Case Studies | SaaS B2B

Ranking eSIM plans with generative AI

Bedrock Knowledge Base eSIM Recommendation

About

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

Challenge

The proof of concept set out to answer three questions.

No automated ranking

New eSIM plans flowed into the client's systems with no automatic way to order them. The first focus was to rank plans by price for a given country so the best options could be shown to customers in the app.

Keeping rankings current

Plan inventory is not static. The second focus was to make sure the ranking stayed accurate as plans were added, removed or repriced, by reindexing the underlying data whenever it changed.

Proving the approach

Before committing to production, the client wanted evidence that an Amazon Bedrock Knowledge Base could ingest their plan data and produce reliable, country-specific rankings. The final focus was a clean, demonstrable proof of concept.

Solution

The client's plan data is held in an Amazon RDS for PostgreSQL database. When an administrator adds or updates a plan through an Amazon API Gateway request, an AWS Lambda function reindexes the Amazon Bedrock Knowledge Base so it reflects the latest inventory, then notifies the administrator once reindexing is complete.

Per country

ESIM plans automatically ranked by price for each country

Auto

Knowledge Base refreshed when plans are added, removed or repriced

PoC

Proof of concept validating Bedrock Knowledge Base ranking

By the numbers:

  • Per country - ESIM plans automatically ranked by price for each country
  • Auto - Knowledge Base refreshed when plans are added, removed or repriced
  • PoC - Proof of concept validating Bedrock Knowledge Base ranking
Changes

Cloud Combinator delivered a working proof of concept that met the success criteria: an Amazon Bedrock Knowledge Base that ingests the client's eSIM plan data and ranks plans by price for a given country, and that can be reindexed whenever stock or pricing changes. The build was deployed with a demonstration and documentation, ready for the client to consider taking into production.

  • Price-ranked plans — The Knowledge Base returns eSIM plans ordered by price for a given country, ready to surface the best value options to customers.
  • Always current — Reindexing on every change keeps rankings aligned with live inventory and pricing, with no manual intervention.
  • Serverless and self-contained — Lambda, API Gateway and SQS keep the pipeline lightweight, event-driven and simple to operate.
  • Proven and portable — Built to run in the client's own AWS environment in the London Region, giving them a clear path from proof of concept to production.
  • Handover — Included a demonstration of the workflow and the materials and documentation needed to run and extend the service.

With the concept proven, the client has an evidence-based foundation for taking AI-driven plan ranking into production, integrating it into their app and extending the approach to rank plans on attributes beyond price as the product grows.

AWS Stack

Amazon RDS

For PostgreSQL for storing the eSIM plan catalogue.

AWS Lambda

For reindexing the Knowledge Base and orchestrating the ranking workflow.

Amazon API Gateway

For administrator updates and ranking requests.

Amazon SQS

For controlled, throttled processing that stays within service limits.

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.