Nadav Cornberg (Eve Security): Interrogating Agents Before They Act
From The Road to Accountable AI by Kevin Werbach
June 11, 2026 · 33 min · Season 5 · Episode 14
About this episode
Kevin Werbach speaks with Nadav Cornberg about securing agentic AI through an interrogation approach that questions agents before they act.
Kevin Werbach speaks with Nadav Cornberg, co-founder and CEO of Eve Security, about securing agentic AI where it counts: at the moment an agent actually does something. He recounts how customers upended his own assumptions that AI agent security should focus on visibility and after-the-fact detection. Buyers insisted on runtime enforcement first, reasoning that learning a production database was deleted after the fact helps no one. With Eve's "interrogation" approach, when an agent attempts an anomalous, high-risk action, Eve's agent-in-the-loop pauses and questions it about its intent, before approving, blocking, or escalating to a human. Cornberg describes building a deterministic enforcement layer on top of inherently non-deterministic models, with the system minting explicit rules from observed behavior so that the large majority of everyday requests resolve deterministically. Ultimately, the consequenes are the same whether an unintended action originates in a prompt injection or a simple hallucination. On the perennial human-in-the-loop question, Cornberg argues that escalating everything would drown security teams as the agentic workforce scales, so the platform…
People in this episode
Host: Kevin Werbach
Guest: Nadav Cornberg
Topics covered
- agentic AI
- AI security
- runtime enforcement
- human-in-the-loop
- deterministic models
Keywords
- AI security
- runtime enforcement
- agentic AI
- deterministic models
- human-in-the-loop
Mentioned in this episode
Organizations: Eve Security
More episodes of The Road to Accountable AI
- Venkat Siva (Compfly): Governing Agents at the Execution Boundary · June 4, 2026 · 33 min
- Munmun De Choudhury (Georgia Tech): Conversational AI and Mental Health · May 28, 2026 · 32 min
- Emre Kazim (Holistic AI): Why AI Governance is Life Cybersecurity · May 21, 2026 · 33 min
- Rumman Chowdhury (Humane Intelligence): The Need for Discernment · May 14, 2026 · 36 min
- Var Shankar: AI Governance for Smaller Organizations · May 7, 2026 · 29 min
- Katie Fowler (Thomson Reuters Foundation): How 3,000 Companies Approach AI Governance · April 30, 2026 · 38 min
Explore listener stats, chart rankings, contacts and more on the The Road to Accountable AI podcast page.