So what are some of the measures that you use? And maybe Brian, we'll start with you.

yeah so corey i mean the success that we're really looking at this area is our you know time to handle the call resolutions um because the duration of the call you you're gonna be in the past we look at the baseline of talking to this 17 step call usually takes about six minutes plus call to handle our members uh uh questions uh or or situations and after we introduce an AI, we're able to see the call reduce down dramatically, right? Not a six minute, not a seven minute, not eight minutes.

It's actually moving into And I was about two to three minutes call and you see almost, you know, a huge amount of time to drop.

What that means is hours agents on the contest center is able to serve more members instead of them waiting on, on, on the phone line and listen to those beautiful music, uh, and put them to sleep.

Right.

So, and this is one of the thing that we, we really looking at.

Um, and the second thing is we also measured by, you know, the NPS, right.

but kind of rewinding to the start of the journey that you took Stanford on and Stanford has been on in terms of the adoption of AI, what would you do differently if you could start over? And what are some of the lessons that you learned the hard way that you wish you knew to make sure that you didn't have to go through the pain that can follow implementing AI in maybe less than ideal ways?