Skip to main content
Features/AI Property Search
Search in ordinary language

Describe the home. The filters fill in — and show their work.

Type or speak in dozens of languages. Location, sale or rent, property type, price, bedrooms and bathrooms become real filters. Preferences only change the order and never remove homes. An editable summary shows exactly how the request was interpreted.

Text or voice

Two ways to describe the same search

Typed

A place stays a place; a description becomes a full request

“Brickell” or “33139” uses the instant place lookup. Anything longer than a place name — three or more words, a number or a price, or a sentence in Chinese, Japanese or Thai — is treated as a descriptive request. It first reaches the website’s own route and is then interpreted by the WebGrowly hub.

The standard place lookup remains in the same panel for buyers who already know the address or neighborhood.

Spoken

A voice clip with automatic language detection

The browser records for up to 60 seconds with MediaRecorder and uploads the clip. An AI transcription model detects the language; the browser’s Web Speech API is not used. That keeps the same recording flow in Chrome, Safari and Firefox without asking the visitor to choose a language first.

Accepted formats: webm, ogg, mp4, m4a, mp3 and wav. Typed and spoken versions share the same request cache.

Request to results

How a sentence becomes filters and ranking preferences

  1. 01

    The buyer opens the language search

    One control on the search page opens a centered panel on desktop or a full-screen sheet on mobile, with examples and a microphone button.

  2. 02

    The request separates filters from preferences

    Location, ZIP, sale or rent, property type, price, bedrooms and bathrooms become hard criteria. Up to 8 preferences can come from a closed list of 52 concepts. A fixed multilingual table checks the model’s result again against word-root patterns in English, Spanish, Russian, French and Portuguese before anything is labeled “couldn’t use.”

  3. 03

    The standard search receives the hard criteria

    The same filter state, URL, result list, map and Market Pulse used by the classic search stay in place. Preferences only reorder those results; they never remove a property.

  4. 04

    Evidence is labeled by strength

    A positive structured MLS field is “confirmed.” A match found only in the broker’s description appears as a quoted sentence, not a checkmark. A negative field is “contradicted.” A blank field is “unknown” and is left out of that property’s denominator rather than scored as a failure.

  5. 05

    The buyer receives an editable interpretation

    The summary separates applied filters, ranking-only preferences and anything that could not be used. Every tag can be removed. Removing a filter runs the search again; removing a preference changes the highlights and order, not the result count.

The request and the interpretation shown together

The returned tags distinguish real filters from ranking preferences and identify anything the system could not apply.

Exact rules

The preference list, limits and language handling

Preferences change order only
Preference list
A closed set of 52 concepts. Anything outside the set cannot be scored, labeled or repeated back as a preference.
Named examples
furnished, washer/dryer in unit, corner unit, high floor, penthouse, renovated, pool, gym in building, elevator, doorman, gated, balcony, boat dock, ocean view, bay view, oceanfront, impact windows, pets, no HOA, near beach, near transit, walkable.
Limit per request
A single request can carry no more than 8 preferences.
Effect on results
Order only. Adding or removing a preference does not change the number of properties.
Preference-only requests
“Furnished, gym nearby” is a valid whole-market search that changes the order instead of returning an error.
"Near the beach"
Measured geometrically against the embedded shoreline from the listing's own coordinates, not guessed from marketing text.
Language and parsing
Input languages
Requests can be written in dozens of languages, including Chinese, Japanese and Thai, which are written without spaces. City names and listing terms are converted to the English values expected by the MLS query.
Request routing
Three or more words, a number or a price in a longer entry, or a sentence in Chinese, Japanese or Thai uses the language interpreter. A place name or ZIP code stays with instant place lookup.
Voice clip
Recorded by MediaRecorder in the browser and stopped at 60 seconds; webm, ogg, mp4, m4a, mp3 or wav.
Bedroom counts
Accepted only when the visitor’s own words state the bedroom count, so the bare number in "hasta 3000 al mes" is read as a price, not a bedroom count.
Named neighborhoods
Resolved to a real boundary polygon before searching, because the MLS City field names the city — Miami for Brickell and Edgewater, Miami Beach for South Beach — not the neighborhood.
Shared cache
Voice and text versions use the same request cache.
Clear limits

What this interpretation never does

  • Protected-class language is removed before it can filter, rank or be repeated back, in all five website languages.
  • School quality is acknowledged but never ranked, and nothing in the search can select homes by who lives in an area or by safety.
  • A general accessibility request, such as step-free or wheelchair access, is surfaced with a note telling the visitor to confirm it with the agent. It is neither silently discarded nor used to rank; a specific amenity such as an elevator stays an ordinary preference.
  • Interpretation and transcription are automated, not human translation, so no arbitrary request is guaranteed to be understood.
  • Wishes are not filters. Nothing is removed from the result set because of one.
  • The AI does not find homes on its own, contact anyone, or book anything, and nothing here is a claim about search rankings, traffic or lead volume.

Bring a search request in your own words

Type or speak it during the demo and inspect the filters and preferences the system returns.

Book a Demo