LIVE

Duco Upgrades Financial Data Platform to Amazon Bedrock AgentCore

🔌 Chips & Hardware 2 min read 👁 10

Financial operations platform Duco has rebuilt its AI stack using Amazon Bedrock and AgentCore to improve transaction processing and data isolation for major banks.

Duco Upgrades Financial Data Platform to Amazon Bedrock AgentCore🔌Chips & Hardware

Photo: AWS Machine Learning Blog

Key points

  • Duco processes 20 billion monthly transactions for over 200 financial clients.
  • The platform migrated from classical machine learning to Amazon Bedrock and AgentCore.
  • Strict multi-tenant isolation ensures separate data contexts for each bank.

Financial operations platform Duco has overhauled its artificial intelligence infrastructure, migrating to Amazon Bedrock and Amazon Bedrock AgentCore to handle large-scale data automation for tier-one banks and asset managers. The company currently manages 20 billion transactions every month for over 200 clients, including seven of the top twenty global banks. By upgrading its systems, Duco aims to accelerate deployment times and lower onboarding costs while maintaining strict data separation between different financial institutions.

Previously, Duco relied on traditional machine learning models for predictive labeling and pattern recognition to automate more than 20,000 workflows. According to Chief Architect and Innovation Officer Rob Gates, those classical models lacked the agility required to handle changing business rules and novel scenarios without extensive historical training data. To overcome these limitations, the company adopted Amazon Bedrock for managed access to foundation models and AgentCore to scale its autonomous agents.

The updated architecture integrates closely with Duco's existing setup using LangChain and LangGraph. It enforces strict multi-tenant isolation through identity authentication and infrastructure controls, ensuring that each client's data and context remain completely separate. Furthermore, the platform employs a multi-model strategy, assigning specific tasks to the most suitable foundation model to optimize both performance and cost efficiency.

What to watch next: Monitor how financial technology providers adopt multi-agent architectures for regulatory compliance and secure enterprise data handling.

Source AWS Machine Learning Blog — aws.amazon.com/blogs/machine-learning/how-duco-transforms-financial-dat… ↗

Contact the newsroom

Got a tip, a proposal or a partnership question? Write to us and we will reply shortly.