Case Studies | SaaS B2B

Automating threat intelligence reporting on AWS

GenAI Report Creation

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.

Collating fragmented third-party data

Threat intelligence on a given incident arrives from several external services, each with its own shape. Bringing those sources together into one coherent picture by hand was slow and did not scale with the product.

Turning data into a readable report

Users needed a collated, plain-language report they could act on, not a wall of raw indicators. The tool had to reason over the incident context and produce something genuinely useful.

Generating reports cost-effectively at volume

With reporting sized for around 10,000 incidents a month, uncontrolled large language model usage would have made the feature uneconomic. Prompt design and request throttling had to keep cost predictable.

A deployable, self-owned solution

The client needed the finished pipeline to run in their own AWS environment, reproducible through infrastructure as code, with their engineers confident enough to continue developing it.

Solution

Cloud Combinator delivered the work through its structured Cloud Accelerator, combining discovery, best-practice foundations, hands-on immersion for the client's team, and a focused build.

10,000

Reports per month at design capacity

100%

Serverless, event-driven architecture

CloudFormation

One-command, repeatable deployment

By the numbers:

  • 10,000 - Reports per month at design capacity
  • 100% - Serverless, event-driven architecture
  • CloudFormation - One-command, repeatable deployment
Changes

The project met its scope: a working, production-ready reporting pipeline deployed into the client's own AWS environment, proving Amazon Bedrock and AWS as the right foundation to continue building the client's product.

  • Automated collation — Fragmented third-party threat data is now pulled together automatically, removing the manual step of stitching sources into a report.
  • On-demand reports — Each incident produces a collated, readable report saved to Amazon S3 and available to users on demand.
  • Cost kept in check — Deliberate prompt design and a SQS buffer keep large language model usage predictable and within limits at volume.
  • Infrastructure as code — The whole stack is defined in CloudFormation, so the client can redeploy and update the solution simply and consistently.
  • Handover — Through the immersion day and demo, the client's engineers were left with a clear understanding of the design decisions and the confidence to extend it, including continued model work in Amazon SageMaker.

With the pipeline live in their own account and their team upskilled, the client are positioned to grow the reporting capability alongside their product, turning more of their threat signal into intelligence their users can act on.

AWS Stack

Amazon API Gateway

For a managed entry point that receives incident events.

Amazon SQS

For buffering requests and keeping the pipeline within model usage limits.

AWS Lambda

For serverless compute that assembles the prompt and orchestrates the flow.

Amazon Bedrock

For the large language model that generates the collated report.

Amazon S3

For durable, low-cost storage of the generated reports.

AWS CloudFormation

For repeatable, infrastructure-as-code deployment into the client's account.

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.