Case Studies | FinTech

The platform for financial crime teams

A FinTech client

About

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

Challenge

The engagement centred on three focus areas that a compliance-grade assistant had to satisfy.

Ingesting diverse and messy data

Compliance data arrives in many shapes, from structured records in CSV, JSON, RDS and MongoDB to unstructured documents in PDF, HTML and XML. The platform needed a flexible ingestion pipeline that could turn all of it into a queryable, structured form the AI could reason over reliably.

Answering relationship questions

The hardest compliance queries are about connections: family ties, business associations and geographic links between entities. Answering questions such as "show me all associated individuals with this person" or "identify recent sanctions related to this region" requires a graph model, not just document search.

Serving many tenants and data sensitivities

The system had to handle both public reference data, such as sanctions lists, and customer-specific data, such as internal policies and watchlists, side by side. Multi-tenant support with clear separation was essential so the same platform could serve different regulatory contexts and customers safely.

Solution

Cloud Combinator offered the client two delivery models for the MVP, so the client could choose the balance of speed and in-house capability that suited them. Both routes deliver the same target architecture on AWS and both include a structured handover.

2 months

Target to MVP staging release (projected)

250

Peak daily users targeted at launch (projected)

2,000

Monthly users targeted (projected)

By the numbers:

  • 2 months - Target to MVP staging release (projected)
  • 250 - Peak daily users targeted at launch (projected)
  • 2,000 - Monthly users targeted (projected)
Changes

The proposal defined a clear target for the MVP: a working the platform integrated with FacctList, with a staging release inside roughly two months and production hardening over six. The figures below are the design targets agreed in scoping, not measured results, and success KPIs such as analyst efficiency gains were to be finalised with the client.

  • A designed, AWS-native architecture — A reference architecture built on Amazon Bedrock, Amazon Neptune and a flexible ingestion pipeline, ready to move into implementation.
  • Relationship-aware querying — A graph-RAG design over Amazon Neptune so analysts can answer complex association and sanctions questions, not just keyword lookups.
  • A route that fits the client — Two costed delivery models, build-and-transfer or joint-build-and-mentor, letting the client choose speed or in-house capability.
  • A fundable path — An engagement structured to leverage AWS Partner funding programmes, with the potential for a significant share of infrastructure cost to be offset once the pricing calculator is finalised.
  • Handover — Both delivery routes include a structured knowledge transfer, with workshops, run-books, backlog and roadmap, so the client can own and evolve the platform.

With the MVP scoped around FacctList, the design leaves a clear runway to extend the platform across FacctView and FacctGuard, turning a focused first integration into a compliance platform that can grow with the client's product suite and its customers' regulatory needs.

AWS Stack

Amazon Bedrock

For deploying and managing the generative AI models behind the compliance agents.

Amazon Neptune

For modelling and querying entity relationships with a graph-RAG pattern.

Amazon Textract

For parsing unstructured compliance documents into usable data.

AWS Glue

And AWS Lambda for the extract-transform-load pipeline that structures diverse data formats.

AWS IAM

And AWS KMS for tenant isolation, access control and encryption across the platform.

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.