Automatically detects and obfuscates sensitive data (PII, secrets, etc.) before Claude processes it, with lossless restoration for client deliverables.
PII sanitization layer for autonomous AI agent pipelines. Detects and redacts emails, phone numbers, national IDs, private keys, and financial data before text reaches LLMs. Supports EN, ES (LATAM), PT (BR/PT), DE, JA.
Screens text for PHI/PII, classifies it, redacts sensitive content, and routes it to approved model tiers based on a declarative policy, with built-in evaluation metrics.