How Duco transforms financial data automation with Amazon Bedrock AgentCore
Machine Learning Blog
This article describes how Duco, an agentic operations platform for financial services, transformed its AI infrastructure by adopting Amazon Bedrock and Bedrock AgentCore to automate mission-critical financial data processes at scale.
- Duco processes 20 billion transactions monthly for 200+ clients including top-tier banks and asset managers
- Migrated from classical machine learning to agentic AI for greater flexibility and adaptability to evolving financial data formats
- Implemented strict per-tenant isolation using dedicated AWS services, VPC networking, and tenant-scoped authentication for regulatory compliance
- Deployed multi-model strategy assigning different foundation models (Claude Opus, Sonnet, Haiku, Nova 2) to specific agent roles
- Reduced context overhead by 90% through MCP skills architecture that loads tool descriptions on-demand rather than statically
- Achieved 10× faster reconciliation deployments, 70% onboarding cost reduction, and 20%+ increase in straight-through processing
- Implemented dynamic MCP tool discovery enabling new capabilities without agent redeployment or reconfiguration
Duco's architecture demonstrates that production-scale agentic AI is viable in regulated financial services when built with strict isolation, compliance controls, and intelligent resource management.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
2026
2026
2026
2026
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.