Posts Tagged → Claude Cowork

The Robot Assistant Field Guide is Here

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.

Get the Robot Assistant Field Guide

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:

Don’t Let the Robot Drive Alone

Since the first release of Claude Cowork, I’ve been diving deep on the tool.

Even when I had my OpenClaw dalliance, I still had a useful robot assistant helping me out in Claude Cowork. I’m convinced that at this point, it is our best option for getting AI assistance with donkey work.

OpenClaw is a 24/7 open door. If the AI hallucinates, it hallucinates with actual consequences. If it misunderstands a command, nobody’s watching.

With Cowork, I watch the AI work. I log in. I verify what it’s doing. Then I log out and the AI doesn’t stay logged in. It doesn’t make decisions in the dark. It executes tasks under supervision.

This sounds less efficient. It isn’t when you consider how much bigger the trust envelope gets.

I still get AI handling my posting, invoicing, and support. The AI processes the work in the same timeframe. The only difference is I’m present during execution.

The trade-off is asymmetric. You lose maybe 10 percent of the raw automation benefit. You eliminate 90 percent of the risk.

With Cowork, nothing happens unobserved. You’re present. You catch the mistake before it’s committed.

The supervised model feels slower only when you’re not familiar with it. Once you’re comfortable, Cowork moves fast.

You initiate a task. You watch. You verify. You’re done. If I trust the process, I’ll put it in a different space and just occasionally swipe in to make sure it’s doing the job.

This model is consistent with the way we humans historically handle high-risk situations. You don’t trust your accountant completely. You verify the numbers. You don’t trust automated backups. You test them. Supervised AI is just the same principle applied to autonomous agents.

If you’re thinking about AI automation, start with Cowork.

Get comfortable with supervised execution and learn where AI makes mistakes. Understand the kinds of donkey work you can offload without the extraordinary risk of an independent agent.

If you want some help getting started, stay tuned. I will have something for you … soon.