Case Studies | SaaS B2B

Turning annual reports into answers

Document Querying IW Build

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.

Making unstructured filings queryable

Annual reports are long, inconsistent PDFs. The service needed to ingest this documentation into AWS, structure it for retrieval and make it searchable by natural-language question rather than by keyword.

Choosing the right AWS approach

Two credible designs existed, one built on Amazon Q with Amazon QuickSight for visual exploration, the other on Amazon Bedrock Knowledge Bases with a vector database queried through an API. Each carried different trade-offs in cost, control and user experience, so the right choice needed to be proven rather than assumed.

Fitting the members' product

Whatever was built had to deploy into the client's own AWS account and integrate cleanly with their member-facing product, leaving the internal team able to operate and extend it.

Solution

We ran the engagement through our Cloud Accelerator, a staged programme that moves from understanding the product to a working deliverable in the client's own account.

2

Candidate architectures built and evaluated

6

Stage guided accelerator, discovery to delivery

~$1,550

Projected monthly AWS run cost (projected)

By the numbers:

  • 2 - Candidate architectures built and evaluated
  • 6 - Stage guided accelerator, discovery to delivery
  • ~$1,550 - Projected monthly AWS run cost (projected)
Changes

Both proposed architectures were built and assessed against real member queries. The engagement delivered a working document querying service into the client's AWS environment, along with a clear, evidence-based recommendation on which design to take forward.

  • Two designs, one recommendation — We built and tested both the Amazon Q and Amazon Bedrock approaches, so the platform choice was made on evidence rather than assumption.
  • Natural-language access to filings — Members can query annual reports directly for details such as ESG progress, instead of reading documents end to end.
  • Deployed in their own account — The solution was stood up inside the client's AWS environment, ready to integrate into the member product.
  • Best practice from the start — Security, billing and recovery baselines were put in place during the build rather than retrofitted later.
  • Handover — We provided a Loom walkthrough and a live demo handover, leaving the client's technical lead able to operate and extend the service.

With a proven querying service and a hardened AWS foundation in place, the client is positioned to widen its document library and layer further AI-driven member services on top of the same architecture.

AWS Stack

Amazon S3

For secure, scalable storage of the annual report library.

Amazon Bedrock

For large language model querying against a vector knowledge base.

Amazon Q

For managed, generative question answering over the document set.

Amazon QuickSight

For visualising query results for members.

Amazon API Gateway

And AWS Lambda for serverless, on-demand query handling.

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.