AI Practices AI实践 6h ago Updated 3h ago 更新于 3小时前 46

How Intuit built an agentic disaster recovery assistant with Amazon Bedrock Intuit 如何利用 Amazon Bedrock 构建智能体灾难恢复助手

Intuit built "EWOK Agent," an AI-powered disaster recovery assistant using Amazon Bedrock, to automate decision-making in failover scenarios that previously required tribal knowledge from senior engineers The system separates reasoning from execution: foundation models decide what to do, while the deterministic EWOK (Ecosystem Wide Orchestrator Kit) layer executes how, maintaining a crisp boundary between the two EWOK already reduced recovery times from several hours to ~20 minutes by standardiz Intuit基于Amazon Bedrock构建了EWOK Agent,将AI智能体能力集成到灾难恢复系统中,解决传统DR流程中依赖工程师"部落知识"进行决策的痛点 核心设计原则是"模型决定做什么,EWOK Agent确定性执行怎么做",通过分层架构实现AI推理与基础设施执行的清晰边界 EWOK系统已能将恢复时间从数小时缩短至约20分钟,AI智能体进一步解决了工作流选择、资产就绪确认和异常处理等决策问题 采用Amazon Bedrock的Converse API和Tool Use功能,将恢复知识编码为"技能"并编译为工具调用,支持多模型评估和无缝切换 系统以插件形式交付,工程师可从Intuit

62
Hot 热度
70
Quality 质量
65
Impact 影响力

Analysis 深度分析

TL;DR

  • Intuit built "EWOK Agent," an AI-powered disaster recovery assistant using Amazon Bedrock, to automate decision-making in failover scenarios that previously required tribal knowledge from senior engineers
  • The system separates reasoning from execution: foundation models decide what to do, while the deterministic EWOK (Ecosystem Wide Orchestrator Kit) layer executes how, maintaining a crisp boundary between the two
  • EWOK already reduced recovery times from several hours to ~20 minutes by standardizing failover execution across compute, databases, networking, caches, and async workloads via YAML-declared recovery intent
  • Amazon Bedrock provides model flexibility (hundreds of FMs via a single API), built-in Guardrails for safety, encryption in transit/at rest, and no data training usage — critical for production financial systems
  • The agent is delivered as a plugin installable from Intuit's Engineering portal or IDE, and the underlying design pattern (typed skills, thin Bedrock layer, bounded agentic loop over a deterministic executor) is reusable for any system with authenticated, auditable APIs

Why It Matters

This represents a practical, production-grade example of agentic AI applied to critical infrastructure operations — not just a demo, but a system actively used by Intuit teams for eight months to run failovers for products serving millions of users (TurboTax, QuickBooks, Mailchimp, Credit Karma). It demonstrates how to responsibly combine LLM reasoning with deterministic execution in high-stakes environments where safety, auditability, and policy compliance are non-negotiable.

Technical Details

  • Architecture pattern: A thin Amazon Bedrock layer sits above the EWOK execution engine, connecting foundation models to "skills" (typed, compiled representations of failover knowledge). The agentic loop processes natural-language requests (e.g., "failover payments-gateway in production") into validated, policy-aligned recovery executions.
  • Core design principle: "The model decides what to do, and the EWOK Agent deterministically executes how." This boundary ensures that LLMs handle ambiguous decision-making (workflow selection, exception handling, change-freeze override procedures) while the underlying system guarantees safe, auditable infrastructure actions.
  • Amazon Bedrock integration: Uses the Bedrock Converse API with tool use (function calling) for skill-to-tool compilation. Supports model evaluation and switching without rearchitecting. IAM actions include bedrock:Converse, bedrock:ConverseStream, bedrock:InvokeModel, and bedrock:ApplyGuardrail.
  • Security and compliance: Bedrock Guardrails provide built-in safety controls. Data is encrypted in transit and at rest, and is not used to train foundation models — essential for a system operating on production financial infrastructure.
  • Delivery and stack: Delivered as a plugin for Intuit's Engineering portal and IDEs. Built with Python, AWS SDK for Python (Boto3), and langchain-aws libraries. The pattern is framework-agnostic and applicable to any system exposing authenticated, auditable APIs.

Industry Insight

  • Agentic AI for infrastructure ops is viable at scale: Intuit's eight-month production deployment proves that AI agents can safely augment critical SRE workflows when the reasoning-execution boundary is strictly enforced — a pattern other enterprises should replicate for incident response, change management, and compliance-heavy operations.
  • Model flexibility without lock-in is a strategic advantage: By using Bedrock's multi-model API, Intuit can continuously evaluate and swap foundation models as capabilities evolve, keeping the agent current without engineering overhead — a model that reduces long-term AI infrastructure costs.
  • The "skills as compiled tools" pattern is broadly reusable: Encoding domain knowledge as typed skills that compile into function-calling tools, then wrapping them in a bounded agentic loop, provides a template for building reliable AI assistants in any regulated or safety-critical domain beyond disaster recovery.

TL;DR

  • Intuit基于Amazon Bedrock构建了EWOK Agent,将AI智能体能力集成到灾难恢复系统中,解决传统DR流程中依赖工程师"部落知识"进行决策的痛点
  • 核心设计原则是"模型决定做什么,EWOK Agent确定性执行怎么做",通过分层架构实现AI推理与基础设施执行的清晰边界
  • EWOK系统已能将恢复时间从数小时缩短至约20分钟,AI智能体进一步解决了工作流选择、资产就绪确认和异常处理等决策问题
  • 采用Amazon Bedrock的Converse API和Tool Use功能,将恢复知识编码为"技能"并编译为工具调用,支持多模型评估和无缝切换
  • 系统以插件形式交付,工程师可从Intuit工程门户或IDE直接安装使用,数据加密且不被用于模型训练,满足金融系统安全合规要求

为什么值得看

本文展示了大型科技公司如何将AI智能体技术应用于关键基础设施的灾难恢复场景,为金融级系统的AI落地提供了可复用的架构模式。其"推理与执行分离"的设计原则对构建生产级AI应用具有重要参考价值。

技术解析

  • 架构分层:系统采用两层架构,上层是Amazon Bedrock驱动的AI智能体负责决策推理,下层是EWOK(Ecosystem Wide Orchestrator Kit)负责确定性执行。AI层通过Converse API和Tool Use能力调用底层技能,确保模型输出经过验证后由确定性系统执行。
  • 技能编码机制:将灾难恢复知识编码为"技能"(Skills),每个技能对应特定的恢复工作流。技能通过YAML声明式配置定义恢复意图,包含计算、数据库、网络、缓存和异步工作负载等组件的故障转移步骤。
  • 智能体循环设计:采用有界智能体循环(Bounded Agentic Loop),将自然语言请求(如"将生产环境的支付网关故障转移到备用区域")转化为经过策略验证的恢复执行。模型负责选择正确的工作流和确认资产就绪状态,EWOK负责确定性执行。
  • 安全与合规:利用Amazon Bedrock Guardrails提供内置安全保护,数据在传输和静态状态下加密,且不被用于模型训练。通过IAM策略严格控制bedrock:Converse、bedrock:InvokeModel等API调用权限。
  • 技术栈:基于Python、AWS SDK(Boto3)和langchain-aws库实现,通过插件形式集成到工程门户和IDE,支持多AWS区域的基础模型访问和评估。

行业启示

  • AI智能体在关键基础设施中的应用范式:本文展示了AI从"辅助建议"向"决策执行"演进的路径,通过明确的职责分离(AI决策+确定性执行)平衡了智能性与可靠性,为金融、医疗等高合规要求行业的AI落地提供了参考。
  • 技能化知识管理的重要性:将领域专家知识编码为可复用的"技能"而非硬编码逻辑,使系统既能保持AI的灵活性,又能确保执行的可预测性。这种模式可推广至运维自动化、合规检查等其他领域。
  • 平台化AI集成的战略价值:通过Amazon Bedrock等托管服务快速集成AI能力,无需自建模型基础设施,降低了技术门槛。企业应评估将AI作为"推理层"叠加到现有确定性系统之上的架构模式,而非完全重构。

Disclaimer: The above content is generated by AI and is for reference only. 免责声明:以上内容由 AI 生成,仅供参考。

Agent Agent Closed Source 闭源 LLM 大模型 Deployment 部署