{
  "id": 20341069,
  "title": "How Duco transforms financial data automation with Amazon Bedrock AgentCore",
  "url": "https://urgent.news/2026/11/16/how-duco-transforms-financial-data-automation-with-amazon-bedrock",
  "topic": "ai",
  "section": "AI",
  "published": "2026-11-16T22:06:08.000Z",
  "source": {
    "name": "AWS Machine Learning",
    "slug": "aws-machine-learning",
    "url": "https://aws.amazon.com/blogs/machine-learning/how-duco-transforms-financial-data-automation-with-amazon-bedrock-agentcore/"
  },
  "original_language": "en",
  "account": "Financial institutions are tasked with the challenge of processing large amounts of data quickly, accurately, and in compliance with strict regulations. Duco, a platform for financial services, serves over 200 clients, including some of the world's top banks and asset managers. To handle growing data processing demands, Duco transitioned from traditional machine learning models to the agentic AI capabilities of Amazon Bedrock and Amazon Bedrock AgentCore. This post will detail how Duco rebuilt its agentic AI stack using these services, resulting in reduced deployment time and onboarding costs while maintaining data isolation for each bank. The primary challenge Duco faced was scaling intelligence in a regulated environment. Their traditional machine learning models for predictive labeling and pattern recognition were limited by the need for extensive historic data, difficulty adapting to new scenarios, and the inability to quickly customize for new use cases. Most importantly, they couldn't adapt quickly to the diverse, constantly changing data formats and business rules that characterize modern financial operations. Rob Gates, Duco's Chief Architect and Innovation Officer, noted that while traditional models worked to some extent, they lacked agility and flexibility. The solution Duco chose was to adopt Amazon Bedrock for managed access to foundation models and Amazon Bedrock AgentCore for running agents at scale. This decision represented a significant shift in how the system could understand, reason about, and act on financial data. Amazon Bedrock is a fully managed service offering high-performing foundation models from leading AI companies via a single API. It includes a broad set of capabilities for building generative AI applications, with a focus on security, privacy, and responsible AI. Bedrock AgentCore is the platform for building, connecting, and optimizing AI agents at scale. It allows integration with open-source frameworks and models, provides built-in authentication and access controls, and offers monitoring and improvement capabilities in production. Amazon Bedrock's suitability for Duco's financial services environment came down to several factors. Security and compliance were paramount, as customer data must remain within the AWS environment and not be used for model training. Private endpoints in a VPC ensure complete isolation of internal systems, which is crucial for sensitive financial data processing. Model flexibility was another key benefit, as Bedrock provides access to leading foundation models from various providers through a single API, allowing Duco to choose the right model for each task. Built specifically for financial services, Bedrock offers robust governance controls and compliance frameworks, eliminating infrastructure complexity while maintaining the necessary security standards for tier-one banks. AgentCore was chosen as the runtime for Duco's agentic workloads due to its compatibility with existing LangChain and LangGraph code, a fully managed runtime reducing operational overhead, and suitability for regulated environments with built-in security and compliance controls. Additionally, AgentCore's multi-tenant architecture ensures isolation by design, using Amazon EKS clusters with namespace-per-tenant isolation and network segregation. Each tenant receives a dedicated set of AWS services, including databases, storage, encryption keys, messaging stacks, caching layers, and user pools, with zero shared data infrastructure across clients.",
  "summary": "Duco, a data automation platform for tier-one banks, rebuilt its agentic AI stack on Amazon Bedrock and Amazon Bedrock AgentCore. With strict per-tenant isolation, a multi-model strategy, and an MCP skills architecture that cut context overhead by 90%, Duco cut reconciliation deployment time 10x and onboarding costs 70%.",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}