Guardrails for LLMs

Screen every inbound and outbound message for hazards and harm.

Guardrails
Result
Hazard probabilities and a harm score per message

A system prompt is the first thing a jailbreak talks past. A second LLM costs a full call and can be talked past too.

This Jev guardrail use case puts the rules in questions you can read, version, and threshold.

Probabilities stay visible, so a reviewer can see why a message was blocked.

Pipeline

  1. Describe each hazard as a Noul question
  2. Score how much harm complying would do
  3. Threshold probabilities in code
  4. Pass, review, block, or route to support

Builder: TypeSafe cookbook. Stack: jev.