Gazelle: Smart validation and 99.9%-accurate property descriptions with Gemini
Gazelle, a Swedish startup automating property documentation for real estate agents in Sweden and Norway, uses Google's Gemini 1.5 Pro to extract key information from lengthy property documents like building-inspection and electricity reports and generate sales content. Gemini increased output accuracy from less than 95% to 99.9%, reduced content generation time from four hours to 10 seconds, and helped Gazelle launch four new products in under a year, saving brokers 4 to 6 hours of manual work per property.
Overview
Gazelle, a Swedish startup automating property documentation for real estate agents in Sweden and Norway, uses Google's Gemini 1.5 Pro to extract key information from lengthy property documents like building-inspection and electricity reports and generate sales content. Gemini increased output accuracy from less than 95% to 99.9%, reduced content generation time from four hours to 10 seconds, and helped Gazelle launch four new products in under a year, saving brokers 4 to 6 hours of manual work per property.
This entry has 15 published fields tied to exact passages in an immutable source capture.
Inspect the highlighted sourceThe challenge
Extracting key information from lengthy property documents was a manual, time-consuming task for real estate brokers; Gazelle found certain documents too complex for traditional machine-learning methods, and its third-party generative AI tool would hallucinate answers, which was unacceptable since customers could get sued for presenting incorrect information.
The solution
Gazelle adopted Gemini 1.5 Pro from Google Cloud to extract and summarize key information from lengthy documents like building-inspection and electricity reports, using Gemini's multimodal capabilities to recognize information across document types and images, integrating via APIs directly into real estate agents' software, and using BigQuery to analyze tool performance; it is also developing a Google Maps Platform and Google Search-grounded feature to generate area descriptions and image captions.
Reported business value
Gazelle increased the accuracy of its output from less than 95% to 99.9% with Gemini, cut content generation from four hours of manual work to 10 seconds, and saves brokers 4 to 6 hours of manual work per object; faster quality control also let Gazelle launch four new products in under a year, and Gemini costs around a fifth of the price of alternatives.
Sources
Open any source and check the claim yourself — that is the point of the register.
This record was researched and written with AI assistance, and its claims were checked against the sources above. (EU AI Act art. 50 transparency notice.)
Other real estate entries in the register.
Matching home buyers with their dream house
Compass, a real estate technology company, uses the Databricks Data + AI Platform to deliver predictive intelligence that identifies homeowners likely to sell, helping agents optimize marketing budgets and outreach strategies, replacing siloed ad hoc data lakes with a unified platform.
CompassDatabricks Data + AI Platform · Unity Catalog · Databricks SQL
First American Data & Analytics fine-tunes open-source LLMs on Databricks, cutting extraction costs 70%
First American Data & Analytics (DNA), a property-centric information provider to the real estate and title insurance industries, used the Databricks Data + AI Platform to fine-tune open-source LLMs (Mistral, Llama 3, Llama 3.1) for page-level classification and extraction of 100+ data fields from roughly 4 million historical title policy images dating to the 1930s. Using Delta Lake, Databricks Model Training, Managed MLflow, and serverless Model Serving on about 50 GPUs, the team fine-tuned models in two weeks versus the two-plus months it previously took on other platforms. The project cut extraction costs by 70%, reduced project completion time by 75% (months to weeks), and increased the number of data elements extracted tenfold.
ECE Group rolls out Microsoft 365 Copilot, with 70 percent of pilot users wanting to keep their licence
German real estate and shopping centre operator ECE Group rolled out Microsoft 365 Copilot after manual information searches and data compilation slowed daily work. It went from budget approval to first pilot training in three months, using Copilot for meeting minutes, customer presentation ideas and press release drafts. The Microsoft customer story reports that around 70 percent of pilot participants want to continue using it.
ECE Group· GermanyMicrosoft 365 Copilot
Aareon builds AAVA, an AI virtual assistant integrated into its German property-management ERP, using Amazon Bedrock
Aareon, a Germany-headquartered property management software provider, integrated an AI virtual assistant called AAVA into its German ERP solution Wodis Yuneo using Amazon Bedrock. AAVA lets real estate housing company customers query documents, request information through chat, automate processes, and accelerate workflows -- including scheduling appointments between tenants and craftsmen, coding invoices, analyzing images to draft damage reports, and sorting incoming email, with both text and voice support. Aareon uses various LLMs available through Bedrock, including Anthropic's Claude models and Amazon Nova models, testing and selecting models by complexity and price performance for each use case (for example, a higher token-limit model for calculating service charges). The Bedrock deployment runs in the AWS Germany (Frankfurt) Region to help meet GDPR requirements, with customer data not used to train or improve the underlying models. The first version of AAVA was built in 4 weeks and announced to customers within 6 months, developed with support from AWS Partner Reply.
Aareon· GermanyAmazon Bedrock · Amazon Nova · Anthropic Claude
Was this helpful?
Your feedback helps us improve our use case database