Case Studies | SaaS B2B

Personalised skincare, powered by generative AI

LLM Based Routine Builder

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.

Personalised recommendations from messy signals

The client needed to match each user to suitable moisturisers using a mix of structured preferences, such as ingredients to avoid, skin type and concerns, alongside behavioural data like clicks and reviews. The recommendation had to reflect all of those at once and be returned in a clean, machine-readable form the platform could consume.

Safe and guarded use of a LLM

Exposing a language model to end users introduces risk. The service needed pre and post screening around every model call, with guardrails in place to prevent misuse and to keep outputs on-topic and appropriate before anything reached a customer.

A secure, repeatable deployment the client could own

This was not a throwaway demo. The proof of concept had to run inside a Virtual Private Cloud, support timed reindexing of the product data, and deploy cleanly into the client's own AWS environment so the team could continue development after handover.

Solution

Cloud Combinator ran the work through its AI and ML Project Accelerator, a staged path that pairs a focused technical build with knowledge transfer to the client's own team.

500

Moisturisers indexed in the proof of concept catalogue

35k

Monthly users the service was sized to serve (projected)

JSON

Structured, platform-ready recommendation output

By the numbers:

  • 500 - Moisturisers indexed in the proof of concept catalogue
  • 35k - Monthly users the service was sized to serve (projected)
  • JSON - Structured, platform-ready recommendation output
Changes

The proof of concept met its acceptance criteria. It demonstrated that Amazon Bedrock and a LLM could generate personalised skincare recommendations from the client's data, delivered them in the required JSON format, and proved that AWS is a suitable environment for the continued development of the client's AI products.

  • Personalisation proven — The service turned each user's preferences, skin type, concerns and behaviour into a tailored product recommendation.
  • Guardrails in place — Pre and post screening around every model call kept the LLM's use safe and on-topic before results reached a customer.
  • Deployed in the client's account — The solution was delivered into the client's own AWS environment inside a VPC, with timed reindexing of the product data.
  • Handover — The service was packaged as a CloudFormation template with guidance and an immersion day, leaving the client's team able to run and extend it.

With the core capability proven, the client has a clear, costed path to widen the approach beyond moisturisers to its full product range and to move from proof of concept toward a production recommendation service on AWS.

AWS Stack

Amazon Bedrock

For the knowledge base and large language model that generate the recommendations.

AWS Lambda

For the serverless logic that screens prompts, calls the model and returns results.

Amazon S3

For storing and staging the product data used to build the vector index.

Amazon VPC

For network isolation and security around the service.

AWS CloudFormation

For repeatable deployment into the client's own AWS environment.

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.