Case Studies | FinTech

Cloud Combinator + Funding Xchange (FXE): Agentic Underwriting for Commercial Lenders, Built on AWS

Funding Xchange
About

Funding Xchange is a UK SME lending marketplace connecting small businesses to more than 70 lenders through a single application, and a white-label credit decisioning provider to over 80 bank brokers and financial institutions, including tier-1 banks.

Challenge
  • Commercial lending is harder to automate than consumer lending - borrowers vary widely, and many cases sit in a grey area where real risk and legitimate mitigating factors coexist.
  • FXE needed a system that could generate genuinely useful underwriting analysis on complex cases while keeping human underwriters firmly in control of the final decision.
  • Reviewer expertise was trapped inside manually edited reports, with no way to systematically learn from the changes underwriters made.
Solution

Cloud Combinator built a multi-agent underwriting workflow on Amazon Bedrock AgentCore: a Risk Profiler classifies each application, specialist agents assess borrower, conduct, business and property factors, mixed-risk cases trigger an adversarial debate between agents, and a final Arbiter agent produces a structured verdict for human review.

By the numbers:

  • Referenced on the AWS Summit keynote stage as a flagship agentic AI example
  • Reduced manual burden on grey-area underwriting cases
  • Reviewer feedback now feeds a governed, continuously improving knowledge base

What changed:

  • Straightforward applications move through a lighter-touch path while complex cases get deeper investigation, so processing cost and time scale with case complexity rather than treating every application the same.
  • Once an underwriter reviews an AI-generated report, the platform compares the two versions, extracts the meaningful deltas, and stores them as structured, machine-readable records rather than leaving them buried in edited documents.
  • Weekly aggregation groups recurring reviewer changes into candidate rule updates, which a human must approve via Amazon SNS notification before they ever reach the tenant-scoped risk-mitigation knowledge base; the system learns from human judgement but never changes the rules on its own.
  • Tenant isolation is enforced end-to-end through Amazon Cognito, scoped IAM policies, and per-tenant DynamoDB/S3 storage, with Amazon Bedrock Guardrails, CloudWatch and X-Ray providing content safety and full auditability.
AWS Stack

Amazon Bedrock & AgentCore

Runtime and orchestration for the multi-agent underwriting workflow.

AWS Lambda

Exposes mitigation lookups and document processing as secure, auditable tools.

Amazon DynamoDB & S3

Tenant-scoped storage for risk mitigation data, reports and structured deltas.

Amazon Bedrock Guardrails, CloudWatch & X-Ray

Content safety, monitoring and end-to-end traceability.

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.