Jev AI

Abide

reads every edit a coding agent makes and has Jev flag rule violations, with the project reporting that an independent reviewer confirmed 10 of the 39 flagged edits and 11 of the 15 flagged turns.

作者
coldteadotai
分野
Agent supervision
カテゴリ
検証とガードレール
種別
REPO
ホスト
github.com
GITHUB で見る

何を判断するか

CHOICE

Picks one option from a fixed set

SCORE

Rates against ordered levels

NOUL

Answers a yes / no question

Inferred from this project's own one-line summary in the community list — it reads as a NOUL decision. Read the source to confirm.

NOUL 呼び出しの形

この質問型の一般的な骨格であって、このプロジェクトの実際のコードではない。

from typesafe import TypeSafe

ts = TypeSafe()
result = ts.evaluate(
    state=tool_call,
    questions={
        "is_risky": {
            "type": "noul",
            "instructions": "Could this call delete or overwrite user data?",
        }
    },
)
if result["is_risky"] and result["is_risky_confidence"] > 0.6:
    escalate_to_human(tool_call)
検証とガードレールの他のプロジェクト