Case Studies | FinTech

A multi-agent AI customer support system, built on AWS

AI Customer Support Agent

About

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

Challenge

The challenge had three focus areas.

A wide range of enquiries to handle

Support spanned payment transactions, account management, merchant onboarding, cash rewards and technical troubleshooting. Answering all of it consistently through a single, generic channel was hard, and routine questions consumed time that could go to complex cases.

Round-the-clock, multilingual demand

A global customer base means questions arrive at all hours in many languages. Meeting that with people alone means either slow responses or a support headcount that grows in lockstep with the customer base.

Escalation without losing context

When an issue genuinely needs a human, the handoff has to carry the full context and a recommended path, so customers do not repeat themselves and agents resolve faster. Getting that escalation right was central to the design.

Solution

Rather than one general chatbot, the system uses a set of specialised agents, each focused on a domain: a Payment Support agent for transactions and refunds, a Merchant Onboarding agent for integration and setup, a Cash Rewards agent for balances and redemptions, a Technical Troubleshooting agent for open banking and app issues, and a General Inquiry agent for account management and routing. An orchestration layer classifies each incoming request, routes it to the right agent, and manages handoffs between them.

5

Specialised support agents across the key enquiry domains

24/7

Multilingual coverage without proportional staffing growth

$2.2k

Projected monthly AWS running cost at design volume (projected)

By the numbers:

  • 5 - Specialised support agents across the key enquiry domains
  • 24/7 - Multilingual coverage without proportional staffing growth
  • $2.2k - Projected monthly AWS running cost at design volume (projected)
Changes

Cloud Combinator delivered the multi-agent system with its specialised agents implemented, an end-to-end orchestration workflow, and the infrastructure provisioned as code, tested through unit, integration and user acceptance testing, and accompanied by documentation and knowledge transfer for the client's team.

  • Specialised agents — Five domain agents, from payment support to technical troubleshooting, each tuned to its area rather than one generic responder.
  • Orchestration and routing — An orchestration layer classifies intent, routes to the right agent, and coordinates handoffs end to end.
  • Memory with AgentCore — Amazon Bedrock AgentCore retains conversation context and condensed insight from past interactions for coherent, informed responses.
  • Context-rich escalation — Defined escalation rules pass complex issues to human agents with full context and a recommended resolution.
  • Handover — Infrastructure-as-code, technical documentation, and knowledge transfer through recordings and workshops for the client's team.

With the system built, tested and handed over to run in its own AWS environment, the client has a scalable support foundation, ready to absorb peaks in demand and to extend with new agents and integrations as the network grows.

AWS Stack

Amazon Bedrock

For the language understanding behind the support agents.

Amazon Bedrock AgentCore

For multi-agent orchestration with conversation and long-term memory.

AWS Lambda

For serverless compute running the agent functions.

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.