How Capital One Evaluates and Governs Its AI Agents

Published October 9, 2026
Larry Dignan
Editor in Chief of Constellation Insights

Executive Summary

Capital One recently outlined how it evaluates and governs AI agents in production at scale. Speaking at CoreWeave Fully Connected 2026, Maulin Patel, managing vice president of product, AI, and ML platforms at Capital One, described the company’s agent evaluation processes in a regulated environment for AI agents and large language models (LLMs).

“Our subject matter experts audit complex financial logic and calibrate our automated LLM channels. This architecture works really well for us for single LLMs and communications. However, autonomous mobile agents introduce an entirely new set of players,” Patel said.

Capital One’s approach to technology comes from the top. Capital One is a bank that sees its technology stack as its differentiator. The company is using its technology platform to integrate acquisitions, most recently the purchase of Discover; create efficiencies; and drive growth, Capital One CEO RichardFairbank said at a recent investor conference.

Membership required to view

Already a member?
--- OR ---
Purchase this single report
$2,350.00