Guardrails
Real-time firewall rules that detect and redact secrets, PII, and toxic content in inbound prompts
SUPERWISE® Sentinel operates natively at the edge, parsing every inbound prompt in real time before it reaches the upstream provider. If a prompt violates your organizational compliance policy, the Sentinel intervenes immediately — redacting the offending content so sensitive data never leaves your perimeter and malicious inputs never reach upstream models.
In the current release, all guardrails run on inbound prompts and redact matched content in place with a
{{REDACTED}}placeholder.
Available guardrails
- Secret & credential detection — redact API keys, cloud credentials, and private tokens before they reach the model.
- PII redaction — redact emails, phone numbers, SSNs, and credit card numbers.
- Rudeness & toxicity — redact profanity, hostile language, and harassment.
Updated 14 days ago
Did this page help you?