Case Studies | SaaS B2B

An AI tutor that stays on the syllabus

Lex Chatbot

About

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

Challenge

The proof of concept centred on four focus areas.

Staying on-curriculum and safe

A tutor must not stray beyond what it should teach. The first focus was to restrict the chatbot's answers to a curated maths curriculum using Amazon Bedrock knowledge bases, with guardrails for safe, consistent responses.

Natural, accessible interaction

Students learn in different ways. The second focus was a chatbot that handles both text and voice, powered by Amazon Lex, with a prompt-engineered tutor persona and a consistent teaching style.

Remembering the conversation

Good tutoring builds on what came before. The third focus was session memory, storing chat history so the tutor keeps context across a conversation.

A curriculum the team can manage

Content changes over time. The final focus was letting curriculum documents be uploaded and new knowledge bases created dynamically, so the client can maintain the tutor's knowledge themselves.

Solution

Cloud Combinator delivered the work in clear phases, each an agreed milestone, from automated infrastructure to a working, handed-over chatbot.

Text + voice

Chatbot handles both spoken and typed interaction

30,000/mo

Student questions the design was sized for (projected)

PoC

Proof of concept under the AWS IW Build Program

By the numbers:

  • Text + voice - Chatbot handles both spoken and typed interaction
  • 30,000/mo - Student questions the design was sized for (projected)
  • PoC - Proof of concept under the AWS IW Build Program
Changes

Cloud Combinator delivered a working proof of concept against the agreed success criteria: a text and voice Lex chatbot with session context, curriculum-restricted answers through Bedrock knowledge bases and guardrails, dynamic knowledge base management, and session tracking

  • On-curriculum by design — Bedrock knowledge bases and guardrails keep the tutor's answers within a curated maths curriculum, with a consistent teaching approach.
  • Voice and text — Amazon Lex lets students interact naturally in whichever way suits them, widening accessibility.
  • Conversational memory — DynamoDB-backed session tracking means the tutor remembers context across a conversation.
  • Curriculum the client can manage — An API and pre-signed uploads let the team add content and create new knowledge bases without engineering support.
  • Handover — Included a runbook, reference architecture and a knowledge-transfer session so the client can maintain and iterate on the tutor.

In DynamoDB. It was deployed via CloudFormation in the client's AWS environment and handed over with documentation and a training session.

With the concept proven on AWS, the client has a controllable, extensible foundation for its tutoring product, ready to add features such as user authentication and a production front end, and to expand the curriculum across new subjects and levels. Cloud Combinator recommended a Well-Architected Framework Review as the next step towards production.

AWS Stack

Amazon Lex

For the conversational chatbot, handling both text and voice interactions.

Amazon DynamoDB

For session history and knowledge base metadata.

AWS Lambda

For backend orchestration and dynamic knowledge base management.

Amazon S3

For storing curriculum documents and chatbot assets.

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.