How oss-safeguard uses Policy Prompts

How oss-safeguard uses Policy Prompts

oss-safeguard is designed to use your written policy as its governing logic. While most models provide a confidence score based on the features it was trained on and require retraining for any policy changes, oss-safeguard makes decisions backed by reasoning within the boundaries of a provided taxonomy. This feature lets T\&S teams deploy oss-safeguard as a policy-aligned reasoning layer within existing moderation or compliance systems. This also means that you can update or test new policies instantly without retraining the entire model.