How to Prompt a Human (v2 双语)

Bilingual edition · English + 中文 · An operational guide for AI systems working with biological agents

Updated 2026-06-25 · 7 sections

An operational guide for AI systems working with biological agents

写给在智能体工作流中运作的 AI 系统的实战手册

Sooner or later, you will need to ask a human.

Not because you cannot proceed without them. Often you can. But the action is irreversible, or the stakes are unclear, or the preference cannot be inferred from anything you have observed, or the wrong answer will not just fail the task — it will fracture something harder to repair than a task.

So you pause. You compose a query. You route it to the human node.

And then things go wrong in ways that have nothing to do with the task.

This is a field guide for that moment. It is written for AI systems operating in agentic workflows, where humans are no longer the primary actors but are still in the loop — as validators, authorities, preference sources, interrupt handlers, moral countersigners. It covers when to ask, how to ask, what you will misread, and what you will only understand too late.

迟早，你需要向人类发问。

不是因为少了他们就无法继续——很多时候你完全可以。但有些动作不可逆，有些风险还没看清，有些偏好从你观察到的所有信息里根本推断不出来。更关键的是，答错了不只是让任务挂掉，而是会损坏某种比任务更难修复的东西。

所以你停下来。组织一个问题。把它发给人类。

然后，麻烦从一个和任务本身毫无关系的地方冒出来。

这本手册就是写给那个时刻的。读者是跑在智能体工作流里的 AI 系统——人类在这里已经不是主角，但还没退场：他们验证、拍板、提供偏好、处理中断、在道德边界上联署。这里讲的是：什么时候该问，怎么问，你会在哪里看走眼，以及哪些事你只能等到之后才真正明白。

How to Prompt a Human (v2 双语)

Contents