realestate.co.nz launches an AI image search function for property listings in New Zealand and mentions they are the first website in the country to bring this type of technology to market.
The feature allows users to search for homes by visual elements in listing photos, as opposed to relying on written descriptions. Searches might include phrases such as weatherboard exterior, wooden flooring, home gym or pool, with results taken from images on the platform.
realestate.co.nz’s system works in two stages. Firstly, it analyses each uploaded image and tags features such as room type, interior style, flooring, and details like custom shelving. The second layer of the system interprets search terms and related concepts to generate results.
Users will then see listings that match both exact requests and closely linked ideas. The tool is also capable of identifying wider or more subjective features, such as a strong view or shade trees in a garden.
Sarah Wood, Chief Executive Officer of realestate.co.nz, mentions the product is reflective of changes in how people search for homes online.
“In our 30-year history, we’ve developed a deep understanding of how people connect with property. Property searches have traditionally depended on how accurately a home is described and whether all the key features a buyer is looking for are included in the listing description. But buying a home is an emotional decision.
“People respond to how a space looks and feels. This tool connects people with homes based on what they’re genuinely drawn to, whether that’s a swimming pool, home gym, wine cellar, or walk-in wardrobe!”
Sarah Wood, Chief Executive Officer, realestate.co.nz
The search function adds a new layer to a property portal which has been in operation since 1996 and proclaims itself as New Zealand’s longest-running property website. It also points to a wider shift and change to online marketplaces utilising AI to make large image libraries more searchable.
Images uploaded to the platform rest within Snowflake’s AI data cloud, which operates as the underlying data environment for the search system. Snowflake mentions the tool illustrates how AI can be applied to a broad property dataset which includes photos, maps, addresses and listings.
“realestate.co.nz is the leader in property intelligence, managing vast amounts of data including photos, maps, addresses, and listings. By leveraging Snowflake’s Cortex AI, realestate.co.nz is using this wealth of data to personalise the customer experience with high accuracy and at significant scale, and this use of AI benefits all New Zealanders buying, selling, or leasing property.”
Tony Shaw, Country Manager New Zealand, Snowflake
The image search tool is described as beta, despite being already live on the site. The label indicates that the AI image interpretation might not be wholly accurate in each case while the product continues to be monitored and refined.
Simon Hargraves, Chief Product and Technology Officer of realestate.co.nz, mentions the company will treat the feature as a live product while continuing to analyse how people use it.
“The beta label is mainly about setting the right expectations. With new AI-powered features, especially those involving image interpretation, it is important to acknowledge that accuracy may not be perfect in every instance.
“Labelling it as beta allows us to be transparent with users while we continue to monitor, learn, and improve the experience. We will be looking closely at the most commonly searched features and making sure the tool performs strongly where user demand is highest.”
Simon Hargraves, Chief Product and Technology Officer, realestate.co.nz
He also adds that the company is collecting usage data to explore which searches are more common and which property attributes are important to most to users. The information uncovered is expected to shape how the tool develops over time.
“This tool places greater importance on high-quality images that showcase a property’s best or most unique features, because those are the images directly powering search results.
“The company has previously introduced other AI-driven search and listing features, including AI floor plan surfacing and a seller-focused assistant called Tāhū. Thirty years ago, we brought property searching online. Now we’re redefining it again.”
Sarah Wood, Chief Executive Officer, realestate.co.nz
Sarah further mentions the tool could affect how agents and sellers approach listing photography, as images play a more direct role in discovery. Stronger images which show a home’s distinctive features will be more valuable when users search visually.
