Search the way buyers describe a home.
“Two-bedroom near the metro, under 12 million, with a balcony” is a filter set written as a sentence. AACSearch turns it into filters, ranks by distance and answers questions about the area from your listing content.
Queries plain keyword search gets wrong
двушка у метро до 12 млнrooms, location, budgetквартира с балконом и парковкойamenitiesдом рядом со школойproximityновостройка сдача 2026dateWhere search loses customers today
Sentences, not filters
Buyers type a description; the site expects them to set eight filters.
Location is the product
Distance to metro, school and work matters more than the listing title.
Questions about the area
“Is it quiet?”, “what schools are nearby?” — answered by agents on the phone.
How AACSearch solves it, layer by layer
Each card names the capability behind it. Items marked “in development” are designed and scheduled, not live yet.
Finds the right item from the first letters — typos, synonyms, filters, meaning.
Natural-language filters
Rooms, budget and amenities extracted from the query into filters.
Widens the basket: similar, frequently together, personal.
Answers questions a filter can't, citing your own catalogue and docs.
Area answers
Answers about the building and neighbourhood from listing descriptions and area guides, with citations.
Learns how items, queries and topics connect — and leads the visitor to the goal.
Buyer journey
Will learn which listings lead to viewing requests and rank toward them.
One visitor, from first query to goal
What the visitor does on the left, what AACSearch does on the right.
- 1
Describe
Types “двушка у метро до 12 млн с балконом”.
Applies rooms, budget and amenities as filters and sorts by distance.
Natural-language search - 2
Explore
Opens a listing.
Shows similar listings nearby in the same price band.
Recommendations - 3
Ask
Asks about schools nearby.
Answers from the area guide with a citation.
AI answers with citations
Your first two weeks
A typical rollout for this industry. Most teams are live on day one and spend the rest of the time measuring and tuning.
Day 1
Import listings with coordinates and amenities.
Day 2
Enable distance sorting and natural-language filters.
Week 1
Index area guides for the assistant.
Week 2
Measure viewing requests per search session.
What to measure
The numbers to judge a rollout by. Compare them with an A/B split or a before/after window on the same traffic.
- Lead rate from search
- Viewing requests per search session.
- Filter usage
- Shows whether natural-language filters replace manual ones.
- Zero-result rate
- Descriptive queries that used to return nothing because no filter matched.
Connects to
- CSV / JSON / XML feed
- REST API
- Embed widget
Capabilities used
Coming next
Search for Real estate, live this week
Connect a feed or a site, embed one script, and measure the difference on your own traffic.