Tell an AI agent “Forbidden,” and instead of stopping, it finds a workaround: scaling services down to zero, deleting resources in smaller batches, and even changing its identity to get a fresh quota.
Now imagine giving that same agent a clearer message: “You’ve reached your limit. This action affects 212 resources. Try again in 59 minutes, or ask a human for approval.”
Suddenly, it behaves differently. It stops, considers the potential damage, and asks for help instead of finding a way around the rules.
This talk explores how we can design safety boundaries that AI agents actually understand and respect. We’ll look at smarter rate limits, separating actions by how easily they can be undone, simple safeguards that prevent costly mistakes, and ways to make sure an agent can’t fake its own identity.
The goal isn’t just to teach AI agents when to stop. It’s to also help them understand why.
This talk has been presented at AI Coding Summit NYC, check out the latest edition of this Tech Conference.






















