Bryan McAnulty

And then I let it do it and just walk away and see what happens.

And I also didn't have to write the 20 pages, right?

So I was communicating with AI, kind of having it interview me to understand what we actually need to accomplish here.

Then it wrote the 20 pages of its own implementation.

And I said, that looks good.

Let's go for it.

But I think the founders out there need to be thinking for themselves and for how they have their teamwork in the future is designing these processes that you can delegate.

And I'm very happy to see that the last couple days on X, people are talking about loops and that the future of working with these agents is you're designing loops that are going to be running for you in your business.

And that's great for me because our coding agent is called LatchLoop.

Hopefully that sticks around.

But the phrase sticks around and people can hook onto it there.

But yeah, I think figuring out where you can design these broader goals that you want to like distribute the attention to.

So you can have AI working on these kind of bigger picture things that you may have not even considered before.

Yeah, because I remember I was talking with, I went to OpenAI Dev Day last year and I went to the separate event of like devs talking at this event

like other people building these AI agents.

And I described the name latch loop of our coding agent to them, and they didn't understand what it was either.

But the idea to me is that when in programming, if you have a loop, it's saying like, okay, while this thing is true, like continue and repeat.

And so what developers found out is you have a tool like ChatGPT and you can send a message, it sends a response.

But if you want to keep working, you have to have a way for it to continue in a loop and work on something.

And so these kind of coding agent tools that we see, what they're doing is we're giving them a goal and then we allow the agent to continue working.