Microsoft-backed (MSFT) OpenAI is previewing Private Safety Processing, a system designed to detect misuse patterns across multiple interactions while remaining compatible with its Zero Data Retention offering, the artificial intelligence firm said Wednesday.

The system extends existing safety checks to identify patterns across related sessions without giving OpenAI personnel access to underlying customer content, which remains encrypted or on customer-controlled infrastructure, the company said.

When risks are flagged, OpenAI receives only a narrow signal about the activity type, not the content itself, the company said, adding that the system is being tested with early customers, with a broader rollout and technical white paper planned for September.

Price: 483.76, Change: +2.13, Percent Change: +0.44