Artificial Intelligence人工智能
Building trade assistant: How Jefferies optimized front office trading operations with AI构建交易助手：Jefferies 如何利用 AI 优化前台交易运营
If you manage a front office trading desk at investment banks, you know the challenge: traders need real-time insights into client behavior, trade patterns, and market trends from vast amounts of data to make split-second decisions. However, they rarely have the time during the day, nor the coding ability, to build and maintain systems capable of delivering those insights. With millions of rows of data spread across multiple visualization tools, achieving end-to-end visibility is difficult. Traditional approaches force traders to rely on subject matter experts for analysis and collaborate with IT teams to build custom dashboards. The process can take days or weeks. The result is a widening gap between the data available and the decisions it should be informing.如果你在投资银行管理前台交易台，你深知这一挑战：交易员需要从海量数据中实时洞察客户行为、交易模式和市场趋势，以便做出瞬息万变的决策。然而，他们白天几乎没有时间，也不具备编程能力，来构建和维护能够提供这些洞察的系统。由于数百万行数据分散在多个可视化工具中，实现端到端的可见性十分困难。传统方法迫使交易员依赖领域专家进行分析，并与 IT 团队合作构建自定义仪表板。这个过程可能需要数天或数周。结果是可用数据与其应指导的决策之间的差距越来越大。
Jefferies, a global full-service investment banking firm, recognized this challenge as an opportunity to apply agentic AI to optimize how its equities trading desks operate. By building an agentic AI trade assistant on AWS, Jefferies set out to put the power of real-time data analysis directly in traders’ hands without the requirement of coding, waiting in IT queues, and with no compromise on accuracy.Jefferies 是一家全球性全方位服务投资银行，将这一挑战视为应用代理式 AI 优化其股票交易台运营的机会。通过在 AWS 上构建代理式 AI 交易助手，Jefferies 致力于将实时数据分析的能力直接交到交易员手中，无需编码、无需排队等待 IT 支持，且不牺牲准确性。
In this post, we explore how Jefferies overcame these challenges with a solution built on Strands Agents, an agent harness SDK for building AI agents that can reason, plan, and act by orchestrating calls to foundation models (FMs) and external tools. The solution uses large language models (LLMs), Amazon Bedrock, and Amazon Bedrock Knowledge Bases. It also uses Model Context Protocol (MCP), an open standard that helps AI agents securely connect to diverse data sources and tools through a unified interface. We cover the solution overview, the rationale for selecting the underlying technology stack, lessons learned, and the business impact the solution created at Jefferies.在本文中，我们探讨了 Jefferies 如何借助基于 Strands Agents 构建的解决方案克服这些挑战。Strands Agents 是一个代理工具包 SDK，用于构建能够通过编排对基础模型 (FM) 和外部工具的调用来进行推理、规划和行动的 AI 代理。该解决方案使用大型语言模型 (LLM)、Amazon Bedrock 和 Amazon Bedrock Knowledge Bases。它还使用了模型上下文协议 (MCP)，这是一种开放标准，可帮助 AI 代理通过统一接口安全地连接到各种数据源和工具。我们将介绍解决方案概述、选择底层技术栈的理由、经验教训以及该解决方案在 Jefferies 产生的业务影响。
Solution overview解决方案概述
The Front Office trade assistant represents a shift in how Capital Markets’ Front Office Equity traders interact with data. At the core of the solution is a domain-specific agent that drives conversation with traders through natural language text. A set of MCP tools lets the agent connect with data sources, including trade data repositories, Financial Information Exchange (FIX) message files, and in-memory databases. When a trader submits a query to the trade assistant, Amazon Bedrock invokes an LLM (Anthropic Claude) to interpret the natural language intent, generate the corresponding SQL, and run it against underlying data sources to surface the response. The solution has a conversational interface, which allows traders to drill down on topics and explore data insights conversationally. The solution maintains conversation context to provide relevant insights and suggestions for deeper analysis over the entire lifetime of the session.前台交易助手代表了资本市场前台股票交易员与数据交互方式的转变。该解决方案的核心是一个特定领域的代理，它通过自然语言文本与交易员进行对话。一组 MCP 工具让代理能够连接到数据源，包括交易数据存储库、金融信息交换 (FIX) 消息文件和内存数据库。当交易员向交易助手提交查询时，Amazon Bedrock 会调用 LLM (Anthropic Claude) 来解析自然语言意图，生成相应的 SQL，并针对底层数据源执行以返回响应。该解决方案具有对话界面，允许交易员深入探讨主题并以对话方式探索数据洞察。该解决方案会维护会话上下文，以便在整个会话生命周期内提供相关洞察和深入分析建议。
How the solution works解决方案的工作原理
The solution integrates with Jefferies’ existing trading infrastructure through an eight-step process depicted in the following architecture diagram. From a security perspective, the solution uses Amazon Bedrock Guardrails to provide content moderation, personally identifiable information (PII) filtering to align the solution with Jefferies policies, and row-level data entitlements to help prevent accidental access to customer-sensitive data through intelligent access controls. It also uses conversation logging for audit trails to meet compliance requirements.该解决方案通过以下架构图所示的八个步骤与 Jefferies 现有的交易基础设施集成。从安全角度来看，该解决方案使用 Amazon Bedrock Guardrails 提供内容审核、个人身份信息 (PII) 过滤以符合 Jefferies 政策，并通过智能访问控制提供行级数据权限，以防止意外访问客户敏感数据。它还使用对话日志记录来满足合规性要求。
The user interaction begins with the Jefferies front-end trading interface, which now includes an embedded AI assistant widget. When a trader poses a question, the request flows through a carefully orchestrated workflow.用户交互从 Jefferies 的前端交易界面开始，该界面现在包含一个嵌入式 AI 助手组件。当交易员提出问题后，请求会流经精心编排的工作流程。
- UI Widget: First, the trader logs in using their credentials on Jefferies’ on-premises Business Intelligence system: Global Flow Monitor (GFM). Once a trader logs into GFM, they have a UI widget to interact with the Trade Assistant Agent.UI 组件：首先，交易员使用其凭据登录 Jefferies 的内部商业智能系统：Global Flow Monitor (GFM)。一旦交易员登录 GFM，他们就可以使用一个 UI 组件与交易助手代理进行交互。
- The Authentication Service uses Amazon Elastic Kubernetes Service (Amazon EKS). The service verifies that only allowed traders can access sensitive trading data.身份验证服务使用 Amazon Elastic Kubernetes Service (Amazon EKS)。该服务验证只有允许的交易员才能访问敏感交易数据。
- Bot Service builds and manages the user session, maintaining context across multiple queries.Bot 服务构建并管理用户会话，在多个查询之间维护上下文。
- The Query Agent (Strands) serves as the intelligent orchestration layer of the solution. When a trader poses a natural language question, the agent first queries the Amazon Bedrock Knowledge Bases, which uses Amazon Titan Embeddings for semantic retrieval to surface relevant database schemas, table relationships, and query patterns. With this context, Claude Sonnet reasons over the trader’s intent and generates a syntactically correct SQL query. The agent then evaluates its available Model Context Protocol (MCP) tools to determine the right data source for execution, whether that’s the in-memory grid for real-time positions or a historical data store for time-series analysis.查询代理 (Strands) 充当解决方案的智能编排层。当交易员提出自然语言问题时，代理首先查询 Amazon Bedrock Knowledge Bases，该知识库使用 Amazon Titan Embeddings 进行语义检索，以获取相关的数据库模式、表关系和查询模式。基于这些上下文，Claude Sonnet 对交易员的意图进行推理，并生成语法正确的 SQL 查询。然后，代理评估其可用的模型上下文协议 (MCP) 工具，以确定执行查询的正确数据源——无论是用于实时持仓的内存网格，还是用于时间序列分析的历史数据存储。
- Amazon Bedrock provides the Query Agent with access to an LLM for planning and executing the agent’s steps. The LLM’s advanced reasoning capabilities enable natural language understanding, SQL generation, and multi-step tool orchestration. The team also chose Amazon Bedrock for its flexibility to choose different LLMs as the trade assistant evolves.Amazon Bedrock 为查询代理提供对 LLM 的访问权限，用于规划和执行代理的步骤。LLM 的高级推理能力实现了自然语言理解、SQL 生成和多步骤工具编排。团队还选择 Amazon Bedrock 是因为其灵活性，可以根据交易助手的发展选择不同的 LLM。
- Amazon Bedrock Knowledge Bases provides a managed Retrieval Augmented Generation (RAG) pipeline that stores embedded representations of the underlying data model metadata (table schemas, column definitions, and query patterns). When the Query Agent receives a trader’s question, it retrieves relevant schema context from the Knowledge Base to inform accurate SQL construction.Amazon Bedrock Knowledge Bases 提供托管式检索增强生成 (RAG) 管道，用于存储底层数据模型元数据（表模式、列定义和查询模式）的嵌入表示。当查询代理收到交易员的问题时，它会从知识库中检索相关的模式上下文，以指导准确的 SQL 构建。
- Query Executor queries the underlying data once the Query Agent identifies the right data source and creates the SQL query. The query executor intercepts user requests and injects SQL filters to provide row-level security for data access. The LLM chooses the visualization to display, and we used a markdown UI library to render the visualizations.一旦查询代理识别出正确的数据源并创建 SQL 查询，查询执行器便会查询底层数据。查询执行器会拦截用户请求并注入 SQL 过滤器，为数据访问提供行级安全性。LLM 选择要显示的可视化内容，我们使用了一个 Markdown UI 库来渲染可视化效果。
- Data Stores: The actual data sources queried by the Query Executor, including in-memory, SQL databases, and FIX messages that contain the underlying trade and execution data.数据存储：查询执行器查询的实际数据源，包括内存数据库、SQL 数据库和包含底层交易及执行数据的 FIX 消息。
Let’s explore the rationale behind our selection of Strands Agents and MCP tools-based architecture.让我们探讨一下选择 Strands Agents 和基于 MCP 工具架构的原因。
Strands AgentsStrands Agents
Strands Agents is an open source agent harness SDK that takes a model-driven approach to building and running AI agents in a few lines of code. Strands scales from straightforward to complex agent use cases, and from local development to deployment in production. It simplifies agent development by embracing the capabilities of LLMs to plan, chain thoughts, call tools, and reflect. With Strands, developers can define a prompt and a list of tools in code to build an agent, then test it locally and deploy it to the cloud. Strands plans the agent’s next steps and executes tools using the advanced reasoning capabilities of models. For more complex agent use cases, developers can customize their agent’s behavior in Strands. For example, you can specify how tools are selected, customize how context is managed, choose where session state and memory are stored, and build multi-agent applications.Strands Agents 是一个开源代理工具包 SDK，采用模型驱动的方法，只需几行代码即可构建和运行 AI 代理。Strands 可从简单的代理用例扩展到复杂的用例，从本地开发到生产部署。它通过利用 LLM 的规划、思维链、工具调用和反思能力来简化代理开发。使用 Strands，开发人员可以在代码中定义提示和工具列表来构建代理，然后在本地测试并部署到云端。Strands 利用模型的先进推理能力规划代理的下一步并执行工具。对于更复杂的代理用例，开发人员可以在 Strands 中自定义代理的行为。例如，你可以指定如何选择工具、自定义上下文管理方式、选择会话状态和内存的存储位置，以及构建多代理应用程序。
Model Context Protocol (MCP) toolsModel Context Protocol (MCP) 工具
The solution implements a Model-Context-Protocol (MCP) tool-based architecture where each data source is exposed as a distinct tool that Strands Agents can invoke. This approach delivers three advantages that position the system for long-term success. First, the approach provides extensibility by enabling new data sources to be added as additional tools, requiring no restructuring of the core architecture, a design choice the team made deliberately to accommodate future functional expansion. Second, it provides separation of concerns by encapsulating the logic for interacting with each specific system within its own tool, which makes the overall architecture more maintainable and testable. Third, the design offers flexibility by allowing the Strands Agent to dynamically select which tools to use based on each query, enabling workflows that span multiple data sources.该解决方案实现了基于 Model-Context-Protocol (MCP) 工具的架构，其中每个数据源都作为一个独立的工具公开，Strands Agents 可以调用这些工具。这种方法带来了三个优势，为系统的长期成功奠定了基础。首先，该方法通过允许将新数据源添加为额外工具来提供可扩展性，无需重构核心架构——团队有意做出这一设计选择，以适应未来的功能扩展。其次，它通过将每个特定系统交互的逻辑封装在其自己的工具中来实现关注点分离，从而使整体架构更易于维护和测试。第三，该设计允许 Strands Agent 根据每个查询动态选择要使用的工具，从而实现跨多个数据源的工作流程，提供了灵活性。
Multi-source data processing多源数据处理
The solution provides an intuitive user experience. A trader can type a question like the one on the screen: “Give me the sector breakdown for trading in the U.S.” Behind the scenes, the assistant uses an LLM to generate the appropriate SQL query, runs it against the relevant data sources hosted in our in-memory data grid, and retrieves the results instantly.该解决方案提供了直观的用户体验。交易员可以输入类似屏幕上的问题：“提供美国交易的行业细分。”在后台，助手使用 LLM 生成适当的 SQL 查询，针对托管在内存数据网格中的相关数据源执行，并立即检索结果。
The trade assistant goes beyond simple data retrieval. It can generate dynamic visualizations, converting text queries into SQL that produces visual stories with charts and graphs. When traders need to compare today’s sector trading with yesterday’s activity, the assistant automatically generates pie charts with color-coded legends, making it straightforward to spot trends and anomalies quickly.交易助手不仅仅进行简单的数据检索。它可以生成动态可视化，将文本查询转换为 SQL，生成带有图表和图形的可视化故事。当交易员需要比较今天的行业交易与昨天的活动时，助手会自动生成带有颜色编码图例的饼图，使发现趋势和异常变得简单快捷。
Lessons learned经验教训
Throughout the journey to deliver the Front Office trade assistant agent, the Jefferies team uncovered several key lessons that shaped its enterprise AI strategy and implementation roadmap. These insights serve as valuable guidance for capital markets organizations building agentic AI applications at scale.在交付前台交易助手代理的整个过程中，Jefferies 团队总结出几个关键经验教训，这些经验塑造了其企业 AI 战略和实施路线图。这些见解为构建大规模代理式 AI 应用的资本市场组织提供了宝贵的指导。
First, the team mitigated the risk of hallucinations by deliberately not relying on LLMs to generate visualizations. Instead, they implemented a hybrid approach in which the LLM handles natural language understanding and query generation while dedicated visualization engines render the actual charts and graphs. This separation of concerns preserves data accuracy while maintaining the conversational interface traders expect.首先，团队通过故意不依赖 LLM 生成可视化内容来降低幻觉风险。相反，他们采用了一种混合方法：LLM 负责自然语言理解和查询生成，而专门的可视化引擎负责渲染实际的图表和图形。这种关注点分离在保持交易员期望的对话界面的同时，保证了数据准确性。
Second, the team used in-memory databases to maximize response times. Traders require split-second insights into client behavior, trade patterns, and market trends. Without this architectural choice, queries against the underlying dataset would have introduced unacceptable latency for real-time trading decisions.其次，团队使用内存数据库来最大化响应时间。交易员需要瞬间洞察客户行为、交易模式和市场趋势。如果没有这种架构选择，针对底层数据集的查询将引入无法接受的延迟，影响实时交易决策。
Third, the team learned to expect user behavior to evolve. Real-world usage proved dynamic. Traders interacted with the system in unexpected ways, and their patterns shifted over time. Investing in observability and user feedback loops proved essential for adapting quickly to these changing behaviors. Finally, the team adopted a deliberate language strategy. They relied on Python for LLM interactions and rapid experimentation, given its rich artificial intelligence and machine learning (AI/ML) landscape. They implemented complex business processing in Java to capitalize on its performance characteristics for high-throughput data processing and integration with existing trading systems.第三，团队学会了预测用户行为的变化。实际使用证明是动态的。交易员以意想不到的方式与系统交互，其模式随时间变化。投资于可观察性和用户反馈循环对于快速适应这些变化的行为至关重要。最后，团队采用了深思熟虑的语言策略。他们依赖 Python 进行 LLM 交互和快速实验，因为 Python 拥有丰富的 AI/ML 生态系统。他们使用 Java 实现复杂的业务处理，以利用其在处理高吞吐量数据和与现有交易系统集成方面的性能优势。
Business impact业务影响
Since launch, the trade assistant solution has delivered measurable efficiency gains across global sales and trading operations, allowing traders to redirect time toward client relationships and strategic decision-making rather than manual data wrangling. These efficiency gains translate directly into a competitive advantage, as trading desks can now dedicate more capacity to onboarding clients and deepening existing relationships. The solution delivers a personalized experience by adapting to each client’s query using MCP tools to access structured, unstructured, and in-memory data sources and dynamically generating graphs and charts in response. Beyond the trading desk, the solution has materially reduced the IT time and effort previously consumed by repetitive dashboard creation, freeing technology teams to focus on higher-value strategic initiatives. Perhaps most notably, the ability to securely query millions of rows of equities trading data using natural language has democratized data access. This fosters a data-driven culture where decisions are informed by real-time analytics rather than intuition or delayed reports.自推出以来，交易助手解决方案已在全球销售和交易运营中实现了可衡量的效率提升，使交易员能够将时间重新分配给客户关系和战略决策，而不是手动数据处理。这些效率提升直接转化为竞争优势，因为交易台现在可以将更多精力用于吸引客户和深化现有关系。该解决方案通过使用 MCP 工具访问结构化、非结构化和内存数据源，并动态生成图表图形来响应每个客户的查询，从而提供个性化体验。在交易台之外，该解决方案显著减少了 IT 团队之前用于重复创建仪表板的时间和精力，使技术团队能够专注于更高价值的战略计划。最值得注意的是，使用自然语言安全查询数百万行股票交易数据的能力使数据访问民主化。这培养了一种数据驱动的文化，决策基于实时分析而非直觉或延迟报告。
Looking ahead未来展望
Jefferies’ roadmap signals the scalability and ambition of this agentic AI approach. The team plans to roll out the Trade Assistant globally for multiple product types and desks, enhance audit capabilities with code generation tools that use natural language processing (NLP), and add Amazon Bedrock AgentCore features to their enterprise AI system. These investments show a commitment to expanding AI-powered capabilities across the organization. The integration with existing Equities business intelligence (BI) applications and the ability to query multiple structured, unstructured, and in-memory data sources positions Jefferies at the forefront of AI-driven trading innovation.Jefferies 的路线图彰显了这种代理式 AI 方法的可扩展性和雄心。团队计划在全球范围内为多种产品类型和交易台推出交易助手，通过使用自然语言处理 (NLP) 的代码生成工具增强审计能力，并为其企业 AI 系统添加 Amazon Bedrock AgentCore 功能。这些投资表明了对在整个组织内扩展 AI 驱动能力的承诺。与现有股票业务智能 (BI) 应用的集成以及查询多种结构化、非结构化和内存数据源的能力，使 Jefferies 处于 AI 驱动交易创新的前沿。
Conclusion结论
In this post, we walked through how Jefferies and AWS collaborated to build an agentic AI trade assistant that transforms how traders interact with equities data across global sales and trading operations. The Jefferies Equities Trade Assistant exemplifies how agentic AI is reshaping capital markets by turning every trader into a data scientist capable of extracting sophisticated insights through simple conversation. These agentic AI systems act as intelligent collaborators that understand context, learn from interactions, and proactively guide users toward better outcomes. The shift from reactive data retrieval to proactive intelligence marks a new era in trading operations. As this technology scales globally and across asset classes, it promises to redefine competitive advantage in front office operations for years to come.在本文中，我们介绍了 Jefferies 和 AWS 如何合作构建一个代理式 AI 交易助手，该助手改变了交易员在全球销售和交易运营中与股票数据交互的方式。Jefferies 股票交易助手展示了代理式 AI 如何重塑资本市场，通过简单的对话将每位交易员转变为能够提取复杂洞察的数据科学家。这些代理式 AI 系统充当智能协作者，理解上下文、从交互中学习，并主动引导用户获得更好的结果。从被动数据检索到主动智能的转变标志着交易运营的新时代。随着这项技术在全球范围内跨资产类别扩展，它有望在未来几年重新定义前台运营的竞争优势。
To get started building your own agentic AI applications, explore Strands Agents, learn more about the MCP integration patterns used in this solution, or contact your AWS account team to discuss engagement tailored to your use case.要开始构建您自己的代理式 AI 应用程序，请探索 Strands Agents，了解有关此解决方案中使用的 MCP 集成模式的更多信息，或联系您的 AWS 客户团队讨论适合您用例的合作方案。