The foundational elements of AI architecture that IT leaders need to scaleIT领导者需要规模化的AI架构基础要素

Four elements of AI architecture you can count on你可以信赖的四大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，以下能力都为走向生产级部署提供了稳定的指南针。

1. Prepare data for AI at scale1. 为规模化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.模型的可靠性取决于其能访问的数据，而低质量的数据会导致AI幻觉、偏见和不可靠的输出。

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.多数企业依赖遗留系统、不一致的数据结构、碎片化的所有权和不完整的数据集，这使得有效规模化AI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.” 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.正如Elastic首席信息官Adnan Adil所解释的：“数据是AI架构中持久的部分，因为没有数据，这些模型就无法运行，无法提供正确的上下文，也无法提供我们希望通过系统实现的服务水平。”行业调查一致将数据质量列为AI成功最大的障碍之一。Adil说：“数据质量必须良好；否则用户会对系统失去信心。”

An effective AI strategy begins with connecting data across the organization and ensuring it is organized, accurate, governed, and accessible in real time. These considerations are most effective when built into models and architecture from the start. Scalable data architecture allows AI systems to evolve alongside the business and connect reliably to the internal information needed to deliver meaningful value.有效的AI策略始于跨组织连接数据，并确保其组织有序、准确、受治理且可实时访问。这些考量最好从一开始就融入模型和架构中。可扩展的数据架构使AI系统能够随着业务发展而演进，并可靠地连接到提供有意义价值所需的内部信息。

Gartner predicts that companies will abandon 60% of all AI projects through 2026 if they are not supported by AI-ready data. Avoiding that outcome includes clear data standards and ownership, clean and labeled data, and pipelines that support real-time retrieval.Gartner预测，到2026年，如果缺乏AI就绪的数据支撑，企业将放弃60%的AI项目。避免这一结果需要明确的数据标准和所有权、清洁且带标签的数据，以及支持实时检索的数据管道。

2. Use context engineering to deliver the right data to every AI query2. 利用上下文工程为每个AI查询提供正确数据

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.上下文工程确保模型针对每个查询提取最相关的信息，选择并组织所需数据，以高效生成准确答案。

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. Many organizations are discovering that reliable AI depends as much on context quality as on the strength of the model.有效的上下文工程塑造了指导AI推理和行动的输入。虽然提示工程关注请求的措辞方式，但上下文工程设计了模型周围的整个信息环境：检索正确的数据，并以结构化、机器可读的方式呈现。许多组织发现，可靠的AI既依赖于模型强度，也依赖于上下文质量。

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. It also requires careful prioritization to determine what information matters most, what should be excluded, and when different types of information should be used. Feeding models too much context can dilute relevant details, increase costs, and slow response times.上下文工程依赖于现代化、统一的数据基础，以及检索和记忆系统，如检索增强生成（RAG）和向量数据库。它还需要仔细的优先级排序，以确定哪些信息最重要、哪些应排除，以及何时使用不同类型的信息。向模型输入过多上下文可能会稀释相关细节、增加成本并减慢响应速度。

“Minimum context, correct and current data, and machine-readable information are critical to effective context engineering,” Adil says.Adil说：“最少上下文、正确且最新的数据、以及机器可读的信息，是有效上下文工程的关键。”

3. Build AI governance and LLM observability in from the start3. 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.强大的治理和LLM可观测性帮助组织保持对AI系统如何使用数据的控制、监控系统性能，并在问题影响运营之前发现它们。

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.在缺乏围绕检索、工作流和模型使用的明确控制时，AI系统往往处理远多于必要的信息。这种低效率还会因需要额外计算资源而推高运营成本，通常体现在更高的令牌消耗和API费用上。

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.治理还与强大的安全措施协同工作。AI扩大了攻击面，引入了诸如基于提示的数据泄露、模型漏洞和对抗性输入等风险。保护敏感信息需要强大的访问控制、监控和监督。

Adil notes that essential controls — including those related to security, granular cost management, project controls, data security, and architecture—are frequently insufficient.Adil指出，包括安全、细粒度成本管理、项目控制、数据安全和架构在内的关键控制措施常常不够充分。

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.为了让治理系统支持透明、合规、可信且成本高效的AI，组织不能将其留作事后添加的层次。治理结构需要从一开始就嵌入架构、工作流程和决策过程中。

When governance is established from the start, it enables robust observability. 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. Observability also helps organizations gain trust by increasing visibility of model performance, behavior, and failure points.当治理从一开始就建立时，它便赋能了强大的可观测性。可观测性帮助组织了解AI应用在实际中的表现。LLM可观测性和基准测试机制使团队能够随时间评估准确性和效用、监控采用模式，并根据条件变化调整系统。可观测性还通过提高模型性能、行为和故障点的可见性，帮助组织赢得信任。

Furthermore, observability is essential to get ROI of AI initiatives, as the benefits of it are often indirect and business value depends heavily on how systems are adopted and used. 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.此外，可观测性对于获取AI项目的投资回报率至关重要，因为其收益往往是间接的，业务价值高度依赖于系统如何被采用和使用。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，并随着需求演变不断优化系统。

In a 2026 report from Elastic, 85% of IT decision makers expect to enable LLM observability for their internal generative AI apps.在Elastic的一份2026年报告中，85%的IT决策者期望为其内部生成式AI应用启用LLM可观测性。

“Observability is actually huge. We can use observability data for cost control, decision-making, and engineering efficiency,” Adil says.Adil说：“可观测性实际上非常重要。我们可以利用可观测性数据进行成本控制、决策制定和工程效率提升。”

4. Keep humans in the loop4. 让人类参与其中

The thoughtful design, integration, and governance that maximize AI value demand specialized in-house expertise. Nearly 70% of respondents in Deloitte’s 2025 Tech Executive Survey report plan to grow teams in direct response to generative AI, a clear contrast to widely reported AI-related cuts. Adil agrees: “We think the people aspect is largely what's going to make AI impactful going forward.”最大化AI价值的深思熟虑的设计、集成和治理需要专业的内行专业知识。德勤2025年技术高管调查中近70%的受访者计划直接因生成式AI而扩大团队，这与广泛报道的AI相关裁员形成鲜明对比。Adil表示赞同：“我们认为人员因素在很大程度上将决定AI未来的影响力。”

As AI systems become more embedded in operations, organizations need people who can govern workflows, evaluate outputs, redesign processes, and adapt systems as conditions change. Evolution toward increasingly autonomous tools requires teams skilled in prompt engineering, orchestration, and change management. 随着AI系统更深入地嵌入运营，组织需要能够管理工作流、评估输出、重新设计流程并在条件变化时调整系统的人员。向越来越自主的工具演变需要团队具备提示工程、编排和变更管理方面的技能。

Talent adept at critical thinking and prepared to adapt with technology’s rapid advances will be in high demand. Although turnover brings in fresh thinking, it also presents high costs in system continuity, institutional understanding, and innovation. Human-centered strategy needs to be built into AI execution stages to ensure smooth implementation. 擅长批判性思维并准备适应技术快速进步的人才将供不应求。尽管人员流动带来新思维，但也给系统连续性、机构理解和创新带来高昂成本。以人为中心的策略需要融入AI执行阶段，以确保顺利实施。

As Adil says, “Many aspects of the stack are moving very, very fast, but institutional knowledge and the ability to adapt remain durable.正如Adil所说：“技术栈的许多方面变化得非常非常快，但机构知识和适应能力仍然持久。”

Thoughtful AI investment for future growth面向未来增长的审慎AI投资

As AI systems evolve from single-task assistants to increasingly autonomous agents, the organizations best positioned to benefit will be those that invest in the underlying systems, governance, and expertise that make AI reliable at scale.随着AI系统从单任务助手演变为越来越自主的智能体，那些投资于使AI在大规模下可靠的基础系统、治理和专业知识的组织将处于最有利的位置。

Tech leaders who focus on these fundamentals can move effectively from experimentation to reliable, production-level deployment in the medium term, confident that these elements will remain relevant and adaptable amid constant advancements.专注于这些基础要素的技术领导者能够有效地从实验阶段迈向中期可靠的生产级部署，并确信这些要素在持续进步中仍将保持相关性和适应性。

“We fundamentally believe that with these tools, velocity of work will get much faster,” Adil says. “We are really focused on how we can do work with these tools in ways we had not thought of before.”Adil说：“我们坚信，有了这些工具，工作速度将大大加快。我们真正专注于如何以我们以前未曾想到的方式利用这些工具完成工作。”

Learn more about how Elastic is building an AI-first enterprise with these core foundational components.了解更多关于Elastic如何以这些核心基础组件构建AI优先的企业。

This content was produced by Insights, the custom content arm of MIT Technology Review. It was not written by MIT Technology Review’s editorial staff. It was researched, designed, and written by human writers, editors, analysts, and illustrators. This includes the writing of surveys and collection of data for surveys. AI tools that may have been used were limited to secondary production processes that passed thorough human review.本文由MIT Technology Review定制内容部门Insights制作。非MIT Technology Review编辑部撰写。内容由人类作者、编辑、分析师和插画师进行调研、设计和撰写，包括调查设计和数据收集。可能使用的AI工具仅限于经过严格人工审核的辅助生产流程。