
I spent the better part of a year experimenting with AI and coming away unimpressed.
The chatbots were fine for generating a quick summary or answering a trivia question. But every time I tried to use them for real work, the same problem showed up. They had no memory. No connection to my actual files. No way to do anything except talk. I’d describe a task, get a wall of text back, and then do all the work myself anyway.
Then Claude Code arrived. Suddenly the AI could read and write files on my computer. That changed things. I could point it at a folder full of notes and say “find every open task and organize them by project.” It would actually do it. But Claude Code ran in the terminal, which meant I had to think like a programmer to get anything done.
When Claude Cowork showed up, the programming barrier disappeared. Same power, but now I could just talk to it. Describe what I needed in plain English and watch it work. That’s when things got interesting.
Add MCPs (connectors that let the AI talk to your calendar, email, Slack, and other apps) and the whole picture comes together. Memory, because it reads your files. Skills, because you can teach it how you work. Reach, because it connects to the tools you already use. That’s the formula.
Once I had all three pieces, I started building. Email processing first. Then daily planning. Then task management. Then customer support, content publication, journaling, sponsor tracking, podcast production, weekly reviews, and a shutdown routine that wraps up my day in fifteen minutes instead of an hour.
At some point I looked up and realized I’d built something. Not a chatbot I ask questions. A system. A persistent assistant that knows my projects, remembers what I told it three weeks ago about that contractor invoice, and handles the tedious stuff I used to spend hours on every day.
I call it my robot assistant.
The biggest difference isn’t even the time saved. It’s that I stay in the zone. I used to break focus a dozen times a day to deal with admin. Email, invoicing, task shuffling, calendar juggling. Every interruption costs more than the minutes it takes. It costs the momentum. The robot handles the donkey work now, and I keep working on the stuff that actually matters.
Today I’m releasing the Robot Assistant Field Guide. It teaches the method behind everything I just described. How to use Claude Cowork and Obsidian to build your own personal AI assistant from scratch.
I want to be clear about what this is and what it isn’t. This is not “let AI write your stuff.” If you want a tool that does your thinking for you, this isn’t it. The Robot Assistant Field Guide teaches you to build an assistant for the donkey work. The email triage, the task management, the scheduling, the data entry, the repetitive admin. So you have more time for your real work.
You get ten foundation videos, about three hours total, that take you from zero to a working robot assistant. Each video builds on the last. By the end you have a functioning system ready for real work.
Then the 10-week live workshop series starts April 2. These aren’t webinars. They’re hands-on working sessions where we build real workflows together. Email processing. Calendar and daily planning. Task management. Personal CRM. Review cadences. All recorded if you can’t make it live.
You also get a Starter Kit with a vault template, sample workflows, and an AI-powered assembler that personalizes everything to your work. You don’t need to be a programmer. You need a Mac and a willingness to try something new.
The price is $199, one-time purchase, no subscription. Use code ROBOTLAUNCH for 10% off through March 30.
I’ve made a lot of Field Guides over the years. This one feels different. It’s the first time I’ve taught you to build the actual tool. The robot assistant isn’t a demo. It’s how I work now. And I think it can be how you work too.
Here’s the first Foundation Video:


