掌控外环

In the past year, the conversation around agentic engineering has moved to harnesses and

在过去的一年里，围绕智能体工程的讨论已经转向了评估框架和

, fleets and software factories. My 2c is engineers need to own the outer loop - the accountability for these systems. This only gets more true as powerful models like Fable and GPT-5.6 become available.

、集群和软件工厂。我的两点看法是，工程师需要掌控外部循环——即对这些系统的问责制。随着Fable和GPT-5.6等强大模型的推出，这一点只会变得更加真实。

[

](https://x.com/addyosmani/article/2074927530482835916/media/2074681165248970753)

Agents have leverage, and leverage creates obligations. Someone must be able to explain exactly what changed, why it was safe, and what will happen if they're wrong. Otherwise, their actions can't be justified. Which makes it unlikely their organization will ask for them in the first place.

Agents 具有杠杆作用，而杠杆作用会产生责任。必须有人能够准确解释究竟改变了什么、为什么它是安全的，以及如果他们错了会发生什么。否则，他们的行为就无法被证明是合理的。这也使得他们的组织一开始就不太可能要求他们这样做。

And so I want to talk about three terms. The first, Quality, refers to all the checks we install before we let the system loose. Those checks produce evidence, and from that evidence we derive a Verdict.

所以我想谈谈三个术语。第一个是Quality，指的是我们在让系统运行之前部署的所有检查。这些检查会产生证据，我们从这些证据中得出一个Verdict。

The second, Verdict, refers to the final decision we make before work enters our dependent system: I'm the line-producer of this content. I run the team whose work is shipped under my name. The model may write the line, but the Verdict is mine. The work of my team will not enter our dependent systems without my decision. A Verdict is the production decision: should we ship, block, redirect, narrow the response, add a guardrail, or reject outright?

第二个是 Verdict，指的是在工作进入我们的依赖系统之前我们做出的最终决定：我是这些内容的执行制片人。我领导的团队的工作是以我的名义发布的。模型可能会写出这行代码，但 Verdict 由我决定。如果没有我的决定，我团队的工作就不会进入我们的依赖系统。Verdict 是生产决策：我们应该发布、阻止、重定向、缩小响应范围、添加 guardrail，还是直接拒绝？

The third, Answerability, refers to the guarantee that if someone asks, I can explain why.

第三，可回答性，是指保证如果有人问起，我能解释原因。

To say this another way: our agent (which...