Duco has shifted its financial data automation infrastructure to Amazon Bedrock to overcome the constraints of legacy models that required extensive historical training data. The new system integrates with frameworks such as LangChain and LangGraph while using private endpoints to guarantee that customer data never trains underlying models. By utilizing Bedrock AgentCore, the platform dynamically switches among models from providers like Anthropic and Cohere to match specific processing needs. This setup drastically lowers client onboarding costs and ensures high-volume transactions remain fully compliant with strict financial regulations.
Key points
Legacy machine learning systems have been replaced to eliminate extensive historical trai…: Legacy machine learning systems have been replaced to eliminate extensive historical training requirements and handle novel data scenarios.
Strict data isolation is maintained through private virtual private cloud endpoints that…: Strict data isolation is maintained through private virtual private cloud endpoints that prevent customer information from training provider models.
Bedrock AgentCore manages operational infrastructure and monitoring while interfacing wit…: Bedrock AgentCore manages operational infrastructure and monitoring while interfacing with existing production tools like LangChain and LangGraph.
Sources checked by our analysis pipeline: 1
Artificial Intelligence
How Duco transforms financial data automation with Amazon Bedrock AgentCore
Financial institutions face a critical challenge: processing massive volumes of data with speed, accuracy, and compliance while operating under some of the world’s strictest regulatory frameworks. Duco is the agentic Operations platform for financial services, serving tier-one banks and other financial institutions. It processes 20 billion transactions monthly for 200+ clients, including 7 of the top 20 banks and 10 of the top 20 asset managers. To keep pace as data processing demands grew, Duco evolved from traditional machine learning models to the agentic AI capabilities of Amazon Bedrock and Amazon Bedrock AgentCore. In this post, we share how Duco rebuilt its agentic AI stack on these services, cutting deployment time and onboarding costs while keeping each bank’s data isolated.
The challenge: Scaling intelligence in a regulated environment
Duco’s platform empowers teams to automate mission-critical data processes using AI and no-code models, handling everything from data extraction to downstream publication. It already used traditional machine learning models for predictive labeling and pattern recognition, helping banks consolidate and automate…
Faced with nearly 30 disconnected source systems and tens of thousands of tables, enterprise teams often spend years on manual preparation before enabling analytics. To bypass this bottleneck, IFS Copperleaf engineered an internal platform that runs natural language queries directly over raw records rather than waiting for exhaustive data cleanup. This targeted modeling approach cuts months off deployment timelines while focusing high-precision modeling strictly on mission-critical business functions.
Enterprise organizations struggle to operationalize complex artificial intelligence systems because coordination challenges, rather than flawed models, derail most initiatives. Compounded handoffs between multiple models quickly degrade overall system reliability, creating significant architectural risks. To mitigate these failures, engineers must structure agent interactions around proven orchestration patterns that maintain operational control.
Developers can now implement contextual artificial intelligence systems by linking conversation histories directly with managed knowledge stores. This integration enables an autonomous planner to extract durable facts and evaluate past user interactions alongside organizational data to refine automated queries. The resulting architecture ensures tailored responses while maintaining strict document-level security boundaries for enterprise deployments.