你的优势是你的问题。二十五年真正会复利的不是信息量，是问出更好问题的能力。最后一个 workshop 是全课程唯一不用 agent 做的。

Your edge is your questions. What compounds over twenty-five years is not information — it is the capacity to ask better questions. The final workshop is the only one you do without an agent.

大部分人只拿 agent 当执行者用。投资场景里 agent 有四个角色——分析师、红队、导师、执行者——你提问的方式决定你激活哪一个。

Most people use their AI agent in one mode. Investment agents play four distinct roles — analyst, red team, tutor, executor — and the way you frame your request determines which role you get.

股票是对未来现金流的权利——不是代码，不是图表。三种回报来源，五种优势类型，以及你在判断 agent 输出之前必须有的词汇。

A stock is a claim on future cash flows — not a ticker, not a chart. Three sources of return, five types of edge, and the vocabulary you need before you can judge an agent's output.

年报不用每一行都读。你要认的是模式。三张报表当三个镜头——业务结构、脆弱度、真假。

You do not need to read every line of a 10-K. You need to recognize patterns. Three financial statements as three lenses — business structure, fragility, and truth.

DCF 里每个数字都是一个故事选择。Agent 算得又快又准，但它默认讲共识。你的工作是带自己的故事进去——以及找到估值暗中依赖的那个假设。

Every number in a DCF is a story choice. Agents compute flawlessly and default to consensus. Your job is the narrative — and knowing which assumption your valuation secretly depends on.

风险是你承受不起的亏损的概率，不是标准差。LTCM 1998 年优化了错误的指标，被相关性崩溃杀死了。四种真正的风险，以及为什么只有你能决定自己亏得起多少。

Risk is the probability of a loss you cannot afford — not standard deviation. LTCM optimized for volatility and was killed by correlation breakdown. Four real risks, and why only you can decide what you can afford to lose.

大部分投资者有的是信念，不是论点。把判断写下来、附上止损条件，是对自己记忆的问责——因为记忆会自我美化，信念会悄悄变形。

Most investors have beliefs, not theses. A written thesis with kill criteria is accountability against your own memory — because memory is self-serving, and beliefs mutate silently.

单个 agent 是工具。有明确角色、交叉验证和显式交接的一组 agent，才能产生质变。五个模式覆盖 90% 的投资研究流程。

A single agent is a tool. A fleet with defined roles, cross-verification, and explicit handoffs is transformative. Five patterns cover 90% of investment workflows — but over-engineering the fleet is itself a form of procrastination.

前八章的全部内容压缩成一个端到端流程。三家公司，一个决定。这一章本身就是 workshop——预计 4 到 8 小时，分多次完成。

Everything from chapters 1 through 8 collapses into one end-to-end workflow. Three companies, one decision. This chapter IS the workshop — expected time: 4 to 8 hours across multiple sittings.

投资分析以前需要 Bloomberg 终端或者会写代码。AI agent 把两个前提都拆了。剩下的门槛是判断力——这改变了投资课程应该教什么。

Investment analysis used to require either a Bloomberg terminal or the ability to write code. AI agents removed both prerequisites. The barrier is now judgment — and that changes what an investing curriculum should teach.