Small decisions. Interesting possibilities.Submit contentSubmit
Jev Search preview

Jev Search

A web-search application uses Jev to choose sources, time ranges and search terms, then rank returned links and snippets.

Added to Jevfast

How it uses Jev

Jev receives the trimmed request, current date, and generated query candidates. It chooses a time window and candidate query/entity, and returns Noul probabilities for source relevance; code applies explicit filters and thresholds before running searches.

What Jev decides

Source relevanceExample answers · not a recorded Jev response · Source ↗
Question 1 · source <id>
YOUR APP
INSTRUCTION

About the request: does it satisfy the selected source’s exact inclusion question?

STATE

The user request, current date, and generated candidate search terms.

JEV · NOUL
YesNo

App workflow

  1. Collect request

    Trim the query and generate candidate search terms; retain optional user-specified time and source filters.

  2. Infer intent

    Ask Jev about recency, source relevance, and candidate query/entity representations.

  3. Choose search lanes

    Apply explicit user filters or the configured probability threshold, falling back to default sources when none qualify.

  4. Search and present

    Run source searches, filter and rank results, then stream them to the interface.

Why it is interesting

Search intent is split into bounded judgements, while deterministic code handles source selection policy, search execution, result merging, and ranking.