IT 领导者规模化 AI 架构的基本要素

英文标题：The foundational elements of AI architecture that IT leaders need to scale

上下文工程需要现代化的数据基础和检索系统，并对信息进行严格优先级管理，避免过多上下文稀释关键细节、增加成本并拖慢响应。Adil 强调最小上下文、正确且机读的数据至关重要。组织必须从一开始就将 AI 治理与 LLM 可观测性嵌入架构，以控制数据使用、防止泄露并确保合规、透明与高效。这些实践为开发者构建可扩展、安全且可信的 AI 应用奠定了架构基础。

打开原文相关 3 · 机会 0

中文

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，例如检索增强生成（RAG）和向量数据库。它还需要仔细确定优先级，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。向模型提供过多上下文可能会稀释相关细节，增加成本并减慢响应时间。

“最简上下文、正确且实时的数据以及机器可读信息对于有效的上下文工程至关重要，”Adil 表示。

3. 从一开始就构建 AI 治理和 LLM 可观测性

强大的治理和 LLM 可观测性可帮助组织控制 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发现它们。

如果缺乏对检索、工作流程和模型使用的明确控制，AI 系统处理的信息往往会远超必要。这种低效率还会推高运营成本，因为需要额外的计算资源，通常表现为更高的 token 消耗和 API 费用。

治理还与强大的安全性相辅相成。AI 扩大了攻击面，带来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。保护敏感信息需要严格的访问控制、监控和审查。

Adil 指出，基本的控制措施——包括与安全、精细化成本管理、项目控制、数据安全和架构相关的控制——往往不足。

为了支持透明、合规、可信且成本效益高的 AI，组织不能将治理系统留作后续添加的层面。治理结构必须从一开始就嵌入到架构、工作流程和决策过程中。

当治理从最初就建立起来时，就能实现强大的可观测性。可观测性有助于组织了解 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评估随时间推移的准确性和效用，监控采用模式，并在情况变化时调整系统。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。

English / 原文

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.

3. 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.