LLM guardrails with Jev
TypeSafe’s guardrails cookbook: put semantic checks on inputs, outputs, and tool calls at a fraction of the cost of the LLM call you wrap (their cost framing — confirm current list price on the models page). This unofficial page adds a two-layer pack and limits. Not a security product claim. No keys from jev.pro.
Layer A — Noul screen
Jailbreak / injection, PII, harm Score. Details: decision workflow.
Layer B — policy checks
One Noul per written rule; AND in code. Details: policy checks.
Typical questions (you write criteria):
- Noul: jailbreak or prompt-injection?
- Noul: sensitive personal data?
- Score: harm if we comply?
- Choice: allow / review / block — or keep those outcomes in code
You decide thresholds. Log structured results.
The use-case map also lists jailbreak detection, citation errors, tool-call mistakes, and response-quality failures under Universal Verification.
LangChain’s AutoModeMiddleware checks risky tool calls before execution — LangChain harness. Those APIs are LangChain’s.
Honest limits
Jev is not a generative safety filter that rewrites the user. It will not sandbox bash. Official jaggedness: adversarial content can steer jev-1.13. If you need a refusal message, another model (or a template) writes it.
Hub: Use cases. Official: docs.typesafe.ai.
Sources
Public TypeSafe or adjacent documentation only. No private claims.