Over the past couple of years, Prompt Engineering has become one of the defining skills for working with artificial intelligence. As Large Language Models became more capable, organizations quickly realized that the quality of the prompt often determined the quality of the response. Learning how to provide context, define objectives, assign roles, and structure instructions became an important part of getting the most from AI.过去几年里，提示词工程 (Prompt Engineering) 已成为使用人工智能的关键技能之一。随着大语言模型能力不断增强，企业很快意识到，提示词的质量往往决定了响应的质量。学习如何提供背景信息、定义目标、分配角色以及构建指令，已成为充分发挥 AI 效能的重要一环。
Prompt Engineering is still incredibly valuable, but AI is beginning to move beyond simple question-and-answer interactions.提示词工程依然极具价值，但 AI 正在开始超越简单的问答交互。
Today’s AI applications rarely operate in isolation. They retrieve information from enterprise data sources, interact with business applications, call APIs, invoke tools, collaborate with other AI agents, and maintain context across increasingly complex workflows. As these systems become more sophisticated, providing a well-written prompt is only one part of the overall solution.如今的 AI 应用很少孤立运行。它们需要从企业数据源中检索信息、与业务应用交互、调用 API、启动工具、与其他 AI 智能体协作，并在日益复杂的工作流程中保持上下文。随着这些系统变得愈发复杂，提供一段精心编写的提示词只是整体解决方案的一部分。
This is where Graph Engineering enters the conversation.这就是图工程 (Graph Engineering) 切入的领域。
Rather than focusing solely on how we communicate with an AI model, Graph Engineering focuses on how information, relationships, workflows, and reasoning are organized before the model is ever asked to generate a response. It shifts the emphasis away from writing better prompts and towards building better knowledge structures that allow AI to reason more effectively.图工程不仅仅关注我们如何与 AI 模型沟通，更关注在要求模型生成响应之前，信息、关系、工作流程和推理逻辑是如何组织的。它将重点从“编写更好的提示词”转向“构建更好的知识结构”，从而使 AI 能够更有效地进行推理。
While the term is still relatively new, the concepts behind Graph Engineering are already influencing how many organizations are designing the next generation of AI applications.尽管这一术语相对较新，但图工程背后的理念已经影响了许多企业设计下一代 AI 应用的方式。
Moving Beyond Documents and Context Windows超越文档与上下文窗口
Traditional Large Language Models work exceptionally well when the information needed to answer a question fits comfortably inside the model’s context window. If you provide enough relevant information in the prompt, the model can often generate impressive responses. Enterprise environments rarely work that way. Consider a user asking:当回答问题所需的信息能够完全容纳在模型的上下文窗口内时，传统大语言模型表现得非常出色。如果你在提示词中提供了足够的相关信息，模型往往能生成令人印象深刻的回答。然而，企业环境很少是这样的。试想用户提出这样一个问题：
“Which cybersecurity projects is Sarah working on that support our European customers, and what compliance requirements apply?”“Sarah 正在负责哪些支持我们欧洲客户的网络安全项目？有哪些合规要求适用？”
That question isn’t answered by a single document. Instead, it requires understanding relationships between employees, departments, projects, customers, geographic regions, compliance frameworks, policies, and perhaps even information stored across multiple business systems.这个问题无法通过单一文档回答。它需要理解员工、部门、项目、客户、地理区域、合规框架、政策，甚至跨多个业务系统存储的信息之间的复杂关系。
A traditional Retrieval-Augmented Generation (RAG) solution may search several documents containing pieces of that information. A graph-based approach starts somewhere entirely different. Instead of retrieving isolated documents, it navigates the relationships between connected pieces of information before deciding what context should be presented to the language model.传统的检索增强生成 (RAG) 解决方案可能会搜索包含这些信息片段的几份文档。而基于图的方法则完全不同。它不是检索孤立的文档，而是在决定向语言模型呈现哪些上下文之前，先遍历连接信息片段之间的关系。
The distinction may seem subtle, but it fundamentally changes how AI reasons about information.这种区别看似细微，但它从根本上改变了 AI 对信息进行推理的方式。
What Is Graph Engineering?什么是图工程？
At its core, Graph Engineering is the practice of representing information as a network of connected entities rather than as isolated pieces of text.图工程的核心在于将信息表示为连接实体的网络，而不是孤立的文本片段。
Instead of viewing an organization as a collection of documents, Graph Engineering models the relationships between the things that matter. Employees belong to departments, departments own projects, projects support customers, customers operate within regions, regions are governed by regulations, and those regulations link to internal policies. Every connection provides additional context that helps explain how the organization actually works.图工程不再将组织视为文档的集合，而是对关键事物之间的关系进行建模。员工属于部门，部门拥有项目，项目支持客户，客户在特定区域运营，区域受法规管辖，而这些法规又与内部政策相关联。每一个连接都提供了额外的上下文，有助于解释组织是如何实际运作的。
Humans naturally think in relationships.人类天生就是通过关系来思考的。
When someone mentions a project you’ve worked on, you don’t simply remember the project name. You immediately associate the people involved, the customers, the technologies, the meetings, the challenges, and the outcomes. Those relationships are often more valuable than any single document describing the project.当有人提到你参与过的项目时，你不会仅仅记住项目名称。你会立即联想到相关人员、客户、技术、会议、挑战和成果。这些关系往往比任何描述该项目的单一文档更有价值。
Graph Engineering attempts to give AI systems a similar understanding by allowing them to navigate relationships rather than simply searching text.图工程旨在让 AI 系统通过遍历关系而非单纯搜索文本，获得类似的理解能力。
Why Relationships Matter为什么关系至关重要
One of the limitations of traditional search is that it primarily answers the question:传统搜索的局限性之一在于它主要回答以下问题：
“Which documents contain these words?”“哪些文档包含这些词？”
Graph Engineering asks a different question:而图工程提出了一个不同的问题：
“How are these things connected?”“这些事物是如何关联的？”
That shift becomes increasingly valuable as AI applications grow in complexity. Imagine an AI assistant helping a project manager prepare for a customer meeting. Rather than simply searching SharePoint for documents containing the customer’s name, a graph-based approach could identify the account manager, recent support tickets, previous projects, engineering teams involved, outstanding action items, upcoming milestones, and related product documentation before assembling the context presented to the model.随着 AI 应用复杂度的增加，这种转变变得愈发重要。想象一下，一个 AI 助手正在帮助项目经理准备客户会议。与其仅仅在 SharePoint 中搜索包含客户名称的文档，基于图的方法可以识别出客户经理、最近的支持工单、过往项目、涉及的工程团队、未完成的任务项、即将到来的里程碑以及相关的产品文档，然后再将这些上下文汇总呈现给模型。
The AI is no longer retrieving information because the same words appear in multiple documents. It is retrieving information because the underlying relationships indicate that those pieces of information are connected.AI 不再是因为多个文档中出现了相同的词汇而检索信息，而是因为底层的关系表明这些信息片段是相互关联的。
This often produces responses that are more relevant, more contextual, and more useful than relying on keyword searches alone.这通常能产生比单纯依赖关键词搜索更相关、更具上下文且更有用的响应。
Graph Engineering and Agentic AI图工程与智能体 AI (Agentic AI)
One of the reasons Graph Engineering is receiving increased attention is the rapid growth of agentic AI.图工程受到越来越多的关注，原因之一是智能体 AI 的快速发展。
Unlike traditional chatbots that simply answer questions, AI agents are expected to perform tasks, make decisions, coordinate workflows, and interact with multiple business systems. To do that effectively, they need a much richer understanding of the environment in which they operate.与仅回答问题的传统聊天机器人不同，AI 智能体需要执行任务、做出决策、协调工作流程并与多个业务系统交互。为了有效地做到这一点，它们需要对其运行环境有更深刻的理解。
Consider an AI agent responsible for onboarding a new employee.以一个负责新员工入职的 AI 智能体为例。
The agent may need to understand the employee’s department, reporting manager, location, required applications, security groups, hardware requirements, training courses, compliance obligations, and licensing needs. None of those decisions exist within a single document. Instead, they emerge from the relationships between multiple business systems.该智能体可能需要了解员工的部门、汇报经理、工作地点、所需应用、安全组、硬件需求、培训课程、合规义务和许可需求。这些决策并非存在于单一文档中，而是源于多个业务系统之间的关系。
Graph Engineering provides a structured way of representing those relationships, making it easier for AI agents to navigate complex organizational environments without requiring every possible piece of context to be embedded inside a prompt.图工程提供了一种结构化的方式来表示这些关系，使 AI 智能体能够更轻松地在复杂的组织环境中导航，而无需将所有可能的上下文都嵌入到提示词中。
Improving Reasoning, Not Just Retrieval提升推理能力，而非仅仅是检索
One misconception is that Graph Engineering simply provides another way of searching documents. In reality, its greatest strength lies in improving reasoning.一个常见的误区是认为图工程仅仅是搜索文档的另一种方式。实际上，它最大的优势在于提升推理能力。
When an AI system understands how information relates to other information, it can begin making more informed decisions. It can identify dependencies, recognize missing information, explain why recommendations were made, and provide responses that reflect the broader business context rather than isolated facts.当 AI 系统理解了信息之间如何关联时，它就能开始做出更明智的决策。它可以识别依赖关系、发现缺失信息、解释做出推荐的原因，并提供反映更广泛业务背景而非孤立事实的响应。
For example, instead of simply answering:例如，与其简单地回答：
“Sarah is assigned to Project Falcon.”“Sarah 被分配到了猎鹰项目 (Project Falcon)。”
a graph-aware AI may explain:具备图感知能力的 AI 可能会这样解释：
“Sarah is assigned to Project Falcon, which supports Contoso’s European operations. The project is owned by the Cloud Engineering team, requires GDPR compliance, and currently involves three active workstreams that are scheduled for completion next quarter.”“Sarah 被分配到了猎鹰项目，该项目支持 Contoso 的欧洲业务。该项目由云工程团队负责，需要符合 GDPR 合规要求，目前涉及三个预定于下季度完成的活跃工作流。”
The answer is richer because the AI understands the relationships surrounding the original question.这个答案更加丰富，因为 AI 理解了围绕原始问题的所有关联信息。
Why Organizations Should Care为什么企业应该关注
Graph Engineering isn’t simply another AI buzzword. It addresses one of the biggest challenges organizations face as AI becomes more deeply integrated into everyday business operations.图工程不仅仅是另一个 AI 流行词。随着 AI 越来越深入地集成到日常业务运营中，它解决了企业面临的最大挑战之一。
Most enterprise knowledge doesn’t exist in a single location. Information is spread across Microsoft 365, SharePoint, Microsoft Teams, Microsoft Graph, CRM platforms, ticketing systems, databases, documentation platforms, and countless other applications. While traditional RAG systems can retrieve information from many of these sources, Graph Engineering helps explain how that information fits together.大多数企业知识并非存在于单一位置。信息分散在 Microsoft 365、SharePoint、Microsoft Teams、Microsoft Graph、CRM 平台、工单系统、数据库、文档平台以及无数其他应用中。虽然传统的 RAG 系统可以从这些来源中检索信息，但图工程有助于解释这些信息是如何组合在一起的。
For organizations, this offers several important benefits.对于企业而言，这提供了几个重要的益处。
AI systems can provide more contextual responses because they understand relationships rather than isolated facts. Retrieval becomes more targeted because the AI follows meaningful connections instead of relying entirely on keyword similarity. AI agents can make better decisions because they understand business dependencies, while security and governance become easier to apply because permissions and ownership can also become part of the graph itself.AI 系统可以提供更具上下文的响应，因为它们理解的是关系而非孤立事实。检索变得更有针对性，因为 AI 遵循的是有意义的连接，而不是完全依赖关键词相似度。AI 智能体可以做出更好的决策，因为它们理解业务依赖关系；同时，安全和治理也变得更容易实施，因为权限和所有权本身也可以成为图的一部分。
Perhaps most importantly, Graph Engineering reduces the amount of context users need to manually provide. Instead of explaining every relationship within the prompt, the AI already understands how those relationships exist inside the organization’s knowledge model.最重要的是，图工程减少了用户手动提供上下文的需求。AI 无需在提示词中解释每一层关系，因为它已经理解这些关系是如何存在于组织的知识模型中的。
Graph Engineering Isn’t Replacing Prompt Engineering图工程不会取代提示词工程
It would be easy to assume that Graph Engineering replaces Prompt Engineering, but the reality is quite different.人们很容易认为图工程会取代提示词工程，但事实并非如此。
A well-written prompt still matters. Users will always need to communicate objectives, constraints, and desired outcomes. What Graph Engineering changes is the quality of the information available before the prompt is processed.编写良好的提示词依然重要。用户始终需要传达目标、约束条件和期望的结果。图工程所改变的是在处理提示词之前可用信息的质量。
Rather than forcing users to describe complex relationships themselves, the graph provides that context automatically. The prompt becomes simpler because the AI already understands much of the surrounding environment.图工程不再强迫用户自己描述复杂的关系，而是自动提供这些上下文。提示词变得更简单了，因为 AI 已经理解了周围环境的大部分内容。
In many ways, Prompt Engineering and Graph Engineering complement one another. One improves how we communicate with AI. The other improves what the AI already knows about the world in which it is operating.在许多方面，提示词工程和图工程是相辅相成的。前者改善了我们与 AI 的沟通方式，后者则改善了 AI 对其所处世界的认知。
Looking Ahead展望未来
Graph Engineering is still an emerging discipline, but it reflects a broader shift in how enterprise AI systems are being designed. As organizations move beyond standalone chatbots towards intelligent assistants and autonomous agents, understanding relationships becomes just as important as understanding individual pieces of information.图工程仍是一门新兴学科，但它反映了企业 AI 系统设计方式的更广泛转变。随着企业从独立的聊天机器人转向智能助手和自主智能体，理解关系变得与理解个体信息片段同等重要。
Whether you’re building AI solutions on Azure AI Foundry, integrating Microsoft 365 Copilot with enterprise data, developing Retrieval-Augmented Generation applications, or exploring autonomous AI agents, the ability to organize knowledge through connected relationships is likely to become an increasingly valuable capability.无论你是在 Azure AI Foundry 上构建 AI 解决方案，将 Microsoft 365 Copilot 与企业数据集成，开发检索增强生成应用，还是在探索自主 AI 智能体，通过连接关系组织知识的能力都将成为一项日益宝贵的技能。
Prompt Engineering taught us how to ask AI better questions.提示词工程教会了我们如何向 AI 提出更好的问题。
Graph Engineering is beginning to teach AI how to better understand the world those questions exist within.图工程则开始教会 AI 如何更好地理解这些问题所处的环境。
While the technology will undoubtedly continue to evolve, the underlying principle is unlikely to change. The future of enterprise AI isn’t just about accessing more information. It’s about understanding how that information connects together, and using those relationships to produce responses that are more intelligent, more contextual, and ultimately more valuable.虽然技术无疑会继续演进，但其基本原则不太可能改变。企业 AI 的未来不仅仅在于获取更多信息，更在于理解这些信息是如何连接在一起的，并利用这些关系生成更智能、更具上下文且最终更有价值的响应。