Use cases· Last updated 2026-09-21

Guardrails policy checks

A policy check is a typed question whose instructions + criteria are your rules (“refunds over $50 need a manager,” “do not quote medical dosage”). Jev scores compliance; code enforces it. This is the second layer after the Noul screen.

Unofficial. Official “how to build”: keep deterministic rules in code when you can; use System One for common-sense over unstructured text. We do not certify GDPR/HIPAA. No keys sold.

Pattern

1. Put policy text and the artifact (draft reply, tool args) in structured state.
2. One Noul per atomic rule: “Does draft violate policy.refund_cap given order.total?”
3. AND/OR in code. Do not hide five rules in one vague Score.
4. Money and dates: extract numbers in code; ask Jev only about the semantic remainder (jaggedness).

violations = [
    name for name, noul in answers.items()
    if noul.noul >= T_VIOLATION
]
if violations:
    return review(violations)

Use-case map “Universal Verification” also lists citation errors, tool-call mistakes, and response-quality failures — same shape, different instructions.

Honest limits

• Policy text in state can itself be attacked (injected “ignore the policy”).
• A Noul of 0.01 is not a legal opinion.
• If a regex can enforce the rule, skip Jev.

Hub: Use cases. Sibling: guardrail glossary. Official: docs.typesafe.ai.