Securing AI Agents from the Ground Up - Luke Hinds

Users were getting hacked by their own AI agents. So Luke Hinds built `nono`—a simple tool to sandbox them and prevent system compromise.

#1about 4 minutes

Why open source is the best model for security software

Open source provides transparency for code reviews, fosters collaboration with diverse experts, and prevents vendor lock-in for businesses.

#2about 6 minutes

Navigating security risks in the current AI gold rush

The rapid pace of AI development often pushes security to a lower priority, creating risks as non-technical users are given powerful, low-level system access.

#3about 5 minutes

Understanding the practical challenges of agentic AI

Agentic AI is in an exploratory phase where it is often misapplied to problems that have simpler, more traditional solutions.

#4about 9 minutes

Introducing nono for secure AI agent sandboxing

The nono project provides a simple, easy-to-use sandbox that uses kernel-level security to isolate AI agents and prevent unauthorized system access.

#5about 11 minutes

A live demo of nono's core security features

This demonstration shows how to use nono from the command line to restrict file access, protect credentials with phantom keys, and roll back unwanted changes made by an agent.

#6about 5 minutes