Case Studies | PropTech

Letting property data answer for itself

AI Property Risk Webchat

About

A PropTech business working with Cloud Combinator on AWS. The client is anonymised at their request.

Challenge

The challenge had three focus areas, each about making a generative AI assistant accurate, useful and compliant.

Grounding answers in real data

A general-purpose chatbot is not enough. Responses had to be grounded in the client's own knowledge base, which meant standing up a vector database and retrieval layer so the model draws on the right documents for each query.

Holding a coherent conversation

Useful assistants remember context. The solution needed conversational memory so it could maintain the state and thread of an exchange rather than treating every question in isolation.

Automating reports within compliance

Beyond answering questions, the assistant had to help automate accurate report creation for internal and external enquiries, all while following the client's compliance and regulatory requirements.

Solution

Cloud Combinator delivered the work through its Cloud Accelerator Program, a staged path that takes a client from idea to a working solution in their own AWS account while upskilling their team.

RAG

Retrieval-augmented answers grounded in the client's own knowledge base

Chat-to-

Natural-language access to property risk and opportunity insight

5-phase

Cloud Accelerator delivery, from discovery to build

By the numbers:

  • RAG - Retrieval-augmented answers grounded in the client's own knowledge base
  • Chat-to- - Natural-language access to property risk and opportunity insight
  • 5-phase - Cloud Accelerator delivery, from discovery to build
Changes

The engagement delivered a retrieval-augmented generative AI back end in the client's own AWS account, giving mortgage assessors and house buyers a way to chat to property data and support automated report creation, and validating Amazon Bedrock as a suitable platform to continue building on.

  • Grounded responses — A Bedrock Knowledge Base over Amazon S3, paired with an OpenSearch vector database, ensures answers are drawn from the client's own documents.
  • Context-aware conversations — Conversational memory in Amazon DynamoDB lets the assistant maintain the state and context of an exchange.
  • Report automation — The assistant is designed to help automate accurate report creation for internal and external enquiries, following the client's compliance requirements.
  • Platform validated — The project confirmed Amazon Bedrock as a suitable environment for the client to continue developing its service.
  • Handover — The solution was demonstrated, tested and handed over in the client's AWS account, with guidance provided on integrating the back end to their front end and on adding more documents to the knowledge base.

With the back end proven and their team guided on extending it, the client is positioned to grow the knowledge base, connect the assistant to its front-end applications, and widen chat-to-data access across more of its property intelligence.

AWS Stack

Amazon Bedrock

For large language model response generation grounded in retrieved knowledge.

Amazon Bedrock Knowledge Base

With Amazon S3 as the document data source.

Amazon OpenSearch Service

As the vector database for efficient similarity search.

Amazon Lex

For interpreting user queries and driving the conversation.

AWS Lambda

For orchestration, and Amazon DynamoDB for conversational memory.

YOU MIGHT LIKE

Related success stories

View all case studies

Case Studies | Insights

Utilising Language Recognition, Speed, and Enhanced Security to Make Social Media a Force for Good

  • Here, we take a detailed look at how the Cloud Combinator team collaborated with another cutting-edge AI service provider that provides intelligent systems to “make social media more social” for brands and users alike.
  • Arwen AI is a UK-based startup specialising in AI solutions to manage and enhance brands’ social media interactions. Founded in 2020 by Matt McGrory, Dr. David Cole, and Joel Bailey, Arwen. AI focuses on using AI to automatically detect and remove spam, toxic comments, and other unwanted content from social media platforms.
  • The team at Arwen have three core products. ‘Moderate’ is focused on identifying and removing toxic content from social media channels. ‘Engage’ helps brands identify and engage with meaningful conversations on social media, and ‘Customize’ allows brands to apply bespoke algorithms to their channels - creating an even more effective moderation and engagement.
Read more
CONTACT US

Ready to turn AI into impact?

We'll help you spot the highest-value opportunities, reduce risk around your first AI initiative, and define a clear path to results from day one.

Why talk to us:

Outcome-driven recommendations

AWS-recognised delivery expertise

Risk-aware AI adoption

Clear next step, not a sales pitch

Start with a focused 20-minute conversation about your goals — no pressure, no commitment.

We use cookies

This website uses cookies to enhance user experience and to analyze performance and traffic on our website.

See our Privacy Policy for details.