Moderation

The process of detecting, blocking, or modifying content that violates safety policies, compliance requirements, or application rules.

A mechanism designed to detect and block toxic, harmful, or policy-violating content in model inputs and outputs.

The process of verifying and sanitizing user inputs or external data before they are processed by an AI system to ensure they conform to expected formats, constraints, and security policies, helping prevent errors, misuse, prompt injection, and malicious inputs.

The process of filtering or removing sensitive, unsafe, or non-compliant content from model outputs before they reach users.