Thanks for listening to the Bank Talk podcast.

Yeah, I'd be happy to do that.

So I would say we see it in a variety of different functions and divisions within each of our clients.

And I might start with the back office.

We're trying to accelerate the work that the bank is already doing, okay? And there may be a day when we're automating that work, but we're not there today.

That's too risky, and we're not going to automate it.

But can we accelerate it? Can we give the people that work at the bank power tools instead of hand tools to do this work? And so a good example of that is with exception item processing.

What else? Give me another

Talk a bit about the team you're building and, and, and training to be able to deliver the value you're beginning to describe.

Yeah.

So, you know, this is a, a really fascinating area.

And, you know, before I was at Jack Henry, I was at Equifax, and data science is the name of the game at Equifax.

I really learned most of what I know from there.

Um, and so the idea is you have machine learning models, and if... and you can-- and these models try a million different parameters, and they train themselves a little bit like neural networks, but it's, it's a similar terminology, but it's not the same process.

But they will try a hundred different or a thousand different permutations of trying to calculate the probabilities of something happening, and then you use that to then predict.

But talk a bit about the, you know, some of these use cases that have been so encouraging and, as you point out, that steady trickle of, of success begetting more enthusiasm and, and experimentation that leads to these ideas.