Chat Concierge, a multi-agentic auto-dealership chat application with a human in the loop, was Capital One's beachhead project for deploying multi-agent systems, designed to seamlessly match customers to the right car and initiate follow-up actions like scheduling test drives.

6:05deployed out to our auto dealers to basically bridge that experience between dealers and their customers and make it very seamless. So, this is an auto buying experience that we wanted to make sure that we deliver the right right solutions or cars to the right customer needs. So, it was a multi-agentic chat experience that was brought to the fore with a human in the loop to our dealer customers,

6:35car buying customers to get get the right match between the car that they need to buy. And and we need to understand we're moving to a world where the car buying experience doesn't start at the dealership. It starts before. It starts when they go to their website and try to figure out, okay, what's the inventory? What are What does this dealership looks like? And that's where the chat

6:58experience where the customer experience begins. It's at this juncture that we wanted to make this experience very seamless that, you know, okay, you you figure out based on your family needs, your demographic needs, your specific personalized needs, what is that car that fits your match matches your specific intent. And then the subsequent actions can be generated, scheduling a test drive, etc. And how did it start with the Did you

7:28know that you would end up doing multi-agentic at the beginning of this project or did that approach evolve? Yes. So, that's a very good question. So, most of the times, I mean, when we are trying to think about the right tool for the right problem, we need to understand the complexity of the scenario and the use case that we need to determine. So, we we go in with multi-agentic