Small decisions. Interesting possibilities.Submit contentSubmit

Natural-language search over Zillow

Jev can serve as better natural language search on websites. It can scan thousands of Zillow listings and classify properties by things you can't normally filter for - e.g. architecture, renovation status, proximity to freeways. This was done in <20 sec and costs $0.18 ๐Ÿ‘‡

Added to Jevfast

How it uses Jev

The system scans Zillow listings and uses Jev to classify properties by criteria such as architecture, renovation status, or freeway proximity, which ordinary listing filters may not cover.

App workflow

  1. Specify a property need

    The user describes the traits they want to find in natural language.

  2. Scan listings

    The system processes thousands of Zillow listings.

  3. Classify property traits

    Jev evaluates each listing for criteria such as architecture, renovation, or freeway proximity.

  4. Surface matches

    Listings meeting the requested traits can be found through the classifications.

Why it is interesting

It applies natural-language criteria across a large listing set by turning otherwise hard-to-filter property traits into classification decisions.