Case Studies | FinTech

Building a Secure EU-Hosted Multi-Agent Finance Assistant on AWS

Incard
About

The client is a UK fintech platform for fast-growing digital businesses, combining business banking, corporate cards, payments and financial insight in one place.

Challenge
  • The client needed a production-grade pattern for business actions like creating a spending category or a rule, where every action had to be previewed, confirmed and logged for full traceability.
  • EU-region data residency, operational resilience and observability all had to be strengthened before the concept could move toward production.
  • As a financial product, the system needed defence-in-depth security and data protection suitable for regulated use.
Solution

Cloud Combinator built a multi-agent system on Amazon Bedrock, deployed in eu-west-2 (London) via Terraform, with an orchestration agent routing requests to specialist agents that turn plain-English requests into validated, previewable operations.

By the numbers:

  • Moved from ad-hoc prototype to a typed, auditable agent pattern
  • EU data residency met via eu-west-2 hosting
  • Reusable Agent to OpenAPI to Lambda to Data blueprint for future use cases

What changed:

  • A request like creating a new spending category is routed to a specialist agent, converted into a structured operation via OpenAPI, previewed for the user, and only written once confirmed, with the full trace visible in CloudWatch.
  • All AWS Lambda functions run in private subnets with least-privilege IAM roles; secrets and logs are encrypted with AWS KMS; and Amazon Bedrock's content filtering is tuned specifically for finance, including PII handling.
  • Cloud Combinator delivered a full technical handover, OpenAPI contracts, agent prompts, runbooks and security playbooks, so the client's team can extend the pattern to new use cases like reconciliation or anomaly review without changing the core architecture.
AWS Stack

Amazon Bedrock

Multi-agent orchestration and specialist agents for category and rule creation.

AWS Lambda

Deterministic execution of validated, structured operations.

AWS KMS & Amazon VPC

Encryption and private networking for finance-grade security.

Incard

Cloud Combinator impressed us with their ability to take complex requirements and translate them into a secure, production-ready design on AWS.

Incard

Client feedback

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.