Because Capital One operates deeply embedded within the banking industry's model risk framework, its platform bakes in risk and compliance as policies, guardrails, and security/cyber enforcement across every layer and thread boundary of its agentic systems.

10:12stacks that is necessary for to build robust scalable enterprise systems. At the same time, we are deeply embedded within the model risk framework that the banking industry gives you. So, this means that we we have a very very robust model risk office that we work very very closely with. We have all of the risk and compliance uh frameworks embedded within the platform, which appear as policies, as guardrails,

10:40as security enforcement, cyber enforcements across our different layers of the platform that get implemented across different thread boundaries uh of the agents. And so, that that speaks to um a couple of things for me. One is that, you know, whatever platform you're deploying these agents on, you know, has you know, regulatory aspects to it. Um are the agents themselves like enforcing regulation, you know, relative to the the platform or as distinct to

11:17from the platform? So, there are two aspects to what you're saying, right? So, one is the building of the agents and the one is the runtime execution of the agents. These platforms come into the fore when you are governing agents in runtime. And that's where the massive huge benefit of platforms comes into the into the fore. This gives the architects of that specific agentic um uh framework the flexibility of focusing

11:45deeply on the design, whereas the platform being brings in all of the governance and risk compliance that is uh that needs to be bounded to make these agents execute safely in in in any environment. The second aspect that the first aspect that you spoke about is the agent development in and of itself. Can the agents themselves bring in governance? Yes, for the specific domains, absolutely. Right? Uh so, you can you can definitely