Marketing Personalization
Scout24 needed to move beyond keyword real-estate search so seekers could get guided help, listings, and recommendations that better reflected how people actually explore where and how they want to live.
Reported impact
Scout24 launched a more intelligent real-estate search experience, established rigorous AI quality controls for customer-facing answers, and created a platform it can extend across seekers, homeowners, landlords, and agents.
Scout24 used GPT-5 to build HeyImmo, a conversational real-estate assistant that turns property search into an interactive guidance experience. Rather than only returning results, the assistant can ask clarifying questions, surface relevant listings, summarize options, and adapt its response format to match what a user needs at that moment—bullet points, full explanations, or direct listing suggestions with image previews. The team intentionally simplified its technical architecture away from a more complex multi-agent plan and instead leaned on function calling and tightly scoped components so it could ship, learn, and optimize for latency and reliability. To protect quality, Scout24 built its own evaluation system inspired by the OpenAI Evals framework and delayed launch once to make sure the experience met its internal bar. Broad employee “swarm testing,” close collaboration with OpenAI solutions architects, and a willingness to refine answer structure and edge-case handling helped turn conversational property search into a trustworthy core product experience.
User search intent enters HeyImmo, which asks follow-up questions, formats results appropriately, and returns listings or summaries based on GPT-5 reasoning. Quality signals from custom evals and broad internal testing then feed back into answer refinement before new improvements are shipped.
"GPT‑5 powering Scout24’s conversational search assistant HeyImmo"
"The company delayed launch once to ensure the experience met the bar"
"We needed a real-estate expert assistant—a sparring partner"
"the team intentionally simplified: using function calling and focused components"
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
OpenAI Sample Aug 10, 2026 Zapier At Zapier, the enterprise marketing team is using ChatGPT Work to build automated funnel optimization systems, enabling them to deliver more value to their sales team with less manual effort. ChatGPT Work operates… Now, the enterprise marketing team can perform automatic QA/QC on thousands of leads every month. The… ChatGPT Work OpenAI Sample Aug 3, 2026 Circles Circles needed to turn rich telco signals such as usage, billing, network activity, and location into real-time support and monetization actions instead of reactive, siloed customer journeys. 22% increase in ARPU in Singapore from AI-driven personalization AI Concierge · CareX · Codex OpenAI Sample Jan 26, 2026 Indeed Indeed needed to expand AI across job search, employer hiring workflows, and internal operations while keeping human decision-makers in the loop and building employee confidence in how to use the technology well. About 70% of sponsored applications come from AI-powered recommendations Career Scout · OpenAI APIs · Smart Sourcing 