Inspiration can come from different places, yet for architecting and designing agentic techniques.
At VB Transform, Capital One explained how it built its agentic program for its automobile company. Milind Naphade, SVP of Technology and Head of AI Foundations at Capital One, said during VB Transform that the company wanted its officials to work similarly to mortal agents, in that they problem-solve alongside clients.
Naphade said Capital One began designing its agentic products 15 months earlier, “before agentic became a phrase. ” For Capital One, it was important that, in building its representative systems, they learn from how their people agencies ask clients for information to identify their issues.
Capital One even looked to another cause of organizational structure for its agencies: itself.
“We took inspiration from how Capital One itself functions, ” Naphade said. “Within Capital One, as I’m certain within other financial services, you have to control danger, and then there are other companies that you also observe, review, issue and assessment. ”
> > See all our Transform 2025 cover these < <
This same composition applies to brokers that Capital One wants to check. They created an adviser that evaluates existing agencies, which was trained on Capital One’s laws and requirements. This appraiser agent can push back the procedure if it detects a concern. Naphade said to think of it as “a team of experts where each of them has a unique experience and comes up to resolve a problem. ”
Financial services organizations recognize the potential of agents to give their human agents with details to handle customer issues, handle customer service, and get more people to their products. Other banks like BNY have deployed agents this year.
Auto dealership agents
Capital One deployed agents to its auto business to assist the bank’s dealership clients in helping their customers find the right car and car loan. Consumers can look at the vehicle inventories of dealerships that are ready for test drives. Naphade said their dealership customers reported a 55 % improvement in metrics such as engagement and serious sales leads.
“They’re able to generate much better serious leads through this more conversational, natural conversation, ” he said. “They can have 24/7 agents working, and if the car breaks down at midnight, the chat is there for you. ”
Naphade said Capital One would love to bring this type of agent to its travel business, especially for its customer-facing engagements. Capital One, which opened a new lounge in New York’s JFK Airport, offers a very popular credit card for travel points. However, Naphade pointed out that the bank needs to conduct extensive internal testing.
Data and models for bank agents
Like many enterprises, Capital One has a lot of data for its AI systems, but it has to figure out the best way to bring that context to its agents. It also has to experiment with the best model architecture for its agents.
Naphade and Capital One’s team of applied researchers, engineers and data scientists used methods like model distillation for more efficient architectures.
“The understanding agent is the bulk of our cost because that ’s the one that has to disambiguate, ” he said. “It’s a bigger model, so we try to distribute it down and get a lot of bang for our buck. Then there’s also multi-token prediction and aggregated pre-fill, a lot of interesting ways we can optimize this. ”
In terms of data, Naphade said his team had undergone several “iterations of experimentation, testing, evaluation, human in the loop and all the right guardrails” before releasing its AI applications.
“ But one of the biggest challenges we faced was that we did n’t have any precedents. We could n’t go and say, oh somebody else did it this way, so we could n’t ask how it worked out for them? ” Naphade said.
Editor’s Note: As a thank-you to our readers, we’ve opened up early bird registration for VB Transform 2026— just$ 200. This is where AI ambition meets operational reality, and you’re going to want to be in the room. Reserve your spot now.