The foundational elements of AI architecture that IT leaders need to scale

IT 领导者实现 AI 规模化所需的基础架构要素

Sponsored in partnership with Elastic. With the rapid progress of AI capabilities and the move to agentic systems, organizations are expanding their use cases as the technology continues to grow. That constant evolution also introduces risk, leaving IT leaders to wonder which investments will prove valuable even six months into the future. 本内容由 Elastic 赞助。随着 AI 能力的飞速进步以及向智能体（Agentic）系统的转型，各组织正在不断扩大其技术应用场景。这种持续的演进也带来了风险，使得 IT 领导者不禁怀疑，哪些投资在六个月后依然具有价值。

Returning to the foundational elements of AI architecture—the structural framework required for deploying and managing reliable, integrated AI systems at scale—allows technology leaders to make astute decisions today while supporting a future of AI agents that can retrieve information, make decisions, and execute complex workflows across systems. 回归 AI 架构的基础要素——即部署和管理大规模、可靠且集成化 AI 系统所需的结构框架——能够让技术领导者在做出明智决策的同时，为未来能够跨系统检索信息、做出决策并执行复杂工作流的 AI 智能体打下基础。

Four elements of AI architecture you can count on

你可以信赖的四个 AI 架构要素

The following capabilities provide a stable compass on the path to production-ready deployment, regardless of how the underlying technology evolves. 无论底层技术如何演变，以下能力都能为通往生产级部署的道路提供稳定的指南。

1. Prepare data for AI at scale

1. 为大规模 AI 准备数据

Models are only as reliable as the data they can access, and poor data quality leads to AI hallucinations, bias, and unreliable outputs. Most enterprises rely on legacy systems, inconsistent data structures, fragmented ownership, and incomplete datasets, making it difficult to scale AI effectively. Powerful as it is, AI itself cannot solve these underlying data problems. 模型的可靠性取决于其所能访问的数据，而糟糕的数据质量会导致 AI 产生幻觉、偏见和不可靠的输出。大多数企业依赖于遗留系统、不一致的数据结构、碎片化的所有权和不完整的数据集，这使得 AI 的有效规模化变得困难。尽管 AI 功能强大，但它本身无法解决这些底层数据问题。

As Adnan Adil, CIO of Elastic, explains: “The data is a durable part of AI architecture because without it, these models won’t run, won’t provide the right context, or won’t give the right level of services that we’re looking to implement.” 正如 Elastic 首席信息官 Adnan Adil 所解释的那样：“数据是 AI 架构中持久的一部分，因为没有它，这些模型就无法运行，无法提供正确的上下文，也无法提供我们想要实现的相应服务水平。”

Industry surveys consistently cite data quality as one of the greatest barriers to AI success. “The data quality has to be good; otherwise, the user loses confidence in the system,” says Adil. An effective AI strategy begins with connecting data across the organization and ensuring it is organized, accurate, governed, and accessible in real time. 行业调查一致认为，数据质量是 AI 成功道路上最大的障碍之一。Adil 表示：“数据质量必须过关；否则，用户就会对系统失去信心。”有效的 AI 策略始于连接整个组织的数据，并确保其具备组织性、准确性、合规性，且能够实时访问。

2. Use context engineering to deliver the right data to every AI query

2. 利用上下文工程为每个 AI 查询提供正确的数据

Context engineering ensures that the model draws on the most pertinent information for each query, selecting and organizing the data needed to produce accurate answers efficiently. Effective context engineering shapes the inputs that guide AI reasoning and action. While prompt engineering focuses on how a request is worded, context engineering designs the entire information environment around the model: retrieving the right data and presenting it in a structured, machine-readable way. 上下文工程确保模型在处理每个查询时都能利用最相关的信息，通过筛选和组织所需数据来高效生成准确答案。有效的上下文工程塑造了引导 AI 推理和行动的输入内容。如果说提示词工程（Prompt Engineering）关注的是请求的措辞，那么上下文工程则是围绕模型设计整个信息环境：检索正确的数据并以结构化、机器可读的方式呈现。

Many organizations are discovering that reliable AI depends as much on context quality as on the strength of the model. Context engineering relies on a modernized, unified data foundation as well as retrieval and memory systems such as retrieval augmented generation (RAG) and vector databases. 许多组织发现，可靠的 AI 不仅取决于模型的强度，同样也取决于上下文的质量。上下文工程依赖于现代化、统一的数据基础，以及检索增强生成（RAG）和向量数据库等检索与记忆系统。

3. Build AI governance and LLM observability in from the start

3. 从一开始就构建 AI 治理和 LLM 可观测性

Strong governance and LLM observability help organizations maintain control over how AI systems use data, monitor system performance, and identify problems before they affect operations. In the absence of clear controls around retrieval, workflows, and model usage, AI systems often process far more information than necessary. This inefficiency also drives up operating costs by requiring additional computing resources, often reflected in higher token consumption and API charges. 强大的治理和 LLM 可观测性有助于组织掌控 AI 系统使用数据的方式，监控系统性能，并在问题影响运营之前将其识别出来。在缺乏针对检索、工作流和模型使用的明确控制时，AI 系统往往会处理远超必要的信息。这种低效还会因需要额外的计算资源而推高运营成本，通常表现为更高的 Token 消耗和 API 费用。

Governance also works in tandem with robust security. AI expands the attack surface, introducing risks such as prompt-based data leakage, model vulnerabilities, and adversarial inputs. Protecting sensitive information requires strong access controls, monitoring, and oversight. 治理也与强大的安全性相辅相成。AI 扩大了攻击面，引入了诸如基于提示词的数据泄露、模型漏洞和对抗性输入等风险。保护敏感信息需要严格的访问控制、监控和监督。

For governance systems to support transparent, compliant, trustworthy, and cost-effective AI, organizations cannot leave them as a layer to add later. Governance structures need to be embedded into architecture, workflows, and decision-making processes from the outset. When governance is established from the start, it enables robust observability. 为了使治理系统能够支持透明、合规、可信且具有成本效益的 AI，组织不能将其视为事后添加的层级。治理结构需要从一开始就嵌入到架构、工作流和决策过程中。当治理从一开始就建立起来时，它就能实现强大的可观测性。

Observability helps organizations understand how AI applications are performing in practice. Mechanisms for LLM observability and benchmarking allow teams to assess accuracy and utility over time, monitor adoption patterns, and adjust systems as conditions change. Real-time visibility into AI behavior allows organizations to measure performance against expectations, identify gaps between intent and reality, and continuously refine systems as requirements evolve. 可观测性有助于组织了解 AI 应用在实践中的表现。LLM 可观测性和基准测试机制使团队能够评估长期的准确性和效用，监控采用模式，并根据情况变化调整系统。对 AI 行为的实时可见性使组织能够对照预期衡量性能，识别意图与现实之间的差距，并随着需求的变化不断优化系统。