Case Studies | FinTech

A personalised assistant for every customer

Onboarding Chatbot with Knowledge Base

About

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

Challenge

The proof of concept concentrated on three focus areas.

Personalising to each customer

The chatbot needed to give advice tailored to the individual customer, drawing on the specific documents the client had produced for them rather than a single shared source.

Grounding answers in trusted documents

In a compliance context, answers cannot be invented. The assistant had to base its responses on the client's own material, so guidance stayed accurate and defensible.

Making it natural to use

Onboarding customers should be able to ask questions in plain language and get helpful, conversational answers, so the experience felt like guidance rather than search.

Solution

The assistant combines Amazon Lex, which handles the conversational interface and understands what the customer is asking, with an Amazon Bedrock Knowledge Base that holds each customer's documents. When a question comes in, the relevant material is retrieved from the knowledge base and used to ground the response.

Changes

The engagement delivered a designed proof of concept and a solution architecture for a personalised, document-grounded onboarding chatbot built on AWS AI services. The results below describe the intended outcomes of the build rather than measured production performance.

  • Personalised guidance — A design that tailors answers to each customer using their own the client's documents.
  • Document-grounded answers — Responses grounded in trusted material through an Amazon Bedrock Knowledge Base, keeping advice accurate.
  • A natural interface — An Amazon Lex conversational layer so customers can ask in plain language.
  • A clear route to production — A proof of concept scoped so the client can validate the experience before rolling it out across customers.
  • Handover — A documented solution architecture that the client can take forward into a production build.

With a working pattern for a document-grounded, personalised assistant, the client has a foundation it can extend beyond onboarding, applying the same combination of conversational AI and a customer-specific knowledge base wherever customers need fast, trustworthy guidance.

AWS Stack

Amazon Lex

For the conversational interface and understanding customer questions.

Amazon Bedrock Knowledge Bases

For grounding answers in each customer's own documents.

Amazon Bedrock

For generating tailored, document-backed responses.

Amazon S3

For storing the customer documents that populate the knowledge base.

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.