Case Studies | PropTech

A conversational knowledge assistant for bid teams

AI Bid-Writing Knowledge 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.

High-quality retrieval

The system had to generate strong embeddings from the client's documents and retrieve the right passages, preserving semantic meaning so answers were accurate rather than approximate.

Natural, grounded answers

It needed to interpret plain-language questions and return relevant, context-accurate responses drawn from the documents, verified through human evaluation.

Secure, self-service access

Teams needed a simple, authenticated web interface to interact with the assistant conversationally, with their documents flowing in securely from where they already lived in Microsoft SharePoint.

Solution

Documents are uploaded to Microsoft SharePoint Online, and AWS AppFlow transfers them into an Amazon S3 bucket. An Amazon Bedrock Knowledge Base uses the Titan Embed embedding model to convert those documents into vector embeddings, which are stored and indexed in Pinecone for fast similarity search.

250/mo

Query volume the solution was modelled to serve

~$23/mo

Estimated running cost including Bedrock and Pinecone (projected)

IaC

Full stack deployed via AWS CloudFormation

By the numbers:

  • 250/mo - Query volume the solution was modelled to serve
  • ~$23/mo - Estimated running cost including Bedrock and Pinecone (projected)
  • IaC - Full stack deployed via AWS CloudFormation
Changes

The assistant was delivered against the agreed success criteria and demonstrated to the client, giving their teams a secure, conversational way to query their document library and validated through human evaluation of answer relevance. The whole stack was deployed as Infrastructure as Code into the client's environment.

  • Accurate retrieval — Bedrock Knowledge Base embeddings stored in Pinecone deliver fast, semantically relevant search across the document corpus.
  • Conversational answers — A Bedrock Agent returns grounded responses to plain-language questions, with continuity held in DynamoDB.
  • Secure access — A Cognito-authenticated Streamlit interface on EC2, with documents flowing in from SharePoint via AWS AppFlow.
  • Repeatable deployment — The solution is defined in CloudFormation, making it straightforward to redeploy and maintain.
  • Handover — Technical documentation, an user guide and administration training were provided to the client's team.

The assistant reduces the time teams spend searching for information and establishes a foundation for further AI initiatives at the client, ready to support growing document volumes and more users. Running costs are an estimate that will depend on actual usage.

AWS Stack

Amazon Bedrock Knowledge Base

And Bedrock Agent for embedding, retrieval and grounded question answering.

Amazon S3

For document storage feeding the knowledge base.

AWS AppFlow

For secure transfer of documents from Microsoft SharePoint Online to S3.

AWS Lambda

For the bridge between the web app and the Bedrock Agent.

Amazon Cognito

For user authentication, with the interface hosted on Amazon EC2.

Amazon DynamoDB

For chat history and session state, deployed via AWS CloudFormation.

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.