Veer Yedlapalli

Veer Yedlapalli

Director of Product Security, Security Engineering and AI Security Grainger
Veer Yedlapalli

Responsible AI Summit North America: Day 1 - Tuesday, June 23, 2026

12:30 PM Panel Discussion – Agentic AI Compliance and Risk Management: Strategic Approaches

As autonomous AI agents proliferate across teams and platforms, organizations face growing challenges in ensuring compliance and mitigating operational and regulatory risk. This session explores strategic and technical approaches for discovering active agents, maintaining accurate inventories, and enforcing governance and risk controls.

• Strategically discovering agents across distributed environments.

• Maintaining comprehensive inventories.

• Implementing governance and risk controls without disrupting workflows.


Responsible AI Summit North America: Day 2 - Wednesday, June 24, 2026

11:40 AM Presentation – Actionable Security for Agentic AI: Securing Clients, Servers, MCPs, and Human-in-the-Loop to Prevent Cascading Risks

The rapid evolution of agentic AI, from single LLM-powered agents to coordinated crews and massive swarms, promises transformative autonomy in domains like supply chain, healthcare, and finance. Frameworks like CrewAI, LangGraph, and Google's ADK, combined with the Model Context Protocol (MCP) standard, enable dynamic agent-to-agent (A2A) collaboration and tool access. Yet this interconnected ecosystem introduces severe cascading risks: a single compromised agent can poison swarms via unsecured MCP calls, leading to data exfiltration, unauthorized actions, or ethical failures.

This technical talk delivers an actionable blueprint for end-to-end security across agentic AI layers, including client-side (agents/swarms), server-side (MCP servers/orchestrators), communications, and Human-in-the-Loop (HITL) integration. Drawing from production deployments and red-team exercises, Veer explore why layered defenses are essential for compliance (EU AI Act, DORA) and trustworthiness.
• One compromised agent can compromise the entire swarm.
• Secure MCPs are critical to preventing cascading failures.
• Layered defenses enable compliance, resilience, and trust.

Check out the incredible speaker line-up to see who will be joining Veer.

Download The Latest Agenda