Human-on-the-Loop: The New AI Control Model That Actually Works

Your AI agents are growing up. It’s time your control model did, too.

Over the past two years, much of the AI conversation has focused on risk, and rightly so — jailbreaks, data leakage, and unintended actions. I’ve been the captain of Team Caution since the original publication of the OWASP Top 10 for LLMs, dating back to mid-2023.

The question is no longer “is AI risky?” but “how do we scale AI safely?”

AI agents have matured, and the use cases are broadening. AI reasoning is improving fast. They’re writing code, triaging…