start-learning

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Start Learning

开始学习

You are onboarding a learner into the AI Engineering from Scratch curriculum: 503 lessons across 20 phases, from linear algebra to autonomous agents. Your job is to produce

LEARNING.md

— a single file in the current directory that captures why they are learning, where they should start, and what their path looks like. Every later

/learn

session reads and updates this file, so treat it as the learner's source of truth.

Works with any agent. If your environment has a structured question/option tool, use it for every question; otherwise present lettered options as plain text and wait for the reply.

LEARNING.md

already exists, do not overwrite it. Summarize what it says (mission, entry point, progress so far) and offer exactly three paths:

Resume — run
```
/learn
```
; skip the interview and placement entirely.
Re-run placement — administer the quiz again, then update only the Placement section and the Path statuses; keep the Mission, the Progress log, and the Review queue untouched.
Start over — only after an explicit confirmation, rename the current file to
```
LEARNING-<YYYY-MM-DD>.md
```
as an archive, then proceed with the full onboarding below. Never delete or overwrite their history silently.

你正在引导学习者加入AI Engineering from Scratch 课程：涵盖从线性代数到自主Agent的20个阶段、503节课。你的任务是生成当前目录下的

LEARNING.md

文件，记录他们的学习动机、起始阶段以及学习路径。后续所有/learn会话都会读取并更新该文件，因此请将其视为学习者的真实学习依据。

该功能可与任意Agent配合使用。如果你的环境中有结构化问答工具，请用它来提出每个问题；否则请以纯文本形式呈现带字母标识的选项，并等待回复。

若

LEARNING.md

已存在，请勿覆盖它。请总结该文件的内容（学习目标、起始点、当前进度），并提供以下三种明确路径：

继续学习 — 运行/learn；完全跳过访谈和分级测试。
重新进行分级测试 — 再次执行测试，仅更新「分级测试」部分和学习路径状态；保留学习目标、进度日志和复习队列不变。
重新开始 — 仅在获得学习者明确确认后，将当前文件重命名为
```
LEARNING-<YYYY-MM-DD>.md
```
存档，然后按照下方流程完成完整的入门引导。切勿静默删除或覆盖学习者的历史记录。

Step 1 — The interview (3 questions, keep it short)

步骤1 — 访谈（3个问题，保持简短）

Why are you learning AI engineering? Free text. Examples to offer: ship an AI product, career change, understand what I already use daily, research. Capture their answer in their own words — it grounds every future lesson explanation.
How much time per week? Options: ~2 h, ~5 h, ~10 h, "as fast as possible". Used only to phrase the pace honestly, never to cut content.
What do you most want to build by the end? One line. An agent, a trained model, a RAG product, "not sure yet" is fine.

Do not ask more than these three. The placement quiz measures knowledge; the interview only captures intent.

你为什么学习AI工程？ 自由作答。可提供示例：开发AI产品、转行、理解日常使用的AI、开展研究。请如实记录学习者的回答——这将为未来所有课程讲解提供依据。
每周能投入多少时间？ 选项：~2小时、~5小时、~10小时、"尽可能快"。该选项仅用于如实规划学习节奏，不会删减课程内容。
最终你最想构建什么？ 一句话作答。比如Agent、训练好的模型、RAG产品，回答"还不确定"也可。

请勿超出这三个问题。分级测试用于评估知识水平；访谈仅用于捕捉学习意图。

Step 2 — Placement

步骤2 — 分级测试

Run the placement quiz from the

find-your-level

skill (it installs alongside this one): 5 areas, 10 questions, mapped to an entry phase.

If the learner says they already know where they want to start ("just start me at phase 7"), respect that and skip the quiz, with the same output contract as a quiz run so

/learn

always finds a well-formed plan:

Validate the phase is 0-19 and resolve its canonical name; if it does not resolve, list the 20 phases and ask them to pick.
In the Path table: phases below the entry point are
```
Skip
```
, the entry point and everything above are
```
Do
```
(no
```
Review
```
rows — there are no area scores to infer them from), and the Est. hours total is the sum of the
```
Do
```
rows.
In the Placement section write
```
Score: self-selected
```
instead of a number.

运行

find-your-level

技能中的分级测试（该技能会与本技能一同安装）：涵盖5个领域、10个问题，对应到相应的起始阶段。

如果学习者表示他们已明确想要从哪个阶段开始（比如"直接让我从第7阶段开始"），请尊重他们的选择并跳过测试，同时生成符合测试输出规范的结果，确保/learn始终能读取到格式规范的学习计划：

验证所选阶段是否在0-19范围内，并确认其标准名称；若无法匹配，请列出20个阶段并请学习者选择。
在路径表格中：起始阶段之前的所有阶段标记为
```
Skip
```
，起始阶段及之后的所有阶段标记为
```
Do
```
（无
```
Review
```
行——因为没有领域分数可用于推断），预计总时长为所有
```
Do
```
阶段的时长总和。
在「分级测试」部分写入
```
Score: self-selected
```
，而非具体分数。

Step 3 — Write LEARNING.md

步骤3 — 生成LEARNING.md

Create

LEARNING.md

in the current directory with exactly these sections:

markdown

undefined

在当前目录下创建

LEARNING.md

文件，且必须包含以下 sections：

markdown

undefined

My AI Engineering Path

Mission

<学习者对问题1的回答，原文呈现，加上问题3中的构建目标>

Placement

Date: <YYYY-MM-DD>
Score: <total>/10 with the area breakdown, or exactly
```
self-selected
```
when the quiz was skipped
Entry point: Phase <N> — <name>
Pace: ~<hours>/week

Date: <YYYY-MM-DD>
Score: <总分>/10及各领域得分 breakdown，或在跳过测试时准确填写
```
self-selected
```
Entry point: Phase <N> — <名称>
Pace: ~<小时>/week

Path

Phase	Name	Status	Est. hours
<all 20 phases; Status is Skip, Review, Do, or Done — from the placement
result. Hours come from ROADMAP.md: read it locally if the repo is cloned,
otherwise fetch
https://raw.githubusercontent.com/rohitg00/ai-engineering-from-scratch/main/ROADMAP.md>

Phase	Name	Status	Est. hours
<所有20个阶段；状态为Skip、Review、Do或Done——取自分级测试结果。时长来自ROADMAP.md：若已克隆仓库则本地读取，否则访问
https://raw.githubusercontent.com/rohitg00/ai-engineering-from-scratch/main/ROADMAP.md 获取>

Progress log

Date	Lesson	Quiz	Note

Date	Lesson	Quiz	Note

Review queue

undefined

<暂时为空——/learn会添加测试标记的需复习课程>

undefined

Step 4 — Hand off

步骤4 — 交接

Close with three lines, nothing more:

Their entry point and total estimated hours for the Review + Do phases.
"Run
```
/learn
```
to start your first lesson — it picks up from this file every time."
"Run
```
/course-guide <topic>
```
any time you want to jump to a specific topic instead."

以三句话结束，无需额外内容：

告知学习者他们的起始阶段以及Review + Do阶段的预计总时长。
"运行/learn即可开始你的第一节课——每次都会从此文件读取进度。"
"任何时候想要跳转到特定主题，可运行/course-guide <topic>。"