Case Studies | SaaS B2B

Bridging the language gap between schools and families

AI Multilingual Parental Engagement

About

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

Challenge

The challenge had four focus areas.

Reaching families in their own language

Weekly educational summaries and content had to be delivered in multiple languages so non-English-speaking families could genuinely engage, not just receive an untranslated notification.

Personalising complex school data

Raw school data is dense and generic. Each message needed to be grounded in an individual student's profile and progress, so parents received something relevant and specific rather than a template.

Reducing dependency on OpenAI

The client's summaries were generated through OpenAI. Moving that capability to Amazon Bedrock would consolidate the platform on AWS, improve control, and prove Bedrock as a suitable replacement.

Handling sensitive data responsibly

Because the platform processes personal and educational data about children, the architecture had to be built with appropriate security, access controls and data-protection considerations from the start.

Solution

Cloud Combinator delivered the work through its structured Cloud Accelerator, combining discovery and consultancy with best-practice foundations, hands-on immersion, and a focused build in the client's AWS account.

Multilingual

Summaries in families' own languages

RAG

Personalised to each student's data

OpenAI to

Consolidated onto AWS

By the numbers:

  • Multilingual - Summaries in families' own languages
  • RAG - Personalised to each student's data
  • OpenAI to - Consolidated onto AWS
Changes

The project met its scope: a working, Bedrock-powered pipeline deployed into the client's AWS environment, demonstrating Amazon Bedrock as a suitable platform to replace OpenAI for personalised, multilingual parental communication.

  • Language no longer a barrier — Summaries are generated and translated so non-English-speaking families can engage with their child's education directly.
  • Genuinely personalised — Retrieval-augmented generation grounds every message in the individual student's data, so parents get relevant detail rather than a generic note.
  • Consolidated on AWS — The generative capability now runs on Amazon Bedrock, reducing the client's dependency on OpenAI and bringing the platform onto a single cloud.
  • Built for sensitive data — The AWS environment was set up with permissions, access controls and security suited to handling personal and educational data.
  • Handover — Through the immersion day and delivery, the client's team were left able to run and continue developing the model themselves.

With a scalable, Bedrock-powered platform live in their own AWS account, the client are positioned to grow their multilingual parental engagement offering and to demonstrate that value as they enter their next phase.

AWS Stack

Amazon Bedrock

For the generative AI that produces personalised, multilingual summaries.

Amazon S3

For secure storage of student data and school content.

AWS Lambda

For the serverless compute that orchestrates the pipeline.

AWS Identity

And Access Management for permissions and access controls around sensitive data.

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.