Case Studies | SaaS B2B

From energy bill to carbon report

AI Carbon Reporting Platform

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, each essential to a platform that regulators and customers could trust.

Reading complex documents accurately

Energy bills and contracts arrive in every imaginable format. The first focus was extracting the right information from that unstructured content reliably, and reducing the client's reliance on third-party models by proving an AWS-native approach.

Multi-tenancy and enterprise security

The platform holds and exports regulated data for many organisations. The second focus was a secure, multi-tenant foundation, with per-tenant data isolation, proper account structure and cost attribution, fit for the security expectations of regulatory reporting.

Turning energy data into carbon results

Extraction is only the start. The final focus was standardising and transforming the extracted data into carbon footprint results and multiyear estimates, then serving those results to web and mobile users and onward to regulatory systems.

Solution

We delivered the platform as a set of workstreams, each building on the last, under the AWS accelerator programmes.

Multi-

Per-tenant isolation for regulated customer data

Bedrock IDP

AWS-native intelligent document processing engine

Multiyear

Carbon footprint and energy estimates produced

By the numbers:

  • Multi- - Per-tenant isolation for regulated customer data
  • Bedrock IDP - AWS-native intelligent document processing engine
  • Multiyear - Carbon footprint and energy estimates produced
Changes

The engagement delivered the AWS foundations of the client's carbon reporting platform. It proved that an AWS-native document processing engine could extract data from complex energy documents, stood up a secure multi-tenant environment fit for regulated data, and connected

  • AWS-native extraction proven — Data could be extracted from energy bills using Amazon Bedrock, reducing the client's reliance on third-party models.
  • Secure foundation delivered — A Control Tower account structure, secure S3 and a per-tenant DynamoDB model gave the platform the isolation and security regulated reporting demands.
  • End-to-end path connected — The flow from uploaded bill through extraction, standardisation and calculation to a served result was wired together on AWS.
  • Handover — The client left the engagement with a running AWS environment, an upskilled internal tech lead and a Well-Architected review of the stack, ready to continue developing the product.

Extraction through to carbon calculation and a served frontend, validating AWS as the platform on which the client could continue to build.

With the foundations in place, the natural next steps (projected) would be to broaden the range of document types the engine handles, deepen the carbon calculation logic, and scale the multi-tenant platform as the client onboards more organisations onto its reporting service.

AWS Stack

Amazon Bedrock

For the large language model at the heart of intelligent document processing.

Amazon Textract

For optical character recognition of energy bills and contracts.

Amazon Comprehend

For entity and phrase extraction from the recognised text.

Amazon DynamoDB

For the multi-tenant data model, isolated per tenant.

AWS Lambda

For the serverless steps that ingest, extract, transform and serve data.

Amazon API Gateway

For accepting documents and data from the client's application.

AWS Amplify

For hosting the web and mobile frontend.

Amazon S3

And AWS Control Tower for secure storage and governed, multi-account structure.

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.