Runtime AI Security

Securing AI by reading internal beliefs, not external inputs

Krnel's solution actively monitors your agents' thinking for signs of compromise.

About Us

We are veteran AI and observability experts, passionate about understanding and securing AI models. We've seen and been part of the growth of AI from small conference rooms to what is today.

Peyman Faratin

Peyman Faratin (PhD)

Expert in multi-agent systems with 35 years of AI experience.

Kimberly Wilber

Kimberly Wilber (PhD)

Research engineer with a computer vision background.

Latest News

Stay updated with our latest announcements and milestones.

We are now part of Nvidia's Inception Network

Krnel.ai joins Nvidia's Inception program to accelerate AI security innovation

Latest Research

Check out our latest research findings and insights on AI security.

Surveying the Precision-Recall Gap in LLM Security

Not all guardrails are created equal.

Into the Kernel: Decoding AI’s Hidden Mind

Model Internals Is All You Need

Join Our Waitlist

Be the first to know about our latest research findings and updates