CalibratedDecisions.

Repo · Search & RAG

jev-judge-rank

Three standard-library Python scripts (and an agent skill) that use TypeSafe Jev to rank a list on several written criteria, merge near-duplicates…

Open github.com ↗

From the repository

Rank a list on several criteria, merge near-duplicates, and recall relevant entries with Jev (TypeSafe System One). Python, stdlib only.

How builders describe it

Three standard-library Python scripts (and an agent skill) that use TypeSafe Jev to rank a list on several written criteria, merge near-duplicates under one representative, and recall the corpus entries that help with a one-sentence situation; every request and response is logged locally, with a…

The decision Jev makes

Rank candidates against a query, or answer whether a passage is relevant.

Where it fits

Search pipelines retrieve too much. These projects use Jev as a reranker or relevance check after the first search, so only useful results reach the user or the model. All 108 search & rag projects →

Related projects