Greg Isenberg

They've got a mug of hot coffee.

Your job is you want to leverage

this as much as possible.

So you don't want your agent to hold a hot coffee, so if you ask it to move this desk into this area, it says, no, I'm holding a cup of hot coffee, I can't do that.

So what sub-agents do is it basically creates leverage

for your open claw.

And it basically says, okay, you're going to create a set of sub-agents who are going to be good at XYZ thing.

And that way it frees up your main agent to, as you say, orchestrate, to basically be the manager of the sub-agents.

And what that can mean is looking at quality of work.

It can mean

checking for certain things and stuff like that.

So I'm certainly bought in on this idea that it could be a really good employee.

I think there's also cases where people aren't setting up their open claw in the right way where it ends up being a bad employee.

And I think that's sort of the...

The issue with that is sometimes you have a bad employee because the manager, the coach essentially, is not doing a good job at giving the right context at the right time.

Do you have any tips and tricks around, besides spinning up sub-agents, how could people listening to this, if they want to go after this opportunity of

essentially verticalize open clause and automating some of these flows, how could people actually take their open clause from a bad employee to a good employee?

Yeah, absolutely.

This is always such a magical experience, just watching a computer navigate the web like a human being.

Um, well, just, you know, sort of a thing I was thinking about is it sounds like when, whenever you're trying to, you know, do a new automation, you start by thinking about what is a lightweight skill that I should create.