Kavak builds one long-running agent per customer with its own VM, full memory of all interactions, and a hard goal to maximize that customer's lifetime value.

3:46um agent will get spawned specifically for this customer with its own virtual machine. It'll remember years of interaction of this customers with with Cabal, what they visited in the web page or call they had 2 years ago. Remember everything like in its memory, come up with a strategy and set a long-term goal to maximize the lifetime value of this customer and do whatever it takes to make the customer happy and

4:14convert them into like all our different products like across time. And this is a completely new and groundbreaking architecture at scale, I think, because like people are still building multi-agent system with with experts and and we realized too bad that long-running agents with hard goals, not just workflows, could could maximize our our customers satisfaction and obviously their their lifetime value. >> Awesome. Okay, so we're going to jump to

4:46the nuances that but maybe versus many companies that say, "Hey, we want to be agentic." And they try some workflows. >> Yes. >> You guys took the just rip like we had to make this work. You had to downsize dramatically. It didn't work for a year. >> Right. >> So, do you want to talk through obviously you had to tune a lot of things to make that work.

5:07Like describe the harness at that time and like what models you were using and sort of specifically. Yeah. >> So so there there were like three main decisions that that we had to make. The first and this is what where I think many companies are stuck right now is the first instinct is, "Okay, let's adopt AI." And you you basically leave your structure as it is and just give