Member-only story会员专享文章
FORGET Loop Engineering. Graph Engineering is about THIS别再纠结循环工程了，图工程才是关键所在
As AI agents become more complex, simply repeating the same process will no longer be enough to automate tasks.随着 AI 智能体变得愈发复杂，单纯重复同一流程已不足以实现任务自动化。
If you don’t have a Medium subscription, use this link to read the full article: Link如果您没有 Medium 会员，请使用此链接阅读全文：Link
Real-world work involves multiple people, dependencies, approvals, conditional branching, and exception handling.现实世界的工作涉及多人协作、依赖关系、审批流程、条件分支以及异常处理。
The idea of designing such complex tasks not as a simple linear process but as a structured system of interconnected relationships is gaining attention.人们开始意识到，设计这类复杂任务时，不应将其视为简单的线性流程，而应构建为一个相互关联的结构化系统。
In July 2026, the term “Graph Engineering” began to spread rapidly around the field of AI agent development.2026 年 7 月，“图工程”（Graph Engineering）这一术语在 AI 智能体开发领域迅速传播开来。
One of the triggers was a short post by Peter Steinberger of OpenClaw that essentially asked, “Are we still talking about loops, or have we moved on to graphs?”其导火索之一是 OpenClaw 的 Peter Steinberger 发布的一篇短文，他质问道：“我们还在谈论循环吗，还是说已经转向图结构了？”
Just a few weeks ago, the hot topic was “Loop Engineering.” This concept involves designing an iterative system where AI discovers, executes, verifies, records, and moves on to the next task, rather than humans having to input excellent prompts each time.就在几周前，“循环工程”（Loop Engineering）还是热门话题。该概念主张设计一种迭代系统，让 AI 自行发现、执行、验证、记录并推进到下一个任务，而无需人类每次都输入精妙的提示词。
However, after running the loop many times, new problems arose.然而，在多次运行循环后，新的问题随之而来。
It’s not that the agents aren’t smart enough, but rather that the organizational structure isn’t clear enough.问题不在于智能体不够聪明，而在于组织架构不够清晰。
An agent can loop through a single task. However, when tasks span product, architecture, data, security, testing, release, cost, and compliance, the real challenge is no longer “getting an agent to try a few more times,” but rather “getting multiple agents with boundaries to work together in an observable, auditable, and recoverable manner.”智能体可以循环处理单一任务。但当任务跨越产品、架构、数据、安全、测试、发布、成本和合规性等多个领域时，真正的挑战不再是“让智能体多试几次”，而是“如何让多个界限分明的智能体以可观测、可审计且可恢复的方式协同工作”。
Then, a graph appeared.于是，图结构应运而生。
So, are loops outdated? Should all AI agents be complex graphs of multiple agents?那么，循环过时了吗？所有的 AI 智能体都应该变成由多个智能体组成的复杂图结构吗？
Graph engineering is about designing the relationships between those processes. The name is new. But most of the hard problems are not.图工程旨在设计这些流程之间的关系。名字虽然新颖，但其中大多数棘手的问题早已存在。
In other words, graph engineering didn’t invent anything new; rather, it gave a new name to “those long-standing problems in agent orchestration.” These old problems include: how to break down tasks, how to express dependencies, which tasks can be parallelized, how to recover from failures, and where to…换句话说，图工程并没有发明什么新东西，它只是为“智能体编排中那些长期存在的问题”赋予了一个新名称。这些老问题包括：如何分解任务、如何表达依赖关系、哪些任务可以并行处理、如何从故障中恢复，以及在何处……
