Building Safe Agents for Business - #NYTechWeek
AI agents are moving from demos to production. They execute payments, write code, access sensitive data, and ship decisions to clients without a human in the loop.
The safety infrastructure has not kept up, and this workshop is focused on fixing that.
Today's guardrails are assertions, not proofs. They only work most of the time, fail silently in the cases that matter, and can be hijacked by a single line of injected text. Every public agent incident ends with the same question: how do you prove the agent followed the rule?
We'll learn how missing layer is cryptographic guarantees, not better prompts or more filters: mathematical proof that an agent action complies with your policy before it runs.
This workshop teaches you how to easily build formal verification of agent policy before each action; defenses that survive prompt injection; and portable receipts your security team, counterparty and your auditor can easily verify.
Hands-on and accessible to all - we hope to see you there!
This event is a part of #NYTechWeek—a week of events hosted by VCs and startups to bring together the tech ecosystem. Learn more at www.tech-week.com.
Guest List
´◡`
:)
◔◟◔
