すべてのプロジェクト

jev-serp-opportunity-lab

suprkco/jev-serp-opportunity-lab

Terminal-based Jev intent triage with typed decisions, explicit simulation mode, review policy and JSON exports.

Python
スター
0
フォーク
0

掲載理由

Jev の判断とコード側の振り分けを分離する検索意図分類。API 接続とオフライン方針シミュレーターを備え、付属 SERP 例は作成済みテストデータ。

関連プロジェクト

  • jev-benchmarks

    Probability-aware evaluation for typed decision models: calibration, selective risk, latency, and reproducible benchmarks.

    共通トピック: evaluation

  • jev-access-day

    A learning scaffold for TypeSafe AI's System One models: eval harness plus a measured, plain-language comparison of the Jev decision model vs an LLM stand-in on 24 real operational decisions. All numbers reproducible from committed run files.

    共通トピック: evaluation

  • no-hallucination

    Three measured experiments on RAG hallucination: quote-checking, TypeSafe's Jev, and IBM's STAIR. 850+ graded questions, raw responses included.

    共通トピック: evaluation