从提示工程升级为上下文工程，系统化构建AI代理的决策环境。
Context Engineering: From Prompts to Corporate Multi-Agent Architecture
- 提出上下文工程五要素：相关性、充分性、隔离性、经济性、可追溯性
- 75%企业计划两年内部署智能代理，但落地受复杂性制约
- 适合企业级AI架构师和自动化系统设计者参考
随着人工智能系统从无状态聊天机器人演变为自主多步骤代理，仅靠提示工程已无法满足需求。本文提出上下文工程（CE）作为独立学科，专注于设计、组织和管理AI代理决策的全部信息环境。基于谷歌ADK、Anthropic、LangChain等厂商架构，以及学术研究（如ACE框架、DeepMind智能委派）、企业调研（德勤2026、毕马威2026）和作者构建多代理系统的经验，论文定义了五项上下文质量标准：相关性、充分性、隔离性、经济性与可追溯性，并将上下文视为代理的操作系统。在此基础上衍生出两个更高阶学科：意图工程（IE）将组织目标、价值观与权衡优先级嵌入代理架构；规范工程（SE）构建可机器读取的企业政策与标准语料库，支持多代理系统规模化自主运行。四大学科构成递进式成熟度模型，每层均以先前层级为基础。企业数据揭示断层：75%企业计划两年内部署代理（德勤2026），但因扩展复杂性导致部署潮起潮落（毕马威2026）。克劳纳案例显示双重缺失：谁掌控上下文，谁就控制行为；谁掌控意图，谁就控制策略；谁掌控规范，谁就控制规模。
原文摘要 · Abstract (English)
As artificial intelligence (AI) systems evolve from stateless chatbots to autonomous multi-step agents, prompt engineering (PE), the discipline of crafting individual queries, proves necessary but insufficient. This paper introduces context engineering (CE) as a standalone discipline concerned with designing, structuring, and managing the entire informational environment in which an AI agent makes decisions. Drawing on vendor architectures (Google ADK, Anthropic, LangChain), current academic work (ACE framework, Google DeepMind's intelligent delegation), enterprise research (Deloitte, 2026; KPMG, 2026), and the author's experience building a multi-agent system, the paper proposes five context quality criteria: relevance, sufficiency, isolation, economy, and provenance, and frames context as the agent's operating system. Two higher-order disciplines follow. Intent engineering (IE) encodes organizational goals, values, and trade-off hierarchies into agent infrastructure. Specification engineering (SE) creates a machine-readable corpus of corporate policies and standards enabling autonomous operation of multi-agent systems at scale. Together these four disciplines form a cumulative pyramid maturity model of agent engineering, in which each level subsumes the previous one as a necessary foundation. Enterprise data reveals a gap: while 75% of enterprises plan agentic AI deployment within two years (Deloitte, 2026), deployment has surged and retreated as organizations confront scaling complexity (KPMG, 2026). The Klarna case illustrates a dual deficit, contextual and intentional. Whoever controls the agent's context controls its behavior; whoever controls its intent controls its strategy; whoever controls its specifications controls its scale.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。