Securing autonomous AI agents: regulatory risk and governance for modern AppSec

Autonomous AI agents writing and executing code at machine speed present an urgent compliance challenge for modern software organizations. As global regulations tighten, engineering leaders must establish clear governance layers over agentic workflows, external tool calls, and Model Context Protocol integrations to ensure full accountability.

In this session, Mend.io experts Asaf Saar and Ben Goldberg unpack the intersection of AI compliance, software supply chain security, and enterprise risk management. Learn how to bridge the accountability gap without sacrificing development velocity.

Timestamps:

00:04 - Introduction and Speaker Overview

02:09 - Defining AI Agents

03:22 - Market Patterns: Adoption vs. Governance

06:06 - Shift in Responsibility and Content Ownership

09:08 - AI Regulation and Framework Landscape

11:27 - Real-World Impact and Safety Considerations

13:58 - Accountability Failures and AI Security Incidents

16:28 - Compliance Failures in Action

20:34 - Frontier Lab Breaches and Agent Autonomy

23:02 - Environmental Visibility and Sub-Agent Proliferation

26:56 - Runtime Security vs. Traditional Application Security

29:43 - Organizational Ownership and Hot Potato Risk

34:04 - Model Governance vs. Agent Accountability Questions

37:20 - Essential Evidence for Auditors

38:58 - 30-Day and Quarterly Recommendations to Get Started

41:01 - FAQ: Mapping In-House Agents and Discovery

43:26 - FAQ: Agent Identity and Identity Aliases

46:37 - Closing Remarks

Watch the full webcast on-demand: https://www.brighttalk.com/webcast/15811/673202

Learn more about securing AI-native software at https://www.mend.io/