classification

What problem does it solve?

Moderation teams need to quickly categorize flagged content by violation type and urgency to route items to the right reviewers and apply appropriate SLAs.

Core Features & Use Cases

• Primary categories: hate speech, violence, adult content, spam, misinformation, PII exposure, copyright
• Severity assessment: assigns a hierarchy (Critical/High/Medium/Low) and suggests queue priority
• Context-aware routing: factors user history, content type, reach, and immediacy to influence decisions
• Output structure: provides category, severity, confidence, context factors, risk assessment, and queue priority for downstream systems

Quick Start

Provide a sample flagged content payload to classify and receive a structured result.