Case Studies | SaaS B2B

Real time knowledge at the point of conversation

Customer Service Knowledge Base

About

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

Challenge

The challenge had three focus areas.

Answers at the speed of the conversation

A customer on the line will not wait while an agent searches. The first focus was surfacing the right answer in real time, as the conversation unfolds, so the agent can respond without breaking the flow of the call.

Grounded in the client's own knowledge

A generic model is not enough. Answers had to be drawn from the client's own material so they are accurate and specific to the business, not plausible sounding guesses. This pointed to a retrieval based approach over a curated knowledge base.

A tool agents trust

An assistant only helps if agents rely on it. The final focus was an experience that fits naturally alongside a live call and earns the team's confidence rather than adding friction.

Solution

In the recommended design, a live call is transcribed to text in real time using Amazon Transcribe. The transcribed customer query is passed to an Amazon Bedrock Knowledge Base, which holds the client's own documents and reference material as its source of truth.

Changes

The engagement gave the client a clear, grounded design for a real time knowledge assistant, with the AWS building blocks and the reasoning behind each choice set out in plain terms. The outcomes below describe the intended behaviour of the solution and are projected until the build is delivered and measured.

  • Real time assist designed — We set out how a live call is transcribed and turned into an answer for the agent as the conversation happens.
  • Grounded in the client's knowledge — The design uses an Amazon Bedrock Knowledge Base so answers come from the client's own material rather than a generic model.
  • Clear AWS architecture — The client left the engagement with a recommended, serverless AWS approach ready to take into a build.
  • Funding identified — The engagement was scoped so that an AWS fund request could support the next phase of delivery.
  • Handover — The client's team retained a clear understanding of the design decisions and the reasoning behind them.

With a grounded design in hand, the client is positioned to give its customer service team a generative AI assistant that turns the company's own knowledge into fast, accurate answers, ready to extend to more channels and use cases over time.

AWS Stack

Amazon Transcribe

For real time conversion of live calls into text.

Amazon Bedrock

For the foundation model that composes grounded answers.

Amazon Bedrock Knowledge Bases

For retrieval over the client's own content.

Amazon S3

For durable storage of the knowledge base source documents.

AWS Lambda

For serverless orchestration between transcription and retrieval.

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.