jev-resume-screening

screens one resume against a JD in a single request of five Noul evidence gates, four Score dimensions, and one background-routing Choice, with criteria hardened v1→v3 against negative-control resumes (a glossy-trap CV's self-described "AI heavy user" fell 0.95→0.49) and any low-confidence answer escalated to human review.

SCORE 호출은 이렇게 생겼다

이 질문 유형의 일반적인 뼈대이지 이 프로젝트의 실제 코드가 아니다.

from typesafe import TypeSafe

ts = TypeSafe()
result = ts.evaluate(
    state=candidate,
    questions={
        "relevance": {
            "type": "score",
            "levels": ["low", "medium", "high"],
            "instructions": "How relevant is this to the query?",
        }
    },
)
if result["relevance"] >= 0.7:
    keep(candidate)