Show 13. juni 2024

Bedre boligannoncer med AI




Kategori :

Type :



For the past decade, danbolig has been a digital front runner among real estate agents. From the first responsive website in the industry to “Our neighborhood”, the internationally award-winning data visualization platform for home seekers and buyers.

danbolig stays ahead by constantly prioritizing innovation – with a roadmap of continuous projects in all corners of the digital space.

As with any true innovation program, many of these sandbox projects never get realized – but the most promising ones do.

danbolig has long experimented with integrating predictive AI in the home searching process, a field with enormous potential but equally enormous data requirements.

While this work continues, the recent boom in generative AI begged the obvious question: Is there any business value to be realized NOW, using this rapidly maturing technology? Or should we simply regard it as a novelty for amusement and attention-seeking?

With an organization and agency collaboration which has, for years, developed a way of working that allows for rapid innovation, iteration and deployment, danbolig immediately set out to solve business problems with OpenAI’s models.

It didn’t take long to find the glaring opportunity of content production: Real estate agents are faced with massive content demands every day, most of it repetitive, unforgiving and short lived.

With a workforce that’s – generally speaking – way more passionate about selling houses than writing, giving them a tool to produce more persuasive, compelling and effective content in next to no time seemed like a no-brainer. Or at least an ‘artificial-brain’-er.


The solution was to create the danbolig AI Assistant for editors – a content power-tool to help danbolig employees make the most of their time and talents.

But while the “idea” of using AI for content production is hardly very innovative – and maybe barely an idea at all – the idea of embedding it deep within the daily workflow of employees is much more interesting. With no alienating technobabble or intro courses, and no disruption of ‘normal content processes’, we wanted to provide unquestionable improvement to the eventual content result, not simply a gimmick.

Our solution integrates an OpenAI-powered large language model (LLM) directly into a market leading content management solution. We used OpenAIs GPT3 – davinci 003 model through Azure as our LLM foundation and Umbraco as the CMS.

We predefined relevant AI prompts and allowed them to be triggered and customized by simple and familiar interface action points like buttons or drop down menus, essentially making a “generative AI prompt designer” available at the fingertips of the content editor.

We have integrated the LLM naturally in the authoring dialog; this allows authors / editors to not leave the CMS to finish the task. Therefore, we rewrote content components in the Umbraco CMS to be connected to the LLM endpoint at all times.

While the house listings themselves are regulated, the AI assistant adds many tools to optimizing and improving existing content. And for all other content – from neighborhood or store descriptions, to invitation emails for open house events, the Assistant helps create content from scratch.

The solution is extendable and customizable. We are now working on finetuning our version of the foundational language model, training it specifically on danbolig vocabulary and brand tone of voice, as well as specific customer segments and real estate descriptions, to produce greater variety and higher quality.

With more robust segmenting, danbolig agents will be able to create segment specific landing pages to enable true personalization at scale.

Another feature in the works is building out the content creation feature to include computer vision to create accurate listings, including neighborhoods and descriptions, simply by uploading a photo with localization data.


Obviously hard, long-term numerical results are impossible at this stage.

Through a series of intense coding sessions, danbolig succeeded in getting from concept ideation to proof of concept implementation in Umbraco in 11 days, giving editors something close to a magic wand.

Now, at the click of a button, content producers can:

1) Fill a website (element) with content from free text field prompts: Authors have a basic text input field, allowing them to enter any prompt. The AI Assistant connects to the LLM and ingests the response directly into the website elements the authors are working on.

2) Trigger predefined prompts: By using this feature the AI assistant collects the website meta information, aggregates it into a prompt, and populates the result directly into the text input field.

3) Optimize SEO: Clicking this button triggers the AI Assistant to take an existing text (whether from latest prompt, or any existing website element) and optimize it for SEO performance.

4) Personalize content for specific Target Group: Like Feature #3, this feature edits and optimizes existing or newly created content. It helps authors make their content more target group specific. 3 key target groups of house-seekers for danbolig are Families, Singles and older people heading towards retirement. Authors simply select target group, triggering a hidden prompt to finetune the content for that segment.

5) Optimize for Readability/ accessibility/ CX: This feature addresses the structure of texts. Authors can use it to shorten existing text by just inputting a number into a "shorten to X words" command, or simplify the text by clicking a "Make it easier to read" button.

When scaled to all agents, this AI Assistant will completely transform danbolig’s ability to create quality content at scale.

An additional benefit is the end of Lorem Ipsum: With this product, danbolig easily got rid of dummy texts in all new development and staging environments, allowing for testing UX and CMS components with real content and metadata – which means a much shorter path to the optimal user experience.

“We believe very strongly in our culture of innovation, but innovation often relies on speed and agility: This project proves that we can move from idea to implementation at a radical pace, a learning that will benefit our entire pipeline of exciting innovation projects.”
Anne Mette Koch, CCO/CIO, danbolig.


Anne Mette Koch

Kommerciel chef (CCO/CIO)

Sidsel Vitger Beuschau

Digital manager


Thomas Walter

Chief Practices Officer

Pål Machulla

Creative Director

Mikkel Nielsen

Development Director

Jacob Munksgard Hoff

Software Engineer

Louise Stolberg

Executive Director & Co market leader

Nicholai Reinseth

CXO, Northern Europe

Nicholai Reinseth

Experience Design Director, Northern Europe


Watch Video