Cobus Greyling

Use TypeSafe Jev for typed judgments (Choice, Score, Noul) instead of asking a chat model to classify. Pair with a generative model for prose. Use when classifying, routing, scoring, guardrailing, or the user runs /jev.

Ask every independent TypeSafe Jev question in one POST /v1/systemone (speculative fan-out). Use for parallel questions, smart-home or compound commands, one-call turn assessment, or when the user runs /jev-fanout. Do not fire one HTTP call per question.

Screen LLM input and output with TypeSafe Jev Noul hazard batteries plus a harm Score; policy in code returns pass, review, or block. Use for jailbreak, prompt injection, secret leak, denylist pressure, or when the user runs /jev-guardrail or `npx jev guard`.

Route with TypeSafe Jev — map Choice plus confidence to act/confirm/human, or pick a coding-agent model tier. Use for confidence routing, model routing, cheap vs frontier, loop-jev, or when the user runs /jev-route or `npx jev route`.