Case Studies | SaaS B2B

Automating pothole damage claims with AI

LLM Processing of Car Damage

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.

Reading evidence automatically

Every claim starts with a number plate image and a garage receipt. Pulling the vehicle and cost details out of those images by hand is slow and error-prone, so the service needed to extract them automatically and enrich them from authoritative sources.

Routing each claim to the right council

A claim is only valid against the authority responsible for that stretch of road. The system had to identify the correct council from a postcode or set of coordinates before a single letter was written.

Chasing claims without manual effort

Councils often do not respond quickly. The client needed automatic, escalating follow-up letters when a claim went unanswered, rather than someone tracking dates in a spreadsheet.

Capturing data to build on

Beyond winning individual claims, the client wanted every interaction stored in a structured way, so future features and analytics could be built on a growing base of claim data.

Solution

Cloud Combinator designed the solution as a set of connected workflows, each deployable via CloudFormation, that together carry a claim from first upload to final outcome.

End-to-

From first upload to final response

2-week

Automated follow-up cadence

CloudFormation

Repeatable, self-owned deployment

By the numbers:

  • End-to- - From first upload to final response
  • 2-week - Automated follow-up cadence
  • CloudFormation - Repeatable, self-owned deployment
Changes

The project met its scope: a working, end-to-end AI claims service deployed into the client's AWS environment, proving Amazon Bedrock and AWS as the right foundation to continue building the product.

  • Automated evidence extraction — Number plates and garage receipts are read automatically with Amazon Textract and enriched from authoritative vehicle and council sources.
  • Correct council, every time — A postcode or coordinate lookup identifies the responsible authority before a claim letter is drafted.
  • Hands-off chasing — EventBridge and Bedrock generate escalating follow-up letters automatically when a council does not respond, with SQS keeping model usage within limits.
  • Data built for growth — Every interaction is captured in Amazon RDS and S3, giving the client a structured foundation for future features and analytics.
  • Handover — The solution is defined in CloudFormation and delivered with a demo and explanation, so the client can deploy, run and extend it, including continued model work in Amazon SageMaker.

With an automated claims engine live in their own account and data accumulating with every claim, the client are positioned to scale their service and build new products on the foundation the engagement put in place.

AWS Stack

Amazon Cognito

For secure user authentication.

AWS Lambda

For the serverless compute that orchestrates each step of a claim.

Amazon Textract

For extracting details from number plate images and garage receipts.

Amazon Bedrock

For the large language model that drafts claim and follow-up letters.

Amazon EventBridge

For scheduling automated checks on unanswered claims.

Amazon SQS

For buffering requests and keeping model usage within limits.

Amazon SES

For sending letters to councils and receiving their responses.

Amazon RDS

And Amazon S3 for structured claim data and image storage.

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.