← All posts

Learn Cowork in Cowork

The fastest way to learn a new tool is to use it with someone who already knows it, sitting right next to you. You ask a small question, you get a straight answer, you keep going. That's often hard to arrange, and it doesn't scale, so most people learn Cowork the slow way: trial, error, more error, and maybe a forum thread written three model releases ago.

We're building a better version of the person sitting next to you. Its name is Chet.

Chet is a managed agent: a Claude expert you put on retainer. You ask it how to get a real task done well, and it answers based on current knowledge, not on whatever was true two model releases back. When the tooling changes, your expert changes with it. You don't need to keep a prompt library or chase release notes. We do that centrally, so Chet is up to date the next time you open it.

Learn Cowork in Cowork

Here is the part this post is about. Chet lives in the same workspace you're already working in. When you get stuck connecting a folder, or you're not sure how to phrase a request, or you want to know whether a task is even a good fit for Claude, you don't leave to go read documentation. You ask Chet, in plain English, right where you are. The lesson and the work happen in the same place.

That matters more than it sounds. Most tools teach you in one window and make you work in another, and the knowledge leaks out in the gap. Learning Cowork inside Cowork closes the gap. The answer arrives in context, about the thing you're actually doing, at the moment you need it.

Where Chet is today

The hard part, getting a managed agent to install directly into your own Claude Cowork space and answer when asked, is proven and running. The part that serves the answers is being built right now. So this is not "sign up and use it tonight." This is early access: a small first group, first-come, first-served, who get in as we open seats. Chet will get smarter every day.

There's a second piece on the way. Some things are easier to watch than to read, so we're recording a short series of follow-along video tutorials, three to five minutes each, starting with creating your first file in Cowork. The videos are built to be done alongside you, not watched passively. The first ones land with early access. If there's a topic you want covered, just let us know. That's how early access works.

Why a retainer, and not just "ask Claude yourself"? Because the value isn't a single answer. Models can change monthly, major app changes can occur weekly, and minor ones daily. It's an expert who stays current, learns how you work, and understands your team better over time. The retainer is the relationship. Staying current is the point.

Early access signup is open now. The first cohort will be small and highly appreciated.

Get early access →

Regards,
Charles Stack
Founder, Coworkers.Global

Coworkers.Global is an AI staffing agency. We place managed agents into organizations that need dedicated expert knowledge work. A managed agent is an AI specialist provisioned for a specific role, trained on your context, supervised by a person, and accountable for its output. The first, Alex, evaluates startup business plans for fundability, informed by human expertise and research, and calibrated against real investor decisions. We are early-stage and pre-revenue, so we lead with the quality of our judgment rather than customer logos we don't yet have. Your managed AI coworker.
Get new posts by email

What we're learning building a startup with managed agents, plus notes on raising. Monthly newsletter, no spam.