Duco 基于 Amazon Bedrock AgentCore 重构金融数据自动化智能体架构
How Duco transforms financial data automation with Amazon Bedrock AgentCore
一家服务一线银行的公司公开了迁移到 Bedrock AgentCore 的完整做法:MCP 技能架构把上下文开销砍了 90%,onboarding 成本降 70%。做金融或合规场景智能体的工程团队可以直接对照抄架构,比看官方文档实在。
面向一线银行的数据自动化平台 Duco 将其智能体 AI 栈迁移到 Amazon Bedrock 与 Amazon Bedrock AgentCore。迁移后,对账部署时间缩短 10 倍,客户 onboarding 成本降低 70%。
架构上有三个关键设计:一是严格的按租户隔离(per-tenant isolation),满足银行客户对数据边界的合规要求;二是多模型策略,不同任务调用不同模型而非绑定单一模型;三是采用 MCP 技能架构(skills architecture),将上下文开销削减 90%,让智能体只加载当前任务所需的工具与知识。
这篇案例对正在为金融等强合规行业构建智能体应用的团队有直接参考价值:它展示了 AgentCore 在多租户 SaaS 场景下的落地方式,以及 MCP 如何用于控制长上下文成本,可作为自建方案与托管方案选型时的对照样本。
How Duco transforms financial data automation with Amazon Bedrock AgentCore
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%.
This report is categorized under AITOP's "How-to" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Amazon Bedrock, AgentCore, MCP and tools, agents.
Primary source verification: published directly by AWS Machine Learning Blog with first-party authority.