OpenAI describes Private Safety Processing for API safety reviews

OpenAI says its Private Safety Processing lets it review related API requests for safety without retaining users' prompts or responses.

According to OpenAI Developers, the records stay in the customer's environment, where an automated safety agent reviews them without OpenAI personnel accessing the content.

OpenAI Developers also published a guide on the feature and on connecting cloud storage, linking to the API documentation. The post gives no further details beyond that link.