Small decisions. Interesting possibilities.Submit contentSubmit

Intent-aware search in Replicas

small experiment where I used jev to power the global search in replicas. the possibilities of improving UX with models like jev are endless. we can now have things like: - search that understands what users mean - actions that change based on what you're trying to do - routing tasks to the right agent/model…

Added to Jevfast

How it uses Jev

Jev powers global search in Replicas. The post frames the intended decision as interpreting what users mean, with related possibilities including changing actions by intent and routing tasks to an agent or model; it does not specify the search request schema or ranking mechanism.

App workflow

  1. Enter global search

    The experiment applies Jev to Replicas’ global search.

  2. Interpret intent

    Jev is used to help search understand what users mean; the post does not describe the exact state sent.

  3. Adapt the experience

    The creator identifies intent-aware results, context-dependent actions, and agent/model routing as possible applications.

Why it is interesting

It treats search as a sequence of small UX decisions, using intent to make search results or next actions more relevant.