'd build together
Ready to make your business AI-enabled?
Consulting and one-to-one coaching for founders and freelancers who want AI actually working inside their business — not just talked about.