{"slug": "how-duco-transforms-financial-data-automation-with-amazon-bedrock-agentcore", "title": "How Duco transforms financial data automation with Amazon Bedrock AgentCore", "summary": "Duco rebuilt its agentic AI stack on Amazon Bedrock and Amazon Bedrock AgentCore, cutting deployment time and onboarding costs while keeping each bank's data isolated, according to an AWS blog post. Duco's platform processes 20 billion transactions monthly for more than 200 clients, including 7 of the top 20 banks and 10 of the top 20 asset managers, and has automated over 20,000 processes. Duco Chief Architect and Innovation Officer Rob Gates said classical prediction models \"weren't agile or flexible enough\" because they \"can only amplify what they've already learned.", "body_md": "## [Artificial Intelligence](https://aws.amazon.com/blogs/machine-learning/)\n\n# How Duco transforms financial data automation with Amazon Bedrock AgentCore\n\nFinancial 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.\n\n## The challenge: Scaling intelligence in a regulated environment\n\nDuco’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 over 20,000 processes.\n\nHowever, these classical machine learning approaches had inherent limitations. They required extensive historical data for training, struggled with novel scenarios, and demanded significant customization for each new use case. Most critically, they couldn’t adapt quickly to the diverse, constantly evolving data formats and business rules that characterize modern financial operations.\n\n*“The classical prediction models worked to an extent, but they weren’t agile or flexible enough. Traditional machine learning models can only amplify what they’ve already learned — they can’t help with the next step or find new problems.”*\n\n— Rob Gates, Chief Architect and Innovation Officer, Duco\n\n## The solution: Amazon Bedrock and Bedrock AgentCore\n\nDuco made a strategic decision to adopt [Amazon Bedrock](https://aws.amazon.com/bedrock/) for managed access to foundation models, and Amazon Bedrock AgentCore to run agents at scale. This was more than a technology upgrade. It was a fundamental shift in how its system could understand, reason about, and act on financial data.\n\n**About Amazon Bedrock and Bedrock AgentCore**\n\nAmazon Bedrock is a fully managed service that offers a choice of high-performing foundation models from leading AI companies through a single API, along with a broad set of capabilities to build generative AI applications with security, privacy, and responsible AI. [Learn more about Amazon Bedrock](https://aws.amazon.com/bedrock).\n\nAmazon Bedrock AgentCore is the platform to build, connect, and optimize AI agents at scale. Build with any open source framework and any model. Connect agents to your tools and data with authentication and access controls built in. Monitor and improve agents in production with tracing and evaluation. AgentCore handles the infrastructure so you focus on agent logic, not backend plumbing, and you get enterprise security and reliability without giving up open source flexibility.\n\nLearn more on the [Amazon Bedrock AgentCore](https://aws.amazon.com/bedrock/agentcore/) product page.\n\n### Why Amazon Bedrock?\n\nSeveral factors made Amazon Bedrock the ideal choice for Duco’s regulated financial services industry (FSI) environment:\n\n- **Security and compliance first:** With Amazon Bedrock, customer data stays within the AWS environment, and it is not used to train models. With private endpoints in its virtual private cloud (VPC), Duco can connect to internal systems while keeping them completely isolated, which matters for sensitive financial data processing.\n- **Model flexibility:** Access to leading foundation models from the Amazon Nova 2 family, Anthropic, OpenAI, Cohere, Meta, and Mistral AI through a single API means Duco can choose the right model for each task. Duco can switch between models by changing a configuration parameter.\n- **Built for financial services:** Amazon Bedrock provides the robust governance controls and compliance frameworks that financial services require, avoiding infrastructure complexity while maintaining the security standards tier-one banks demand.\n\n### Choosing AgentCore as the runtime\n\nDuco’s existing agent infrastructure was built on LangChain and LangGraph, both of which were already in production. When evaluating runtime options for its agentic workloads, AgentCore emerged as the clear choice for three key reasons:\n\n- **Compatibility with existing primitives:** AgentCore is fully compatible with Duco’s existing LangChain and LangGraph code, so most existing code continued to work without modification.\n- **Managed runtime:** Instead of Duco running its own agent infrastructure, AgentCore provides a fully managed runtime, reducing operational overhead for the engineering team.\n- **Regulated environment suitability:** AgentCore met the stringent requirements of deploying in regulated financial services environments, with built-in security and compliance controls.\n\n## Multi-tenant architecture: Isolation by design\n\nDuco’s platform operates as a multi-tenant software as a service (SaaS) offering with strict tenant isolation (figure 1). This is a non-negotiable requirement for regulated institutions. The architecture reflects this at every layer, from the underlying cloud infrastructure right up to the AI agent runtime.\n\n### Infrastructure layer\n\n- **Amazon Elastic Kubernetes Service (Amazon EKS) clusters** with namespace-per-tenant isolation and network segregation help maintain workload separation at the Kubernetes layer.\n- **Per-tenant dedicated AWS services** : every tenant receives a dedicated Amazon Aurora MySQL database, Amazon Simple Storage Service (Amazon S3) storage bucket, AWS Key Management Service (AWS KMS) encryption keys, Amazon Simple Email Service (Amazon SES) and Amazon Simple Queue Service (Amazon SQS) messaging stack, Amazon ElastiCache layer, and Amazon Cognito user pool. Zero shared data infrastructure across clients.\n- **Per-tenant autoscaling** helps minimize the impact of one client’s compute-intensive workload on another tenant’s performance.\n\n### Security and access control\n\nIsolation is enforced through identity as well as infrastructure, with every hop between the user and their data authenticated (figure 2):\n\n- **Tenant-scoped authentication** : every request carries a JSON Web Token (JWT) issued by the tenant’s dedicated Cognito user pool, validated by the inbound authorizer of the AgentCore runtime, a capability of Amazon Bedrock AgentCore, before agent logic runs.\n- **Gateway-mediated tool access** : agents reach tools only through the tenant’s dedicated AgentCore Gateway, a capability of Amazon Bedrock AgentCore, which passes calls through to the tenant’s container-based Model Context Protocol (MCP) services running in Amazon EKS.\n- **End-to-end user identity** : the user’s identity is passed through to downstream services, and each MCP server validates both the agent’s and the user’s identity against the tenant’s Cognito user pool, so every tool call is authorized as the calling user, made by a trusted agent.\n- **Private networking** : tenants share a VPC and Amazon EKS cluster, segregated by namespace and network policy, with private endpoints keeping traffic to Amazon Bedrock and AgentCore on the AWS network. Each tenant’s AgentCore runtime runs in VPC network mode, with network interfaces in the private subnets, so its outbound traffic enters the VPC and is governed by security groups.\n\n### Agent layer\n\nThe isolation principle extends fully into the agent architecture:\n\n- **One AgentCore runtime and Gateway per tenant** : each tenant is served by a dedicated runtime and Gateway, configured against that tenant’s own Cognito user pool and Amazon EKS namespace. Combined with the built-in session isolation of AgentCore, this means there is no shared memory, context, or tooling between clients. Each bank’s unique schemas, naming conventions, and institutional knowledge remain completely isolated from other tenants.\n- **Per-tenant MCP servers** : each tenant has its own set of MCP servers providing service-specific capabilities, dynamically discovered at boot time.\n\nThe architecture helps maintain a model where each agent only has access to one bank’s data, context, and reasoning, facilitating real isolation of context across banks.\n\n## Multi-model strategy\n\nRather than committing to a single foundation model, Duco uses the right model for each job, assigning each role in its agent design to the model best suited to it. This approach delivers both quality and cost efficiency by matching the right model capability to each specific workload:\n\n| **Model** | **Primary role** | **Use cases** | \n| **Anthropic Claude Opus** | Planning agent | For complex reasoning and understanding, formulating up front plans for other agents to execute on | \n| **Anthropic Claude Sonnet** | Main reasoning & complex decision-making | Exception investigation, reconciliation logic, rule interpretation | \n| **Anthropic Claude Haiku** | Lightweight tool routing decisions | Fast routing choices, low-latency classification, cost-efficient first-pass triage | \n| **Amazon Nova 2 Pro** | Tool output summarization | Condensing MCP tool responses, generating readable summaries for analysts | \n\nThis multi-model approach is architecturally designed to allow model swapping without disrupting the stack, which is critical in a landscape where model capabilities evolve rapidly.\n\n## Solving context bloat: The MCP skills architecture\n\nOne of Duco’s most significant technical innovations addresses a challenge familiar to anyone building production agent systems: context window management.\n\n### The problem\n\nWith 300–400 tools exposed per tenant through AgentCore Gateway (which fronts a separate MCP server for each underlying Duco service), approximately 200,000 tokens of tool descriptions were loaded into context before work began. This caused *context overloading*: response quality degraded as conversations lengthened, and the model lost the thread of earlier reasoning. The team emphasized that a feeling an agent is becoming less capable isn’t enough evidence on its own. Evaluations must be run before engineering decisions are made.\n\n### The solution: On-demand skills loading\n\nDuco created a skills architecture using MCP resource types to move tool descriptions out of the static context and load them only when needed:\n\n- `skill:// resources` — on-demand tool descriptions loaded only when a skill is required.\n- `system:// resources` — dynamic system prompt sections composed at runtime, keeping the base system prompt lean.\n- `ui:// resources` — UI-specific resources, isolated from operational tooling.\n\nThree new meta-tools, implemented in Duco’s agent harness, replaced the bloated tool description payload:\n\n- `load_skill` — fetches skill descriptions on demand, only when the agent determines a skill is needed.\n- `find_tool` — locates relevant tools without loading all schemas into context.\n- `invoke_tool` — executes the selected tool once identified.\n\n### The results\n\n- **90% context reduction** : Main context reduced from 200,000 tokens to approximately 20,000 tokens by moving tool descriptions out of static context and limiting the size of tool responses.\n- **Prompt caching preserved** : the static prompt prefix (system prompt plus the three meta-tools) stays small and stable, and skills load into the conversation rather than the tool list, so loading a skill does not invalidate the cache.\n- **Measurably improved agent response quality:** validated through a rigorous evaluation framework.\n- **Zero infrastructure changes required** : same underlying models, same tools, and same tasks, with measurably better outcomes.\n\n## MCP tool discovery: Deploy a service, gain a capability\n\nA key architectural decision was implementing MCP tool discovery at boot time. When a new service is deployed, its MCP server is registered as a target on the tenant’s AgentCore Gateway as part of the deployment. When an agent boots, the harness builds a registry of every tool the Gateway exposes and shares just the tool names. The agent then uses find_tool and invoke_tool to discover the details and invoke tools on demand. As a result, the agent automatically gains that capability with no redeployment or agent reconfiguration required. Access control is enforced by the underlying services themselves: because the user’s identity is passed through the Gateway, each tool call succeeds only if that user is permitted to perform the action.\n\nThis provides operational agility: the platform t", "url": "https://wpnews.pro/news/how-duco-transforms-financial-data-automation-with-amazon-bedrock-agentcore", "canonical_source": "https://aws.amazon.com/blogs/machine-learning/how-duco-transforms-financial-data-automation-with-amazon-bedrock-agentcore/", "published_at": "2026-11-16 22:06:08+00:00", "updated_at": "2026-11-17 19:52:51.855570+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-agents", "ai-infrastructure", "generative-ai", "ai-products"], "entities": ["Duco", "Amazon Bedrock", "Amazon Bedrock AgentCore", "Amazon Web Services", "Rob Gates", "Amazon Nova 2", "Anthropic", "OpenAI"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/how-duco-transforms-financial-data-automation-with-amazon-bedrock-agentcore", "markdown": "https://wpnews.pro/news/how-duco-transforms-financial-data-automation-with-amazon-bedrock-agentcore.md", "text": "https://wpnews.pro/news/how-duco-transforms-financial-data-automation-with-amazon-bedrock-agentcore.txt", "jsonld": "https://wpnews.pro/news/how-duco-transforms-financial-data-automation-with-amazon-bedrock-agentcore.jsonld"}}