Getting Started
AI Runtime Protection is the live monitoring and enforcement layer for your deployed AI systems. It extends the SPLX Platform by enabling you to define, activate, and manage runtime protection policies that detect misuse or policy violations as they occur, helping you maintain security, safety, compliance, and trust in production.
The SPLX Platform acts as the control plane, where you define and manage policies, while the AI Runtime Protection service is the runtime enforcement layer that evaluates your AI system’s input and output messages.
To use AI Runtime Protection:
Create and connect an AI Runtime Protection - First, create a AI Runtime Policy in the SPLX Platform and get the AI Runtime Policy ID. - Then, connect to the AI Runtime Protection service.
Define protection policy - Within the platform’s UI, specify the policy you want enforced for both inputs and outputs. - You can prevent system-prompt leakage, block jailbreak attempts, flag PII exposure, and protect against a variety of other vulnerabilities.
Monitor real-time results - Through the UI, use live dashboards & tables to observe how messages are being evaluated. - See both flagged and allowed messages, metrics on violations, and runtime behavior.
Review & iterate policy - Track effectiveness and update your AI Runtime Policy in response to new threat patterns or usage behavior.
Last updated