> For the complete documentation index, see [llms.txt](https://zhouhao4221.gitbook.io/haiqing-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://zhouhao4221.gitbook.io/haiqing-docs/01-thinking.md).

# 01 · 思维

AI 驱动工程的思维模型与框架。行动之前如何思考。

***

## 目的

好的 AI 输出源于好的思考。工具用对了但思维没跟上，输出质量依然不稳定。本章节解释 AI 工程的核心思维框架，帮助你：

* 在提示前正确分解问题
* 批判性地评估 AI 输出而不是盲目接受
* 判断什么时候该用 AI、什么时候必须人工判断
* 理解上下文如何约束 AI 的行为边界

***

## 本章节文档

| 文档                                                                                     | 内容                                       |
| -------------------------------------------------------------------------------------- | ---------------------------------------- |
| [ai-thinking-framework.md](/haiqing-docs/01-thinking/ai-thinking-framework.md)         | 提示前的四个问题、决策边界、输出评估清单、常见失败模式              |
| [context-as-constraint.md](/haiqing-docs/01-thinking/context-as-constraint.md)         | 上下文为什么是约束而非信息、三类失效模式、实践含义                |
| [skill-oriented-knowledge.md](/haiqing-docs/01-thinking/skill-oriented-knowledge.md)   | Skill 作为可执行知识单元的概念、结构、组合方式与系统架构          |
| [agent-as-exoskeleton.md](/haiqing-docs/01-thinking/agent-as-exoskeleton.md)           | 为什么不需要先给 Agent 定义角色、Agent 的核心结构与 Loop 闭环 |
| [passionate-coding-warning.md](/haiqing-docs/01-thinking/passionate-coding-warning.md) | 激情开发陷阱：为什么 AI 会放大这种失败模式、如何识别和熔断          |
| [mvp-is-a-draft.md](/haiqing-docs/01-thinking/mvp-is-a-draft.md)                       | MVP 是草稿而非资产：试错成本结构变化如何改变 MVP 决策逻辑        |
| [ai-as-bookworm.md](/haiqing-docs/01-thinking/ai-as-bookworm.md)                       | AI 是书呆子不是打工人：知识广但无阅历，判断责任永远在人这里          |
| [judgment-gap.md](/haiqing-docs/01-thinking/judgment-gap.md)                           | 判断力缺口：看不懂 AI 答案时怎么决策，三步框架让错误可控可纠正        |
| [knowledge-into-experience.md](/haiqing-docs/01-thinking/knowledge-into-experience.md) | 知识变经验：项目中的四个积累动作，让判断力可以被传递               |
| [knowledge-outlasts-people.md](/haiqing-docs/01-thinking/knowledge-outlasts-people.md) | 知识不随人走：AI 工程对人员流动的真正解法，从人依赖到系统依赖         |
| [team-as-product.md](/haiqing-docs/01-thinking/team-as-product.md)                     | 团队是你的第一个产品：用产品思维看团队，从判断人到设计系统            |


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://zhouhao4221.gitbook.io/haiqing-docs/01-thinking.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.