How Amazon Finance streamlines regulatory inquiries by using generative AI on AWS亚马逊金融科技如何利用 AWS 上的生成式 AI 简化监管问询处理

Amazon’s Finance Technology (FinTech) teams build and operate systems for Amazon teams to manage regulatory inquiries in compliance with different jurisdictions. These teams process regulatory inquiries from authorities, each presenting different requirements, document formats, and complexity levels.亚马逊的金融科技（FinTech）团队负责构建和运维相关系统，帮助亚马逊各团队按照不同司法辖区的合规要求处理监管问询。这些团队需要处理来自监管机构的问询，每项问询都有不同的要求、文档格式和复杂程度。

Processing these regulatory inquiries involves reviewing documentation, extracting relevant information, retrieving supporting data from multiple systems within Amazon’s infrastructure, and compiling responses within regulatory timeframes. As inquiry frequency and business complexity grew, Amazon needed a more scalable approach.处理这些监管问询涉及审阅文档、提取相关信息、从亚马逊基础设施内的多个系统中检索支持数据，并在监管时限内汇编回复。随着问询频率和业务复杂性的增长，亚马逊需要一种更具可扩展性的方法。

In this post, we demonstrate how Amazon FinTech teams are using Amazon Bedrock and other AWS services to build a scalable AI application to transform how regulatory inquiries are handled. Each team using this solution creates and maintains its own dedicated knowledge base, populated with that team’s specific documents and reference materials.在本文中，我们演示亚马逊金融科技团队如何利用 Amazon Bedrock 和其他 AWS 服务构建可扩展的 AI 应用，以变革监管问询的处理方式。使用该解决方案的每个团队都会创建并维护自己的专用知识库，其中包含该团队特定的文档和参考资料。

Challenges挑战

The scale and complexity of managing regulatory inquiries presented several interconnected challenges:管理监管问询的规模和复杂性带来了若干相互关联的挑战：

Knowledge fragmentation and retrieval complexity知识分散与检索复杂

Regulatory inquiries require synthesizing information from thousands of historical documents. These documents exist in various formats (PDF, PPT, Word, CSV) and contain domain-specific terminology. Teams needed a way to quickly locate relevant precedents and supporting information across this vast corpus while maintaining accuracy and regulatory compliance.监管问询需要综合成千上万份历史文档中的信息。这些文档格式多样（PDF、PPT、Word、CSV），并包含领域专业术语。团队需要一种方法，能够在这一庞大语料库中快速定位相关先例和支持信息，同时保持准确性和监管合规性。

Conversational context and state management多轮对话上下文与会话状态管理

Regulatory inquiries require multi-turn conversations where context from earlier interactions is essential for generating accurate responses. Maintaining conversational state across sessions and tracking response evolution as team members refine answers through iterative interactions presents significant complexity.监管问询往往需要多轮对话，早期交互中的上下文对于生成准确回复至关重要。跨会话维护对话状态，并跟踪团队成员通过迭代交互完善答案时的回复演进过程，带来了显著的复杂性。

Observability and continuous improvement可观测性与持续改进

With generative AI systems, understanding why a particular response was generated is as important as the response itself. Teams required comprehensive visibility into the retrieval process, model decisions, and user interactions to identify areas for improvement and maintain compliance with responsible AI principles. For example, teams must detect when the model hallucinates information that isn’t present in source documents, or catch when the system retrieves outdated compliance guidelines that could lead to regulatory violations. AI systems experience accuracy drift over time as models, prompts, and the document corpus change, requiring continuous monitoring.对于生成式 AI 系统，理解某个回复为何被生成，与回复本身同样重要。团队需要对检索过程、模型决策和用户交互有全面的可见性，以识别改进方向并维护负责任 AI 原则的合规性。例如，团队必须检测模型是否产生了源文档中不存在的信息（幻觉），或者系统是否检索到过时的合规指南，从而可能导致违规行为。随着模型、提示词和文档语料库的变化，AI 系统会随时间出现准确性漂移，因此需要持续监控。

Solution overview 解决方案概览

To address these challenges, Amazon FinTech team built an intelligent regulatory response automation system using Amazon Bedrock, AWS Lambda, and supporting AWS services. The solution implements Retrieval Augmented Generation (RAG) with Amazon Bedrock Knowledge Bases and Amazon OpenSearch Serverless for vector storage, enabling information retrieval from thousands of historical documents. Real-time chat interactions powered by Claude Sonnet 4.5 through the Converse Stream API, combined with Amazon DynamoDB for conversation history management, provide contextually-aware multi-turn conversations. Comprehensive observability through OpenTelemetry and self-hosted Langfuse ensures continuous monitoring and improvement of the AI system’s performance. The system doesn’t cache large language model (LLM) responses or intermediate results because regulatory inquiries are highly contextual and are prone to a low cache hit rate.为应对这些挑战，亚马逊金融科技团队利用 Amazon Bedrock、AWS Lambda 及配套 AWS 服务构建了一套智能监管回复自动化系统。该解决方案采用基于 Amazon Bedrock 知识库和 Amazon OpenSearch Serverless（用于向量存储）的检索增强生成（RAG），从而能够从数千份历史文档中检索信息。通过 Converse Stream API 由 Claude Sonnet 4.5 驱动的实时聊天交互，结合 Amazon DynamoDB 进行对话历史管理，实现了具备上下文感知能力的多轮对话。通过 OpenTelemetry 和自托管 Langfuse 实现的全面可观测性，确保了对 AI 系统性能的持续监控和改进。该系统不会缓存大语言模型（LLM）回复或中间结果，因为监管问询具有高度上下文相关性，缓存命中率可能很低。

The following diagram shows how you can use Amazon Bedrock Knowledge Bases in a workflow, alongside Converse API and other tools, to provide necessary information for regulatory inquiries:下图展示了如何在流程中使用 Amazon Bedrock 知识库，配合 Converse API 和其他工具，为监管问询提供必要信息：

Knowledge base ingestion flow知识库摄取流程

The knowledge base ingestion flow provides an automated document processing pipeline that initiates after the user uploads a document. Its job is to embed the document’s data into an Amazon Bedrock Knowledge Base. Here is the flow:知识库摄取流程提供了一个自动化的文档处理管道，在用户上传文档后启动，其任务是将文档数据嵌入到 Amazon Bedrock 知识库中。流程如下：

You can use the knowledge base ingestion workflow to upload documents in bulk and transform them into searchable vector embeddings through an automated pipeline. The following detailed flow is illustrated in the previous figure.您可以使用知识库摄取工作流批量上传文档，并通过自动化管道将其转换为可搜索的向量嵌入。前图展示了以下详细流程。

1. Document Upload by User: Users upload documents through the client application.用户上传文档：用户通过客户端应用上传文档。
2. Pre-Signed URL Generation: The client application sends a request to Amazon API Gateway, which invokes the knowledge base ingestion AWS Lambda function to generate a pre-signed S3 URL.预签名 URL 生成：客户端应用向 Amazon API Gateway 发送请求，API Gateway 调用知识库摄取 AWS Lambda 函数生成预签名 S3 URL。
3. Document Upload: The client application uses the generated pre-signed URL to upload the document.文档上传：客户端应用使用生成的预签名 URL 上传文档。
4. Ingestion Trigger and Data Processing: After the document is successfully uploaded to Amazon Simple Storage Service (Amazon S3), the client application triggers the Amazon API Gateway to initiate the document processing AWS Lambda, which handles format conversion and manages the concurrent ingestion of documents. We don’t need to pre-process the images, charts, and tables in these documents because the Amazon Bedrock Knowledge Base is configured with Amazon Bedrock Data Automation (BDA) to effectively extract this multimodal content. The AWS Lambda function then calls the Amazon Bedrock Knowledge Bases.摄取触发与数据处理：文档成功上传到 Amazon Simple Storage Service（Amazon S3）后，客户端应用触发 Amazon API Gateway 启动文档处理 AWS Lambda 函数，该函数负责格式转换并管理文档的并发摄取。我们无需对这些文档中的图片、图表和表格进行预处理，因为 Amazon Bedrock 知识库配置了 Amazon Bedrock Data Automation（BDA），可有效提取这些多模态内容。随后，AWS Lambda 函数调用 Amazon Bedrock 知识库。
5. Vector Storage: The Amazon Bedrock Knowledge Base chunks the document content using a hierarchical chunking strategy, generates embeddings using Amazon Titan Text Embeddings, and stores the resulting vectors in OpenSearch Serverless. Hierarchical chunking creates nested parent-child relationships that mirror the sectioned structure of financial documents. This strategy works well for structured and complex documents because it indexes small chunks for precise retrieval while returning larger parent chunks to provide sufficient context for coherent responses.向量存储：Amazon Bedrock 知识库采用分层分块策略对文档内容进行分块，使用 Amazon Titan Text Embeddings 生成嵌入向量，并将生成的向量存储在 OpenSearch Serverless 中。分层分块会创建嵌套的父子关系，与金融文档的分节结构相对应。这种策略适用于结构化和复杂文档，因为它会索引较小的块以实现精确检索，同时返回更大的父块以提供足够的上下文，从而生成连贯的回复。

Building an automated ingestion pipeline addresses the core challenge of knowledge fragmentation by efficiently processing thousands of historical documents across multiple formats while optimizing content indexing for relevant AI responses. This parallelized approach enables the system to scale effectively, accommodating the growing year-over-year regulatory inquiry activity while maintaining consistent processing performance across large document volumes.构建自动化摄取管道解决了知识分散这一核心挑战，能够高效处理跨多种格式的数千份历史文档，同时优化内容索引以提高 AI 回复的相关性。这种并行化方法使系统能够有效扩展，适应逐年增长的监管问询活动，同时在大规模文档处理中保持一致的性能。

Chat Application 聊天应用

The Chat Application provides a real-time conversation interface powered by AWS serverless architecture, enabling natural language interactions with the system. We chose to stream responses to customers so they can begin reading the AI response sooner in real-time, implementing this capability through WebSocket connections. Through these WebSocket connections and the Claude Sonnet 4.5 model, it delivers contextually relevant responses while maintaining conversation state in DynamoDB. The workflow operates as follows:聊天应用基于 AWS 无服务器架构提供实时对话接口，支持与系统进行自然语言交互。我们选择向客户流式传输回复，以便用户能更早地实时开始阅读 AI 回复，并通过 WebSocket 连接实现这一能力。通过这些 WebSocket 连接和 Claude Sonnet 4.5 模型，该应用能够提供上下文相关的回复，同时在 DynamoDB 中维护会话状态。工作流程如下：

1. Initiate Chat Conversation: Users initiate or open an existing chat session through the client application.发起聊天会话：用户通过客户端应用发起或打开现有聊天会话。
2. WebSocket Connection: The application uses WebSockets to establish a persistent, bi-directional connection with Amazon API Gateway.WebSocket 连接：应用使用 WebSocket 与 Amazon API Gateway 建立持久、双向连接。
3. Message Submission: The application posts the user questions through the WebSocket connection which is propagated to the Chat service AWS Lambda function.消息提交：应用通过 WebSocket 连接发布用户问题，该连接将问题传递到聊天服务 AWS Lambda 函数。
4. Query Enhancement: The Chat Service AWS Lambda function uses the Claude 3.5 Haiku model with a query expansion strategy to generate multiple variations of the user’s question.查询增强：聊天服务 AWS Lambda 函数使用 Claude 3.5 Haiku 模型和查询扩展策略，生成用户问题的多个变体。
5. Knowledge Retrieval: The Chat Service Lambda invokes the Amazon Bedrock Knowledge Bases Retrieve API for each expanded query. The API performs vector similarity searches against the underlying OpenSearch Serverless index and returns the most relevant document chunks along with their source metadata and relevance scores.知识检索：聊天服务 AWS Lambda 为每个扩展查询调用 Amazon Bedrock 知识库 Retrieve API。该 API 对底层的 OpenSearch Serverless 索引执行向量相似性搜索，并返回最相关的文档块及其来源元数据和相关性分数。
6. Context Assembly: The Chat Service AWS Lambda function retrieves conversation history from Amazon DynamoDB (for existing conversations, based on that specific conversation ID) and combines it with the retrieved knowledge base results and the user’s question.上下文组装：聊天服务 AWS Lambda 函数从 Amazon DynamoDB 检索对话历史（对于现有对话，基于特定对话 ID），并将其与检索到的知识库结果和用户问题组合在一起。
7. Response Generation: The Chat Service AWS Lambda function uses the Converse Stream API with Claude Sonnet 4.5 and a response generator prompt to produce a contextually relevant answer based on the assembled context.回复生成：聊天服务 AWS Lambda 函数使用带 Claude Sonnet 4.5 的 Converse Stream API 以及回复生成提示词，基于组装的上下文生成上下文相关的回复。
8. User Engagement: The Chat Service AWS Lambda function streams the generated response back to the client application in Markdown format through the WebSocket connection and stores all the conversation in the Conversational History Table by Amazon DynamoDb.用户交互：聊天服务 AWS Lambda 函数通过 WebSocket 连接将生成的回复以 Markdown 格式流式返回给客户端应用，并将所有对话存储在 Amazon DynamoDB 的对话历史表中。
9. Observability: Throughout the process, the Chat Service publishes end-to-end traces to a self-hosted Langfuse instance using the OpenTelemetry (OTEL) SDK. This captures detailed telemetry data including latency metrics, token usage, prompt templates, and model responses.可观测性：在整个过程中，聊天服务使用 OpenTelemetry（OTEL）SDK 将端到端追踪发布到自托管的 Langfuse 实例。这捕获了详细的遥测数据，包括延迟指标、令牌用量、提示词模板和模型回复。

Multi-turn conversational experience多轮对话体验

Regulatory inquiry discussions often progress through multiple exchanges as teams refine responses and reference additional data sources. To support this iterative process, the Amazon FinTech team implemented a multi-turn conversational workflow using Amazon API Gateway (WebSocket APIs), AWS Lambda, and Amazon DynamoDB, integrated with the Amazon Bedrock ConverseStream API for low-latency, context-aware dialogue. Each chat session is securely authenticated through Amazon Cognito and assigned a unique conversation ID. DynamoDB stores messages in chronological order to preserve context across sessions, so users can resume prior discussions seamlessly and maintain continuity.监管问询讨论通常会随着团队完善回复并引用额外数据源而进行多轮交互。为支持这种迭代流程，亚马逊金融科技团队使用 Amazon API Gateway（WebSocket API）、AWS Lambda 和 Amazon DynamoDB 实现了多轮对话工作流，并与 Amazon Bedrock ConverseStream API 集成，以实现低延迟、上下文感知的对话。每个聊天会话都通过 Amazon Cognito 进行安全认证，并分配唯一的对话 ID。DynamoDB 按时间顺序存储消息，以跨会话保留上下文，使用户可以无缝恢复之前的讨论并保持连续性。

When a user submits a query, the system sanitizes inputs to prevent prompt injection attacks. After sanitization, the system classifies intent and determines whether retrieval from the Amazon Bedrock Knowledge Base is required. This determination is made through an LLM call that classifies the user query as either conversational or knowledge intensive. For complex, knowledge-intensive questions, the workflow employs a query expansion strategy that addresses the prevalent use of acronyms and abbreviated questions by users. This layer generates up to five query variations using Claude 3.5 Haiku, then makes parallel Retrieve API calls to the Knowledge Base, retrieving relevant results using OpenSearch vector similarity search. To maintain performance at scale, the workflow implements parallel processing for these retrieval calls using multi-threading. This optimization reduced retrieval latency from 10 seconds (sequential processing) to under 2 seconds, enabling responsive conversations. The retrieved information—combined with recent conversation history—is passed to Claude Sonnet 4.5 through the ConverseStream API augmented with Amazon Bedrock Guardrails, that implement sensitive information filters to automatically detect and remove PII and financial data from both inputs and outputs. This is critical for protecting regulatory documentation. When prompt injection attempts are detected, the system responds with “Sorry, the model cannot answer that question,” maintaning secure and compliant interactions while maintaining conversational fluency.当用户提交查询时，系统会对输入进行净化以防止提示注入攻击。净化后，系统对意图进行分类，并判断是否需要从 Amazon Bedrock 知识库进行检索。该判断通过一次 LLM 调用完成，将用户查询归类为对话型或知识密集型。对于复杂的、知识密集型问题，工作流采用查询扩展策略，以应对用户普遍使用缩写和简略问题的现象。该层使用 Claude 3.5 Haiku 生成最多五个查询变体，然后对知识库进行并行的 Retrieve API 调用，使用 OpenSearch 向量相似性搜索检索相关结果。为了在大规模下保持性能，工作流使用多线程实现这些检索调用的并行处理。这一优化将检索延迟从 10 秒（顺序处理）缩短到 2 秒以内，从而实现响应迅速的对话。检索到的信息与最近的对话历史相结合，通过 ConverseStream API 传递给 Claude Sonnet 4.5，并辅以 Amazon Bedrock Guardrails——后者实现敏感信息过滤器，可自动检测并从输入和输出中移除个人身份信息（PII）和财务数据。这对于保护监管文档至关重要。当检测到提示注入尝试时，系统会回复“抱歉，模型无法回答该问题”，在保持对话流畅性的同时确保交互的安全性和合规性。

This architecture delivers continuity, transparency, and scalability. Users receive real-time, streaming responses with status updates throughout the retrieval and generation phases, improving engagement and reducing latency. Persistent logs in DynamoDB provide an immutable audit trail for compliance review, while the serverless and event-driven design scales automatically to support concurrent sessions. Together, these capabilities enable Amazon FinTech team to conduct complex, iterative conversations—producing contextually relevant, secure, and regulatory-compliant responses powered by Amazon Bedrock.该架构实现了连续性、透明性和可扩展性。用户在检索和生成阶段可实时获得带状态更新的流式回复，从而提升参与度并降低延迟。DynamoDB 中的持久日志为合规审查提供了不可篡改的审计轨迹，而无服务器和事件驱动设计可自动扩展以支持并发会话。这些能力共同使亚马逊金融科技团队能够进行复杂的迭代对话——借助 Amazon Bedrock 生成上下文相关、安全且合规的回复。

Observability可观测性

Observability plays a critical role in understanding and improving AI-driven workflows. To achieve complete visibility into the regulatory inquiry response system, the Chat Service AWS Lambda integrated OpenTelemetry (OTEL) with a self-hosted Langfuse instance to capture detailed, end-to-end traces of each interaction. This setup provides engineers and applied scientists with fine-grained telemetry on how prompts are processed, knowledge is retrieved, and responses are generated. This enables nearly continuous refinement of the system’s performance and accuracy. The decision to use OTEL over the native Langfuse SDK provides vendor-neutral flexibility, allowing telemetry data to be routed to multiple observability backends and adapted to evolving monitoring requirements.可观测性在理解和改进 AI 驱动的工作流中扮演着关键角色。为了全面了解监管问询回复系统，聊天服务 AWS Lambda 集成了 OpenTelemetry（OTEL）与自托管的 Langfuse 实例，以捕获每次交互的详细端到端追踪。这一配置为工程师和应用科学家提供了关于提示词如何处理、知识如何检索以及回复如何生成的细粒度遥测数据，使得系统性能和准确性几乎可以持续不断地得到改进。选择 OTEL 而非原生 Langfuse SDK，可以提供与厂商无关的灵活性，使遥测数据能够路由到多个可观测性后端，并适应不断变化的监控需求。

At runtime, each stage of the Chat Service AWS Lambda is manually instrumented using the OTEL Java SDK to record latency, token usage, model decisions, and prompt metadata in OTEL Generative AI semantic standard. Spans are published to Langfuse in near real time, giving the team a transparent view of how the Amazon Bedrock ConverseStream API, Knowledge Base retrieval, and Claude Sonnet 4.5 interact within a single request. The detailed telemetry allows the team to identify performance bottlenecks, optimize prompt strategies, and enhance retrieval precision while maintaining responsible AI practices.在运行时，聊天服务 AWS Lambda 的每个阶段都使用 OTEL Java SDK 进行手动埋点，以按照 OTEL 生成式 AI 语义标准记录延迟、令牌用量、模型决策和提示词元数据。Span 几乎实时发布到 Langfuse，使团队能够透明地看到 Amazon Bedrock ConverseStream API、知识库检索和 Claude Sonnet 4.5 如何在单个请求中相互作用。详细的遥测数据使团队能够识别性能瓶颈、优化提示词策略并提高检索精度，同时保持负责任的 AI 实践。

This observability framework maintains trust and accountability in the system’s behavior. Engineers can correlate user actions with model outcomes, trace data lineage across multiple services, and fine-tune configurations without disrupting operations. By combining OpenTelemetry’s interoperability with Langfuse’s visualization and analytics, Amazon FinTech team gains a scalable, extensible foundation for evaluating generative AI systems at scale—turning every interaction into actionable insight for continuous improvement.这一可观测性框架维护了系统行为中的信任和问责。工程师可以将用户操作与模型结果关联起来，跨多个服务追踪数据血缘，并在不中断运营的情况下微调配置。通过将 OpenTelemetry 的互操作性与 Langfuse 的可视化和分析能力相结合，亚马逊金融科技团队获得了可扩展、可扩展的基础，用于大规模评估生成式 AI 系统——将每次交互转化为持续改进的可操作洞察。

The following screenshot illustrates an end-to-end trace captured in Langfuse, showcasing how the observability solution captures the complete workflow—from query expansion and knowledge retrieval to model prompts, responses, and latency metrics. It also highlights source document citations, offering a transparent view of how contextual information flows through the system during response generation以下截图展示了 Langfuse 中捕获的端到端追踪，展示了可观测性解决方案如何捕获完整工作流——从查询扩展和知识检索到模型提示词、回复和延迟指标。它还突出显示了源文档引用，透明地展示了上下文信息如何在回复生成过程中流经系统。

Reference: End-to-End Trace Posted in Langfuse参考资料：发布在 Langfuse 中的端到端追踪

Conclusion结论

In this post, you saw how Amazon FinTech team built a scalable AI solution using Amazon Bedrock, designed to support regulatory inquiries by automating knowledge retrieval, conversational workflows, and response generation. By combining a document ingestion pipeline, multi-turn stateful conversations, and detailed observability via OpenTelemetry and Langfuse, the architecture empowers teams to handle regulatory inquiries in governed, traceable and compliant manner.在本文中，您了解了亚马逊金融科技团队如何利用 Amazon Bedrock 构建一个可扩展的 AI 解决方案，通过自动化知识检索、对话工作流和回复生成来支持监管问询。通过将文档摄取管道、多轮有状态对话以及基于 OpenTelemetry 和 Langfuse 的详细可观测性相结合，该架构使团队能够以可治理、可追踪且合规的方式处理监管问询。

Because the entire stack is built on AWS serverless services, it offers the operational scalability, security, and elasticity required for enterprise-grade deployment. Whether you’re dealing with legal compliance, regulatory inquiries, or high-volume internal knowledge workflows, this pattern offers a practical foundation that you can tailor and extend to your business domain.由于整个技术栈构建在 AWS 无服务器服务之上，因此具备企业级部署所需的运维可扩展性、安全性和弹性。无论您处理的是法律合规、监管问询，还是高吞吐量的内部知识工作流，这一模式都能提供一个实用的基础，您可以根据自身业务领域进行调整和扩展。

If you’re ready to modernize your knowledge-intensive processes with generative AI, explore the Amazon Bedrock documentation to discover how you can begin building your own secure, governed, and scalable AI-powered workflows.如果您准备好利用生成式 AI 对知识密集型流程进行现代化改造，请探索 Amazon Bedrock 文档，了解如何开始构建您自己的安全、可治理且可扩展的 AI 驱动工作流。

About the authors关于作者