Skip to content

Topic: observability

Podcast episode
1 podcast episode

In Artificial Intelligence and Computer Science

Podcast episode · Machine Learning

Why AI Agents Break the GenAI Security Model with Devvret Rishi

The TWIML AI Podcast

Jun 16, 2026

Devvret Rishi discusses how agents with access to tools and external systems change the security requirements of generative AI applications. He examines the limitations of static controls and the need for runtime policies, observability and recovery mechanisms as agent workflows become more capable.

We use cookies for analytics.