Pause Before You Prompt: NY Court Finds AI-Generated Content Is Not Privileged

In what appears to be a first of its kind ruling, a federal district judge (Hon. Jed S. Rakoff, Southern District of New York) on February 17, 2026 held that AI-generated information, that relied on privileged inputs, is not protected by attorney-client or work product privilege.

Among other factors, the Court considered the AI tools' privacy policy which allowed disclosure of user inputs and outputs to "government regulatory authorities" and to other "third parties" in certain situations. Interestingly, these terms may exist even in enterprise versions of AI tools.

While the ruling relates to highly nuanced facts and should be read narrowly, it highlights risks that should be considered by organizations wishing to protect confidential information while increasingly relying on AI to work smarter.