IT领导者需要扩展AI架构的基础要素
内容总结：
AI架构四大基石：企业规模化部署智能系统的关键
随着人工智能能力快速演进并向智能体系统发展，企业应用场景不断扩展，但技术迭代也带来风险。对于IT领导者而言，如何确保当前投资在未来六个月内仍具价值，成为核心挑战。回归AI架构的基础要素——即部署和管理可靠、集成化大规模AI系统所需的结构框架，是做出明智决策的关键。以下四大要素无论底层技术如何演变，均具有持久价值。
1. 规模化数据准备
模型可靠性完全取决于其可访问的数据质量。数据质量低下会导致AI产生幻觉、偏见和不可靠输出。多数企业受限于遗留系统、数据结构不一致、所有权分散和不完整数据集，难以有效扩展AI。行业调查反复指出，数据质量是AI成功的最大障碍之一。有效的AI战略始于连接组织内数据，确保其有序、准确、受管控且可实时访问。Gartner预测，到2026年，若无AI就绪数据支持，60%的AI项目将被放弃。建立清晰的数据标准和所有权、保持数据清洁与标注、构建支持实时检索的数据管道，是避免失败的关键。
2. 情境工程：为每次AI查询提供精准数据
情境工程确保模型为每个查询调用最相关的信息，高效产出准确答案。与提示工程关注请求措辞不同，情境工程设计模型周围的整体信息环境——检索正确数据并以机器可读的结构化方式呈现。其依赖现代化、统一的数据基础，以及RAG和向量数据库等检索与记忆系统。关键原则是"最小上下文、正确且当前数据、机器可读信息"，过多上下文会稀释关键细节、增加成本并降低响应速度。
3. 从起步阶段构建AI治理与LLM可观测性
强有力的治理和LLM可观测性帮助组织维持对AI系统数据使用方式的控制，监控性能，并在问题影响运营前发现隐患。缺乏清晰控制会导致AI系统处理过多不必要信息，推高运营成本。治理需与网络安全协同，应对提示词数据泄露、模型漏洞等新增风险。治理结构必须从一开始就嵌入架构、工作流程和决策过程，而非事后添加。可观测性对评估准确性、监控采用模式、优化系统至关重要。Elastic报告显示，85%的IT决策者预计将为其内部生成式AI应用启用LLM可观测性。
4. 让人类保持参与
最大化AI价值的精心设计、集成和治理需要专业内部人才。德勤2025年技术高管调查中，近70%受访者计划因生成式AI而扩大团队。随着AI系统更深嵌入运营，组织需要能够治理工作流、评估输出、重新设计流程并适应变化的人员。具备批判性思维并能适应技术快速进步的人才将持续供不应求。以人为中心的战略必须嵌入AI执行的各个阶段，确保平稳落地。
未来增长的投资方向
随着AI从单任务助手演变为自主智能体，那些投资于基础系统、治理和专业知识的组织将获得最大收益。聚焦这些基本要素的技术领导者，能以更稳健方式从实验阶段走向可靠的生产级部署。正如Elastic首席信息官所言："有了这些工具，工作速度将大幅提升，我们正以前所未有的方式思考如何运用它们。"
中文翻译：
赞助内容
IT领导者扩展AI规模需把握的四大架构基础
在模型持续迭代的当下，数据质量、情境工程、治理机制与人类专业知识这四大AI架构基础要素依然稳固。
与Elastic联合呈现
随着AI能力飞速发展及代理式系统转型的推进，组织正随着技术演进不断拓展应用场景。这种持续演进也带来风险，让IT领导者难以判断哪些投资在六个月后仍能产生价值。
回归AI架构的基础要素——即规模化部署和管理可靠、集成化AI系统所需的结构框架——能使技术领导者当下做出明智决策，同时为未来能跨系统检索信息、做出决策并执行复杂工作流程的AI代理奠定基础。
值得信赖的四大AI架构要素
无论底层技术如何演变，以下能力将为生产级部署提供稳定指引。
- 为规模化AI准备数据
模型的可靠性取决于其能访问的数据质量，低质数据会导致AI产生幻觉、偏差及不可靠输出。
多数企业依赖传统系统，面临数据结构不一致、所有权分散、数据集不完整等问题，阻碍AI有效扩展。尽管AI功能强大，但无法自行解决这些底层数据问题。
正如Elastic首席信息官Adnan Adil所解释："数据是AI架构中持久的组成部分，因为离开它，模型无法运行，无法提供正确上下文，也无法达到我们期望的服务水平。"行业调查反复将数据质量列为AI成功最大障碍之一。Adil表示："数据质量必须过硬，否则用户会失去对系统的信任。"
有效的AI策略始于连接组织内所有数据，确保数据实时组织有序、准确、受管控且可访问。将这些考量从起始阶段融入模型与架构最为有效。可扩展的数据架构使AI系统能随业务共同演进，并可靠连接内部所需信息以创造切实价值。
Gartner预测，到2026年，若缺乏AI就绪数据支撑，企业将放弃60%的AI项目。避免这一结果需明确数据标准与所有权、使用清洁标注数据、构建支持实时检索的数据管道。
- 运用情境工程为每次AI查询提供精准数据
情境工程确保模型为每次查询提取最相关的信息，通过筛选组织数据高效生成精确答案。
有效的情境工程能塑造引导AI推理与行动的信息输入。提示工程侧重请求的措辞方式，而情境工程则围绕模型设计整个信息环境：检索正确数据并以结构化、机器可读形式呈现。许多组织发现，可靠的AI既依赖模型强度，也取决于情境质量。
情境工程依赖现代化统一数据基础，以及检索增强生成（RAG）和向量数据库等检索与记忆系统。同时需要精心权衡，确定哪些信息最重要、哪些应排除、何时使用不同类型信息。向模型输入过多情境会稀释关键细节，增加成本并降低响应速度。
Adil指出："最小情境量、准确且实时的数据、机器可读信息，是有效情境工程的关键。"
- 从起步阶段构建AI治理与LLM可观测性
强有力的治理与LLM可观测性帮助组织掌控AI系统如何使用数据、监控系统性能，并在问题影响运营前及时发现。
若缺乏围绕检索、工作流程和模型使用的明确管控，AI系统常处理远超必要的信息量。这种低效会因额外计算资源消耗推高运营成本，通常体现为更高的令牌消耗与API费用。
治理还需与强健的安全体系协同。AI扩大了攻击面，引入基于提示的数据泄露、模型漏洞和对抗性输入等风险。保护敏感信息需要严格访问控制、监控与监督。
Adil指出，关键管控措施——包括安全、精细成本管理、项目管控、数据安全与架构方面——往往不够充分。
要使治理系统支撑透明、合规、可信且经济的AI，组织不能将其作为后期附加层。治理结构需从初始阶段嵌入架构、工作流程与决策过程。
从起步阶段建立治理，可实现强大的可观测性。可观测性有助于组织了解AI应用的实际表现。LLM可观测性与基准测试机制使团队能持续评估准确性与效用，监控采用模式，并根据条件变化调整系统。可观测性还能通过提升模型性能、行为及故障点的可见性来增强组织信任。
此外，可观测性对实现AI投资回报率至关重要，因为AI效益通常间接体现，商业价值高度依赖系统的采用与使用方式。对AI行为的实时可见性使组织能衡量性能是否符合预期，识别意图与现实之间的差距，并随需求演变持续优化系统。
Elastic 2026年报告显示，85%的IT决策者预计将为其内部生成式AI应用启用LLM可观测性。
Adil表示："可观测性极其重要。我们可以利用可观测性数据进行成本控制、决策制定和提升工程效率。"
- 保持人类参与
最大化AI价值所需的设计、集成与治理需专业内部 expertise。德勤2025年技术高管调查中近70%受访者计划因生成式AI扩招团队，这与广泛报道的AI相关裁员形成鲜明对比。Adil认同："我们认为人员因素将在未来很大程度上决定AI的影响力。"
随着AI系统深度融入运营，组织需要能管控工作流程、评估输出、重新设计流程并随环境变化调整系统的人才。向更具自主性工具演进，需要团队掌握提示工程、编排和变革管理技能。
擅长批判性思维、能适应技术快速变革的人才将备受追捧。虽然人员流动能带来新思维，但也会在系统连续性、机构理解和创新方面造成高额成本。以人为中心的策略需嵌入AI执行各阶段，确保平稳实施。
如Adil所言："技术栈的许多层面变化极快，但机构知识与适应能力始终是持久资产。"
面向未来增长的审慎AI投资
随着AI系统从单任务助手向日益自主的代理演进，最受益的组织将是那些投资于底层系统、治理和专业知识，使AI实现可靠规模化部署的企业。
聚焦这些基础要素的技术领导者，能在中期从实验阶段平稳过渡到可靠的生产级部署，确信这些要素在持续演进中仍具相关性与适应性。
Adil表示："我们坚信，借助这些工具，工作速度将大幅提升。我们正专注于如何以前所未有的方式运用这些工具开展工作。"
了解更多关于Elastic如何以这些核心基础组件构建AI优先型企业的信息。
本内容由MIT Technology Review定制内容部门Insights制作，非编辑部撰写。由人类作者、编辑、分析师和插画师完成调研、设计和撰写，包括调查问卷设计与数据采集。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。
深度探索
人工智能
一家初创公司声称突破制约LLM的瓶颈
Subquadratic已公布其新模型更多细节，但仍有质疑之声。
AI就业恐慌的现实审视
关于人工智能对劳动力市场影响的真实数据说明了什么？答案或许出乎意料。
Anthropic的Claude Code展示编程的未来——无论你是否喜欢
随着Claude Code等工具日益强大，越来越多开发者乐于将编码任务交给它们。软件开发方式已彻底改变。
AI聊天机器人泄露真实电话号码
用户反映其个人信息被谷歌AI曝光，且似乎无法简单阻止。
保持联系
获取MIT Technology Review最新资讯
发现特惠、重要报道、即将举办的活动等更多内容。
英文来源：
Sponsored
The foundational elements of AI architecture that IT leaders need to scale
Discover four foundational elements of AI architecture that will endure as models continue to advance: data quality, context engineering, governance, and human expertise.
In partnership withElastic
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.
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.
Four elements of AI architecture you can count on
The following capabilities provide a stable compass on the path to production-ready deployment, regardless of how the underlying technology evolves.
- Prepare data for AI at scale
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.
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.
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.
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. - Use context engineering to deliver the right data to every AI query
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. 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. 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.
“Minimum context, correct and current data, and machine-readable information are critical to effective context engineering,” Adil says. - Build AI governance and LLM observability in from the start
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.
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.
Adil notes that essential controls — including those related to security, granular cost management, project controls, data security, and architecture—are frequently insufficient.
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. 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.
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.
In a 2026 report from Elastic, 85% of IT decision makers expect to enable LLM observability for their internal generative AI apps.
“Observability is actually huge. We can use observability data for cost control, decision-making, and engineering efficiency,” Adil says. - Keep humans in the loop
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.”
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.
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.
As Adil says, “Many aspects of the stack are moving very, very fast, but institutional knowledge and the ability to adapt remain durable.
Thoughtful AI investment for future growth
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.
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.
“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.”
Learn more about how Elastic is building an AI-first enterprise with these core foundational components.
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.
Deep Dive
Artificial intelligence
A startup claims it broke through a bottleneck that’s holding back LLMs
Subquadratic has now shared more details about its new model. But some are still skeptical.
A reality check on the AI jobs hysteria
What do the numbers really say about the impact of artificial intelligence on the labor market? The answer might surprise you.
Anthropic’s Code with Claude showed off coding’s future—whether you like it or not
As tools like Claude Code get better, more and more developers are happy to hand off coding tasks to them. The way software gets built has changed for good.
AI chatbots are giving out people’s real phone numbers
People report that their personal contact info was surfaced by Google AI—and there’s apparently no easy way to prevent it.
Stay connected
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.