Video: How To Use Claude Cowork by one of the Engineers Who Created It

As I indicated in another post, I have subscribed five of my team members to Claude Teams. I came across this video by one of the engineers who developed Cowork. It is a little slow at the beginning, but I think it is worth watching. I learned a good deal from it.

In this episode, I sit down with Boris, the creator of Claude Code and one of the key builders behind Claude Cowork, to unpack what Cowork actually unlocks and how people use it in the real world. He walks through a hands-on demo where Cowork organizes files, extracts receipt data, builds a clean spreadsheet, and even drives the browser to create and share a Google Sheet. We go deep on how “agentic” work feels different when the model takes actions across your computer, your browser, and your tools. Then I shift into Boris’s viral workflow for Claude Code: parallel sessions, plan-first execution, Claude.md as a compounding team memory, and verification loops that dramatically improve output quality.

4 Likes

I wonder how this fits in with Macsparky’s warning about OpenClaw?

It’s quite different. With Claude Cowork you are limiting its access to a specific folder and giving it explicit instructions to follow. There are also many built-in guardrails preventing it from being destructive. I’ve used it extensively (including Claude Code) for working with documents and it’s been a pleasure to work with.

1 Like

I’ve created a directory named “Claude’s Files” where I can put things that I specifically want Claude to work on. Of course there are times when you need to give Claude access to some other folder or directory—if you want it to clean up your downloads folder, say—but for a limited subset of documents it seems like good hygiene to be purposeful in this way.

Thanks. I guess that is somewhat like NotebookLM. Still working my way through the video Dr Mosbacker referenced.