Case Studies | SaaS B2B

The right answer in an emergency

RAG Emergency Document Search

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 critical to a tool staff could rely on when it matters most.

Speed when it counts

In an emergency, time is everything. The first focus was making essential information, such as fire drill and evacuation guidance, retrievable in seconds through a simple natural-language query.

Grounded in the client's own documents

Generic answers are not good enough for safety-critical guidance. The second focus was grounding the search in the client's own documents using a vector database and retrieval augmented generation, so answers come from the correct, current source material.

Right information, right person

Staff should only see what applies to their role and location. The final focus was role and location-based access control, and syncing the client's data from Azure Blob Storage into AWS so the search always worked from the right content.

Solution

The client's documents are synchronised from Azure Blob Storage into Amazon S3 and indexed into a vector database. This gives the search a grounded, up-to-date body of the organisation's own emergency and operational content to draw on.

RAG

Retrieval augmented search grounded in the client's documents

Role +

Access segregation so staff see only what applies

Azure to

Documents synchronised into the search from Azure Blob

By the numbers:

  • RAG - Retrieval augmented search grounded in the client's documents
  • Role + - Access segregation so staff see only what applies
  • Azure to - Documents synchronised into the search from Azure Blob
Changes

The engagement delivered the back end for the client's retrieval augmented document search. It proved that staff could ask a natural-language question and get an accurate answer drawn from the client's own documents, with access controlled by role and location and data kept in step across Azure and AWS, validating AWS as a suitable platform for continued development.

  • Fast retrieval proven — Emergency and fire drill information could be surfaced quickly through a natural-language query.
  • Grounded answers — A vector database and large language model on Amazon Bedrock, or Amazon Q, returned answers from the client's own source documents.
  • Access controlled — Amazon Cognito enforced role and location-based user segregation across the search.
  • Handover — The client left the engagement with a working retrieval back end, an Azure-to-AWS data sync and an upskilled internal tech lead ready to continue development.

With the retrieval back end in place, the natural next steps (projected) would be to broaden the document set behind the search, deepen the front-end experience for staff on site, and harden the solution to a full production standard through a Well-Architected review.

AWS Stack

Amazon S3

For storing the synchronised document set.

Amazon Cognito

For role and location-based user segregation.

AWS Lambda

For the pipeline that ties the services together and connects to the front end.

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.