Case Studies | SaaS B2B

Answers from your own documents

Bedrock Knowledge Base Query

About

A SaaS B2B business working with Cloud Combinator on AWS. The client is anonymised at their request.

Challenge

The build focused on three requirements that together make a private knowledge base genuinely useful.

Grounded answers, not guesses

A generic large language model does not know an organisation's private documents. The service needed retrieval-augmented generation, pairing Amazon Bedrock with a vector index so responses are drawn from the client's own content rather than invented.

Secure, controlled access

Because the corpus is private, the application needed authenticated access with advanced security, and deployment in the EU (London) region to keep data in the right place.

A scalable, serverless pipeline

Both document ingestion and live querying needed to run on managed, event-driven components that scale with demand and keep operational overhead low.

Solution

Documents are held in Amazon S3 and indexed into Amazon OpenSearch Service, which acts as the vector store for the knowledge base. An user reaches the application through a front end hosted on AWS Amplify and signs in via Amazon Cognito.

8

AWS services orchestrated in the build

EU (London)

Deployment region for data residency

By the numbers:

  • 8 - AWS services orchestrated in the build
  • EU (London) - Deployment region for data residency
Changes

The engagement delivered a complete, working knowledge base query service on AWS: documents indexed into a managed vector store, a Bedrock-backed retrieval-augmented generation flow, and a secured front end, all provisioned in the EU (London) region. As this piece is drawn from the delivery artifacts rather than a signed statement of work, the outcomes below describe the capability that was built.

  • Grounded answers — Retrieval-augmented generation pairs Amazon Bedrock with an Amazon OpenSearch Service vector index so responses come from the client's own documents.
  • Secure access — Amazon Cognito provides authenticated sign-in with advanced security features for a private corpus.
  • Serverless pipeline — AWS Lambda, Amazon API Gateway and Amazon SQS handle query and ingestion on managed, event-driven components.
  • Document store and front end — Source material is kept in Amazon S3, with the user interface hosted on AWS Amplify.
  • Handover — The solution was delivered on the client's AWS account, ready for their team to operate and extend.

With a working retrieval-augmented knowledge base in place, the client has a foundation it can grow, adding more documents and use cases on the same AWS stack as the need expands.

AWS Stack

Amazon Bedrock

For the large language model that generates grounded answers.

Amazon OpenSearch Service

As the vector store for the knowledge base index.

AWS Lambda

For serverless retrieval and orchestration.

Amazon API Gateway

For handling query requests from the application.

Amazon Cognito

For authenticated access with advanced security.

Amazon SQS

For decoupled, asynchronous document ingestion and processing.

Amazon S3

For document storage, with AWS Amplify hosting 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.