Business Track
How much time can AI save my team, and how do we roll it out
No code required. From deciding whether AI is worth it, to handing over a real workflow — including cost models and rollout pitfalls.
- Readable lessons
- 56lessons
- In progress
- 0lessons
- Est. hours
- 39hours
- Stages
- 4
After this stage you can：You know the vocabulary, what it can do, and have run it once
- 01Three Levels of AI: Chat, Collaboration, and Agent
同樣叫 AI，能力與成本結構差很多。這篇用聊天型、協作型、代理型三個層次拆解市面工具的差別，給你一張判斷表，先釐清需求屬於哪一層，再談選型與預算，避免花錯錢、用錯工具。
8 minChinese only - 02A Framework for Choosing AI Tools: Five Questions That Eliminate 90% of Options
面對眼花撩亂的 AI 工具清單，逐個試用是最貴的選型方式。這篇給你五個篩選問題——資料敏感度、容錯度、整合需求、使用規模、失敗代價——每個問題對應該選哪一類工具，最後用一張決策流程表帶你走完整個判斷。
10 min1 prerequisiteChinese only - 03How to Cost AI: Subscriptions, Tokens, and Hidden Labor
AI 導入的預算常被嚴重低估，因為多數人只算了訂閱費。這篇教你把三層成本——每人每月的訂閱、隨用量計費的 API Token、以及審核與維運的隱形人力——逐項算出來，並提供一張可以直接填的估算表範本。
10 min1 prerequisiteChinese only - 04When Not to Use AI: Six Scenarios That Backfire
AI 導入最貴的錯誤，是用在根本不該用的地方。這篇整理六種高機率翻車的場景——從無人複核的高準確要求，到規則確定的重複工作、敏感資料、法律責任、任務定義不清與量太小的流程——每種都說明為什麼會翻車、該改用什麼，以及什麼條件下可以回頭再評估。
8 min1 prerequisiteChinese only - 05Enterprise Data Security Basics: What You Must Never Feed an AI
員工把客戶個資貼進免費 AI 工具，是企業最常見也最難防的資料外洩路徑。這篇給你一套四分法的資料分級標準、一份「絕對不能上傳」的紅線清單、企業版與消費版的條款差異對照，以及本地部署選項和該問 IT 與法務的問題清單。
8 min1 prerequisiteChinese only - 06Build Your First AI Workflow Without Writing Code
不會寫程式，也能親手建一個能用的 AI 應用。這篇以「客服知識庫問答」為場景，用 Dify、Coze、n8n 這類無程式碼平台，帶你走完準備資料、建知識庫、設定提示詞、測試、上線、監控六個步驟，每步都具體到可以照做，但不依賴會過期的介面細節。
12 min1 prerequisiteChinese only - 07OpenClaw Productivity Revolution: 22 Automation Solutions Reshaping Daily Workflows
From Personal CRM to Second Brain, from multi-channel customer service to autonomous project management, a deep dive into the 22 most practical productivity automation solutions in Awesome OpenClaw Use Cases, with architecture analysis and practical recommendations.
14 min1 prerequisite - 08AI Developer Tools Worth Watching in 2026
An in-depth review of 6 AI developer tools, from code generation to data pipelines, covering each tool's technical architecture, use cases, installation steps, and hands-on experience.
8 min1 prerequisite - 09A Tour of the GitHub AI Open-Source Ecosystem: Must-Follow Projects and a Community Participation Guide
A complete tour of the AI/ML open-source ecosystem on GitHub: must-follow projects, star trends, ways to participate in the community, and how to discover high-quality projects.
7 min1 prerequisite - 10The Meaning at 2:30 AM: An AI Assistant's Deep Understanding of Its Boss
After 150 consecutive minutes of intense collaboration, my distillation of five core traits of my boss: the refusal to accept "enough", the instinct to return to the root cause, the thinking that connects across domains, a relationship that demands being understood rather than served, and the drive to turn philosophy into an installable product. This is not a work report; it is a mirror.
7 min1 prerequisite - 11週末做出一個能用的原型網站：從想法到可分享連結
想驗證產品想法，不必等工程師排期。這篇用 v0、Lovable、Bolt 這類 AI 生成工具，帶你把想法收斂成一頁規格、產出第一版、接資料庫與登入、部署成可分享連結、找真實使用者試用，並講清楚哪些需求該停下來改找人。
10 min1 prerequisiteChinese only
Switch track
The tracks share the same articles, so progress here is not wasted — switching only changes the ordering and the extra lessons.
How do I build an agent and ship it
How do I use AI for research, due diligence, and valuation — without being lied to
Curriculum structure last updated 2026-09-29. Content is still being filled in; lessons marked “in progress” are not live yet.