How Duco transforms financial data automation with Amazon Bedrock AgentCore
Duco rebuilt its financial‑data automation platform on Amazon Bedrock and Bedrock AgentCore, moving from traditional ML models to managed foundation models and scalable agents. The shift enabled the processing of 20 billion transactions per month for 200+ clients—including 7 of the top 20 banks—while keeping each bank’s data isolated and compliant. By leveraging Bedrock’s private VPC endpoints and AgentCore’s managed agent infrastructure, Duco cut deployment time and onboarding costs, allowing engineers to focus on agent logic rather than backend plumbing.
⚡ Key Takeaways
- Processes 20 billion transactions monthly for 200+ clients (including 7 top‑20 banks and 10 top‑20 asset managers).
- Uses Amazon Bedrock for managed access to foundation models and Bedrock AgentCore for scalable agent execution.
- Achieves compliance by keeping customer data within AWS and not using it to train models, with private VPC endpoints for secure internal connectivity.
- Integration is done via a single Bedrock API, allowing any open‑source framework or model to be plugged into AgentCore.
- Agents run with built‑in authentication, access controls, tracing, and evaluation, eliminating custom backend infrastructure.
🔧 Tools & Libraries
Engineers can now deploy compliant, high‑throughput AI agents for financial data pipelines without building custom model serving stacks, accelerating time‑to‑value while meeting strict regulatory requirements.
✅ Practical Steps
- Connect your data pipelines to Amazon Bedrock via its single API, ensuring VPC private endpoints for secure data flow.
- Build or import agents using any open‑source framework and register them with Bedrock AgentCore to handle scaling, authentication, and monitoring automatically.
Want the full story? Read the original article.
Read on AWS ML Blog ↗