iCreatAI News
Skip to content
Trending storyWatching

Duco rebuilds its agent stack based on Bedrock AgentCore

1 reports1 sources1 days agoUpdated

Understand this story

AI overview

Financial data automation company Duco shared on the official AWS blog that it has rebuilt its agentic AI stack based on Amazon Bedrock and Bedrock AgentCore, shifting from traditional machine learning to an agent-based approach, which it says has shortened deployment time and reduced customer onboarding costs. The new architecture targets multi-tenant financial data automation: each tenant's AgentCore runtime runs in VPC network mode, with network interfaces placed in private subnets and outbound traffic controlled by security groups; high-risk operations require explicit authorization, and complex scenarios exceeding the agent's confidence threshold have an escalation path. Duco says that with Bedrock, customer data stays within the AWS environment and is not used to train models, the platform supports workloads subject to SOC 2 and DORA, and data residency controls are provided per institution.

AI overview based on source reports · Updated 1 days ago

Coverage timeline

Follow the coverage to explore different perspectives.

Nov 17
  1. AWS Machine Learning Blog
    How Duco transforms financial data automation with Amazon Bedrock AgentCore

    Duco, an agentic Operations platform serving 200+ financial institution clients and processing 20 billion transactions monthly, rebuilt its agentic AI stack on Amazon Bedrock and Amazon Bedrock AgentCore, moving from traditional machine learning to foundation-model-based agents. The architecture uses per-tenant AgentCore runtimes, Gateways and MCP servers for strict isolation, a multi-model strategy spanning Anthropic Claude Opus, Sonnet and Haiku plus Amazon Nova 2 Pro, and an MCP skills architecture that cut main context from 200,000 to roughly 20,000 tokens. Duco reports reconciliation deployments 10× faster, a 70% reduction in onboarding costs and over 20% higher straight-through processing for one global bank.

Activity for this story

Current comparable activity
5
Peak comparable activity
10Nov 17 07:00
Change in the past 24 hours
-50%

Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.