Case Studies | FinTech

Teaching software to recognise and read a deal

Document Identification and Data Extraction

About

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

Challenge

The proof of concept concentrated on three focus areas.

Identifying the right document

Before any information can be extracted, the system has to recognise whether a document is an agreement to purchase a company. Getting that classification right is the gate for everything that follows.

Extracting the information that matters

Once a document is identified, the service needs to pull out the key pieces of information reliably, turning a dense agreement into structured data a compliance team can use.

Making it a repeatable workflow

An one-off script is not enough. The solution had to run as an orchestrated, repeatable pipeline so that identification and extraction happen the same way every time, at the volumes a compliance operation generates.

Solution

Documents enter an orchestrated workflow managed as an AWS Step Functions state machine, so each stage runs in order and the process is easy to monitor and repeat. Amazon Comprehend is used to identify and classify the document, determining whether it is the acquisition agreement the service is looking for.

Changes

The engagement delivered a designed proof of concept and a solution architecture for automated document identification and data extraction, built on AWS AI services. The results below describe the intended outcomes of the build rather than measured production performance.

  • Automated document triage — A design that recognises acquisition agreements automatically, removing a manual classification step.
  • Structured extraction — Key information pulled from identified documents with Amazon Bedrock and returned in an usable, structured form.
  • An orchestrated pipeline — An AWS Step Functions workflow that makes identification and extraction repeatable and observable.
  • A clear route to production — A proof of concept scoped so the client can validate the approach before scaling it into their compliance operation.
  • Handover — A documented solution architecture and workflow that the client can take forward into a production build.

With a working approach to identifying and reading acquisition agreements, the client has a foundation it can extend to other document types and compliance workflows, applying the same AWS-native pattern of classify, then extract, wherever manual document handling slows their teams down.

AWS Stack

Amazon Comprehend

For identifying and classifying whether a document is an acquisition agreement.

Amazon Bedrock

For reading matched documents and extracting the key information.

AWS Step Functions

For orchestrating the identification and extraction workflow as a repeatable pipeline.

Amazon S3

For storing documents as they move through the workflow.

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.