Why AI Control is the New Security Standard

This episode explores rapid enterprise AI adoption and why visibility into “shadow AI” and runtime control are essential to a robust AI control plane. Learn how organizations can securely steer thousands of agents while maintaining the low latency and high accuracy required in production environments.

Key Takeaways:

The critical shift from standard cybersecurity frameworks to AI control and alignment
How to utilize synthetic data pipelines to train high-accuracy, low-latency security models
Strategies for managing "shadow AI" across the cloud, browser, and no-code tools
The impact of the exponential growth in agent-to-agent communication on organizational security
Why the "human in the loop" remains the ultimate guardrail for agentic governance

Gil Elbaz is the Cofounder and Chief AI Officer at Onyx Security, where he focuses on the intersection of artificial intelligence and enterprise security. With over 15 years of experience in the machine learning field, he previously served as an AI Architect within the NVIDIA CTO office, working directly on LLM deployment strategies and distributed training for global enterprises. His technical background also includes a five-year tenure as the CTO of Datagen, a role in which he built foundational synthetic data infrastructure. Throughout his career, he has specialized in developing robust machine learning systems for high-stakes environments where accuracy and production-level reliability are critical requirements.

Episode resources

Gil Elbaz on LinkedIn
Gil Elbaz Website: https://www.onyx.security/
Itamar Friedman on LinkedIn
Qodo Website