Many Companies Use AI. Few Know How to Build an AI-Native Enterprise Data Platform.
Many Companies Use AI. Few Know How to Build an AI-Native Enterprise Data Platform.
许多公司都在使用人工智能，但很少有人知道如何构建人工智能原生企业数据平台。
A practical enterprise AI architecture with data agents, AI-powered QA, and AI governance. 一套包含数据智能体、AI 驱动的质量保证及 AI 治理的实用企业级 AI 架构。
Many organizations have already adopted AI to improve everyday productivity over the past few years. AI has rapidly become part of enterprise workflows: Building internal chatbots to answer HR, IT, or policy questions. Using ChatGPT or Microsoft Copilot to search and summarize documents. Assisting developers with code generation and debugging. Drafting reports, emails, meeting notes, and business presentations. These applications have undoubtedly improved individual productivity. 过去几年中，许多组织已经采用人工智能来提高日常生产力。AI 已迅速成为企业工作流程的一部分：构建内部聊天机器人以回答人力资源、IT 或政策问题；使用 ChatGPT 或 Microsoft Copilot 搜索并总结文档；协助开发人员进行代码生成和调试；起草报告、电子邮件、会议纪要和商业演示文稿。这些应用无疑提高了个人生产力。
But if we believe that’s where AI’s potential ends, we’re missing the important parts. The reality is that many companies stop here and fail to tap into AI’s most transformative capabilities. AI can do much more. In my view, one of its most powerful applications lies in transforming the enterprise data ecosystem. 但如果我们认为 AI 的潜力仅止于此，那就错过了重点。现实情况是，许多公司止步于此，未能挖掘 AI 最具变革性的能力。AI 能做的远不止于此。在我看来，它最强大的应用之一在于重塑企业数据生态系统。
Beyond Chatbot: What AI Agents Actually Do
超越聊天机器人：AI 智能体究竟在做什么
Data teams in many organizations spend a significant amount of time every day answering questions from business users. For example, if you are a data analyst working for an E-commerce platform, you may receive tons of questions from business like: “Which product categories contributed most to revenue growth in Southeast Asia last quarter?“ 许多组织的数据团队每天花费大量时间回答业务用户的问题。例如，如果你是一家电子商务平台的数据分析师，你可能会收到大量来自业务部门的问题，例如：“上个季度东南亚地区哪些产品类别对收入增长贡献最大？”
As a data analyst, here’s what you typically do: Business Question ↓ Write SQL ↓ Export Data ↓ Create Charts ↓ Explain Findings. Now, you hand this over to an AI agent, and the workflow becomes: Business Asks ↓ Agent Retrieves Semantic Information ↓ Generates SQL ↓ Returns Explanation. 作为数据分析师，你通常的做法是：业务提问 ↓ 编写 SQL ↓ 导出数据 ↓ 创建图表 ↓ 解释发现。现在，如果你将其交给 AI 智能体，工作流程就变成了：业务提问 ↓ 智能体检索语义信息 ↓ 生成 SQL ↓ 返回解释。
On the surface, the business user is still just having a conversation with AI by throwing a question to get an answer. Feels a lot like chatting with a bot, doesn’t it? But working with an AI agent is fundamentally different from chatting with a chatbot. 从表面上看，业务用户仍然只是通过提问来获取答案，这与和机器人聊天感觉很像，对吧？但与 AI 智能体协作与和聊天机器人对话有着本质的区别。
What is an AI Agent?
什么是 AI 智能体？
An AI agent is an autonomous system that perceives its environment, makes decisions, and takes concrete actions to achieve a goal. The key difference between an AI agent and a chatbot is that an AI agent can take actions instead of simply generating responses. While chatbots primarily answer questions through conversations, AI agents execute multi-step tasks, interact with software and tools, make decisions, and work toward completing a specific goal autonomously. AI 智能体是一个能够感知环境、做出决策并采取具体行动以实现目标的自主系统。AI 智能体与聊天机器人的关键区别在于，智能体可以采取行动，而不仅仅是生成回复。聊天机器人主要通过对话回答问题，而 AI 智能体则可以执行多步骤任务、与软件和工具交互、做出决策，并自主朝着完成特定目标努力。
Although the business users may feel like they’re just having a conversation with the AI agent, behind the scenes the agent is busy executing a series of actions—retrieving relevant context, generating and running SQL queries, interpreting the results, and then delivering a polished answer. 尽管业务用户可能觉得只是在与 AI 智能体进行对话，但在幕后，智能体正忙于执行一系列操作——检索相关上下文、生成并运行 SQL 查询、解读结果，然后提供一份完善的答案。
In the world of data, these AI agents are usually called data agents. They focus on retrieving, querying, analyzing, and explaining enterprise data through natural language interactions. Most data platforms, like Microsoft Fabric, Snowflake, and Databricks, have data agents integrated into themselves. For example, Fabric has the Fabric data agent, Snowflake has Cortex Analyst, and Databricks has AI/BI Genie. 在数据领域，这些 AI 智能体通常被称为“数据智能体”。它们专注于通过自然语言交互来检索、查询、分析和解释企业数据。大多数数据平台（如 Microsoft Fabric、Snowflake 和 Databricks）都内置了数据智能体。例如，Fabric 有 Fabric 数据智能体，Snowflake 有 Cortex Analyst，Databricks 有 AI/BI Genie。
Data agents are designed to act as AI data analysts. They reduce the repetitive work of pulling data, writing routine queries and generating standard reports so that analysts spend less time performing repetitive data retrieval and reporting tasks, and more time on work that requires human judgment and critical thinking. 数据智能体的设计初衷是充当 AI 数据分析师。它们减少了提取数据、编写常规查询和生成标准报告等重复性工作，使分析师能减少在重复性数据检索和报告任务上花费的时间，从而将更多精力投入到需要人类判断和批判性思维的工作中。
Looks beautiful? But in practice, simply relying on data agents often leads an organization to the following problems: Ambiguous business terminology, Multi-step reasoning, Business rules, Inconsistent answers, Retrieval quality, Handling edge cases that sit outside predefined semantic layers, Keeping up when data schemas change, Maintaining accuracy across different business contexts. 看起来很美好？但在实践中，仅仅依赖数据智能体往往会导致组织面临以下问题：模糊的业务术语、多步推理、业务规则、答案不一致、检索质量、处理预定义语义层之外的边缘情况、应对数据模式变更、以及在不同业务背景下保持准确性。
These aren’t small annoyances. For example, when the business user typed “What is the percent of revenue growth in Southeast Asia last quarter?“, it would be very frustrating if the agent answers with no data provided or provides incorrect number. When a data agent gets something wrong, it doesn’t just frustrate the users. To make matters worse, it can feed bad information into a business decision. The bottom line? Relying on data agents alone isn’t enough. The real path forward should be connecting data platforms with enterprise AI architectures. 这些并非小麻烦。例如，当业务用户输入“上个季度东南亚地区的收入增长百分比是多少？”时，如果智能体回答没有数据或提供错误的数字，会非常令人沮丧。当数据智能体出错时，不仅会让用户感到挫败，更糟糕的是，它可能会将错误信息输入到商业决策中。结论是什么？仅靠数据智能体是不够的。真正的出路在于将数据平台与企业级 AI 架构连接起来。
Where AI Fits in the Data Platform
AI 在数据平台中的位置
A typical enterprise data platform workflow looks like this: data engineers design the architecture, implement the creation of ETL pipelines and data warehouse and manage the data governance. Business users raise business-related questions, data analysts create BI reports or dashboard. Business users then use dashboard for analysis and generate insights. 典型的企业数据平台工作流程如下：数据工程师设计架构，实施 ETL 管道和数据仓库的创建，并管理数据治理。业务用户提出业务相关问题，数据分析师创建 BI 报告或仪表板。随后，业务用户使用仪表板进行分析并生成洞察。
This workflow has run for decades and effectively supported and empowered many businesses. Then AI came. People start thinking: Why do business users keep asking the same questions? Why do data engineers spend hours validating ETL jobs? Why do analysts manually investigate KPI changes? Quickly, AI is embedded into the data platform. Data agents are used. Agentic coding is introduced. Then come new questions: Why do we trust AI-generated answers without measuring their quality? Why does AI become less reliable as business rules grow more complex? These aren’t isolated problems. They’re symptoms of a traditional data platform that was designed for storing and reporting data instead. 这种工作流程已经运行了几十年，有效地支持并赋能了许多企业。然后 AI 出现了。人们开始思考：为什么业务用户总是问同样的问题？为什么数据工程师要花数小时验证 ETL 作业？为什么分析师要手动调查 KPI 的变化？很快，AI 被嵌入到数据平台中。数据智能体被使用，智能体编码被引入。随之而来的是新的问题：为什么我们在不衡量质量的情况下就信任 AI 生成的答案？为什么随着业务规则变得复杂，AI 变得越来越不可靠？这些并非孤立的问题，而是传统数据平台（其设计初衷仅为存储和报告数据）所表现出的症状。