Skip to main content
Seeki.eu
How natural-language property search works, for Europe

How natural-language property search works, for Europe

Peter Marci
Peter Marci

Founder of Seeki.eu. Writes about buying, renting and selling across European property markets, drawing on the portal's own listings data.

Natural-language property search is a way of finding homes by typing a sentence the way you'd say it out loud, such as "two-bedroom apartment in Prague near a school, under €200,000", and getting a filtered map and list back. Instead of clicking through ten dropdowns, you describe what you want and the system pulls out the criteria.

This kind of search only became reliable in the last two years. Earlier filter-based portals could handle one country, one language, and a fixed schema. A buyer searching across Europe runs into a different problem: every country names its rooms, layouts and listing types differently, and most portals only speak one language at a time. Seeki.eu was built to close that gap.

This post explains how the search works at a high level, why cross-border buying breaks traditional filters, and where the system still asks for help instead of guessing.

Last reviewed: 2026-08-11. Product mechanics move underneath a post like this one, so every behaviour described below was re-checked against the live search before this update.

How it works

A sentence goes through a few steps before it becomes a result. First the system reads the sentence and pulls out the parts that describe a home: a place, whether you want to buy or rent, a property type, a price range, a size range, a floor range, a room layout, the condition of the building, must-haves such as a lift, furnishing or step-free access, whether you want a short let rather than a long one, and any nearby amenities you named. Then it resolves the place name against a hierarchical gazetteer of European locations, so "Prague", "Praga", "Praha" and "Prag" all land on the same city. The criteria become a query against the marketplace, and your budget is normalised to euros behind the scenes, so a figure typed in złoty and a figure typed in euros compare like for like. The result is a map and a list, with a URL you can bookmark or send. Prices themselves keep displaying in whichever currency you have chosen.

It reads relative locations too. "Within 20 km of Brno", "north of Vienna" or "between Prague and Kladno" turn into a real area on the map with a drawn boundary, scoped to the towns that fall inside it, rather than a single pin and a guess about how far "near" means.

One thing it deliberately will not do is stretch a single sentence across several countries. Each query resolves one place, and that place can sit in any of the markets we cover. Searching more than one country at a time is a different job, done by the comparison tools rather than the sentence box, and the guide to searching several EU countries at once walks through how that works.

The reason this matters more in Europe than in any single-country market is that the unit names do not agree across borders. A two-bedroom apartment in English is a "T3" in Portuguese real-estate terminology (the number counts rooms, not bedrooms). In Czech it is a "3+kk" or "2+1" depending on whether the kitchenette is part of the main room. In German listings it is "Drei-Zimmer-Wohnung". In Italian "trilocale". In Polish "M3". None of these map cleanly into the others. A dropdown that says "2 bedrooms" in English does not survive translation. It changes its meaning every country it crosses.

Natural-language search sidesteps this by treating the question as language and the result as data. You speak the vocabulary of your own market, and the system translates into one canonical schema before searching. The same mechanism powers the cross-border use case: a German buyer planning a holiday rental can type "house with a pool near Lake Balaton under €300,000" in German, and get Hungarian listings back, with a budget that means the same thing on both sides of the border and the same filters they would use at home.

A worked example

Step What goes in What comes out
Read the sentence "2-bedroom apartment in Prague near a school under €200k" place: Prague, buy or rent: buy, type: apartment, layout: 2-bedroom, max price: €200k, near: school
Resolve the place "Prague" the Prague area page in your language
Filter the marketplace the criteria above apartments in Prague matching the filters
Render the matching listings a map and a list, with a shareable URL

A sentence in another language traces the same path. "Mieszkanie dwupokojowe w Warszawie do 400 000 zł" lands on the Warsaw apartments page, with the złoty budget compared against listings priced in other currencies without you converting anything.

Can I change my mind without starting over?

Yes, and this is the part that saves the most clicking. Once you are looking at results, the next sentence refines the one before it instead of resetting it. "Cheaper" keeps the city and the property type and moves the price. "With a garden" adds a requirement. "Forget the lift" takes one away. If you are already looking at an area and you describe criteria without naming a place, the search stays where you are rather than sending you somewhere else.

You can speak the query instead of typing it. The words appear in the box and a short countdown runs before the search fires, so a mis-heard word is something you catch and correct rather than something that navigates you away.

The same box answers questions as well as running searches. On a property page it will answer questions about that specific home. On an article it will answer questions about what you are reading and show which pages the answer came from. And when what you want is a tool rather than a listing, a sentence like "compare countries on my budget" or "what is my flat worth" opens the right one.

Where the system asks for help

A sentence-based search is only as good as its handling of vague or impossible queries, and the rule it follows is that it does not guess.

If the sentence is not about property, it says so and you keep typing. If the sentence is about property but there is nothing in it the search can act on, whether that is because the place name matches nothing we hold or because "I want a nice flat" carries no criterion at all, it asks you to be more specific instead of returning a city in the wrong country. Where it can only place you in a broader area than the one you named, it tells you which area it landed on, so you are never left wondering whether it understood.

These guards exist because silently picking a default is worse than asking one extra question. A search system that confidently returns the wrong city is the failure mode this kind of product fails at most often.

Frequently asked questions

Does it work in my language?

It works in every language the site runs in: English, Czech, Slovak, German, Dutch, Polish, Spanish, Italian, Portuguese, French, Hungarian and Ukrainian. Write the query in any of them and the answer comes back in the same one. The place you search can sit in any of the markets Seeki.eu covers, and a listing originally written in another language has its title and description translated into yours on demand.

What if my query is too vague?

The system tells you it is too vague rather than guessing. The chat returns a short follow-up ("which city?", "what's your budget?", "buy or rent?") and waits. One round of clarification is normally enough to produce a useful search. If you would rather click filters, the result page still has all the dropdowns available, and the sentence-based search is the entry point, not the only path.

Can it find listings near a school, a metro stop, or a park?

Yes. The system picks up point-of-interest constraints if you mention them, and narrows results to listings within walking distance of a matching place. Schools, kindergartens, metro and tram stops, parks, playgrounds, supermarkets, pharmacies, hospitals and a dozen other everyday amenities are recognised. There is a fuller walkthrough of searching by what is nearby, including the cases where the answer changes which neighbourhood you should be looking at.

How does it handle different room-count systems?

The system knows the local conventions. A Portuguese "T3" and a German "Drei-Zimmer-Wohnung" describe the same layout, and the search treats them as the same thing when it goes looking. You do not have to learn another country's terminology to search there.

What happens after I see the results?

The URL is shareable, so you can bookmark it or send it. Changing the price, adding a filter or panning the map keeps you on the same page and updates the results directly, with no need to go back through the sentence box. Opening a listing shows the property detail with similar homes on the map, all in your language.

Is the language model deciding which property is best?

No. It only identifies what you asked for. Ranking and filtering happen inside the database against objective criteria (price, location, room count, the listing's own data), not against a model's preference. The system is a translator from sentences to filters, not a recommender.

Seeki.eu is the marketplace, and the sentence-based search is one way in. For background on how prices and stock differ across the continent, the country price snapshot shows live €/m² for Czechia by region, and the Prague district breakdown walks through how a single city can sit in several different price tiers at once.