Case Studies | PropTech

An AI webchat assistant for letting agents, built on AWS Bedrock

AI Webchat Assistant

About

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

Challenge

The challenge had three focus areas.

Accurate answers grounded in the client's own knowledge

The core objective was the most accurate service possible for the client's customers. A generic model would not do. Answers had to be drawn from the client's own data through retrieval augmented generation over a vector database, so responses are specific and correct rather than plausible guesses.

Safe, compliant automation

Automating customer communications in a regulated sector means controlling what the model can and cannot say. Guardrails and coverage of compliance and regulatory requirements were a first class part of the scope, not an afterthought.

Proving AWS Bedrock and enabling the team

The engagement also had to validate AWS Bedrock as the platform to continue building on, and to leave the client's internal technical lead confident enough to carry development forward independently.

Solution

The work was delivered through Cloud Combinator's Cloud Accelerator Program, a staged path from discovery to a working delivery in the client's own AWS account.

Changes

The proof of concept met its scope: a working AWS Bedrock back end for AI webchat, grounded in the client's own knowledge, with guardrails and a retrieval pipeline in place, and Bedrock

  • Knowledge grounded webchat back end — A Bedrock powered service that answers enquiries from the client's own data through retrieval augmented generation over a vector database.
  • Guardrails and compliance built in — Controls to keep automated responses safe and within regulatory boundaries were part of the delivery.
  • Secure AWS foundation — AWS and Amazon S3 were set up with appropriate permissions and security, alongside best practice for billing and recovery.
  • Platform validated — The engagement demonstrated AWS Bedrock as a suitable environment to continue developing the client model.
  • Handover — An immersion day and knowledge transfer left the client's internal technical lead able to carry the model development forward.

Validated as a suitable platform to continue development. The cost figures noted below are the SoW estimate and are projected until the service runs at steady state.

With a validated Bedrock back end and an upskilled internal team, the client is positioned to connect the service to its front end and extend automated, knowledge grounded customer service across more of the business. The SoW put the indicative AWS run cost at around 1,570 US dollars per month, or roughly 18,800 US dollars a year, projected until measured in production.

AWS Stack

Amazon Bedrock

For the large language model and guardrails that generate safe, accurate responses.

Amazon S3

For secure storage of the client's knowledge data.

AWS Lambda

For the pipeline that combines the services and connects towards the front end.

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.