Case Studies | SaaS B2B

Reading legal documents at machine speed

AI Legal Document Extraction Platform

About

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

Challenge

The project concentrated on three focus areas.

Extracting the right information reliably

Legal documents are dense and every matter has its own essentials. The platform had to extract and summarise information against the client's pre-determined criteria, returning answers a professional could trust rather than a loose summary.

Scaling to real legal volumes

The design target was significant: over 10,000 PDFs a day, averaging 15 pages, once scaled. An architecture that worked on a handful of documents but buckled at that volume would not have served the business, so scalability was a first-class concern.

Delivering a clean, ownable platform

The client wanted a standalone AI platform they could take forward, delivered with a documented GitHub repository and a demonstration, so their technical lead could continue development after handover.

Solution

Cloud Combinator delivered the platform through a six-stage accelerator, taking the client from discovery to a running solution in their own AWS account, with the skills to keep building.

10,000/day

Documents targeted at full scale (projected)

15 pages

Average document length handled

JSON

Structured output returned per document

By the numbers:

  • 10,000/day - Documents targeted at full scale (projected)
  • 15 pages - Average document length handled
  • JSON - Structured output returned per document
Changes

Acceptance was defined around the Cloud Accelerator Program: sign-off on the delivery scope, confidence in the client's internal technical lead, and confirmation that the platform on AWS

  • An event-driven extraction pipeline — Documents in S3 trigger Lambda extraction and Bedrock analysis, with no manual step in the middle.
  • Criteria-based answers — A design that returns the essential information against the client's own pre-determined criteria, as structured JSON.
  • Built to scale — An architecture designed around the client's anticipated volume of over 10,000 documents a day.
  • A platform they own — A standalone AI platform handed over with a fully documented GitHub repository and a working demonstration.
  • Handover — An immersion day, a documented codebase and a Well-Architected Framework Review, so the internal tech lead can continue development.

Bedrock met the original scope and demonstrated Bedrock as a suitable environment to continue developing the client's platform. The figures below are the design and scale targets set in scope.

With a working extraction platform and Bedrock proven as the right environment, the client were positioned to fold AI summarisation into their case-management product and take back time their legal professionals would otherwise spend reading and meeting.

AWS Stack

Amazon S3

For secure storage of legal documents, triggering the extraction flow on upload.

AWS Lambda

For serverless information extraction and for data transfer and packaging between steps.

Amazon API Gateway

For submitting documents to the platform and returning results via an API.

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.