AI Security

Session AI Agentic Security

Your Newest Employee Has Sudo Access: Blueprints to Stop AI Insider Threats

Monday Jun 1 / 10:20AM EDT

Deploying a tool-calling agent is effectively onboarding a new employee who operates at a million actions per minute with database access and zero concept of consequences.

Speaker image - Adrianna Valle

Adrianna Valle

Product Security Engineer @Klaviyo, Author of "Engineering Secure Agentic Systems at Scale", Specializing in the Intersection of Quantitative Data Models and Autonomous System Security

Session AI Security

Zero Trust Agent Systems that Pass Audits and Still Ship

Monday Jun 1 / 10:20AM EDT

Most agentic AI demos assume a greenfield environment. In a real enterprise, agents run inside strict boundaries where security, compliance, and incident response are non-negotiable.

Speaker image - Advait Patel

Advait Patel

Senior Site Reliability Engineer (DevSecOps + Cloud + AIOps) @Broadcom, Creator of DockSec, Docker Captain, and IEEE Senior Member