Maggie Appleton 写设计、人类学和智能体界面时,习惯先画清楚隐喻,再谈工具。把「A Short History of Bi-Directional Links」整理成可阅读的中文笔记:问题在哪、界面默认会把人带去哪、落地时该改什么。原站导航、评论回响和广告已去掉。

Bi-directional links are not new

With the recent rise of Roam Research , the idea of bi-directional linking is having a bit of a moment.

We’re all very used to the mono-directional link the World Wide Web is built around. They act as one-way pointers we follow in a linear sequence.

Bi-direction Linking in Personal Digital Gardens

While we can link to any site, the destination page hasn’t a clue we’ve done so.

We set up all these single-direction paths, trying to signal relevance and context, only to have the other side completely ignore our efforts.

Building Your Own Bi-Directionals

Our monolinks are trying to establish relationships in vain.

We’re starting to look around our mono-linked environment and wonder why it’s so hard to surface relevant contextual relationships.

Bi-Directional Linking with WebMentions

Manually interlinking content takes an awful lot of human curation and effort. Efforts we should probably slog off onto our systems.

A bi-directional link has social awareness – it knows about other pages or ‘nodes’ that point to it, and can make them visible to people. This means we get a two-way conversation flowing between our web locations.

落地时建议先做的 5 件事

  1. 先写清这个工具在强化思考还是在替人思考。
  2. 默认交互不要只会谄媚:该追问、该给反例、该要求证据。
  3. 智能体界面要露出推理步骤,而不是只给一个光滑答案。
  4. 知识发布用可生长的笔记,而不是一次性营销长文。
  5. 改产品前先画隐喻:用户以为自己在做什么,系统实际在做什么。

和智能体产品怎么接

龙虾PRO做 OpenClaw 落地时,最该从这类笔记里拿走的是「别把聊天框当唯一界面」。数字员工要能追问、能验证、能把过程摊开,而不是只负责说好话。

本文侧重全链路风控方法论。落地时请用自身业务单据做回放验证,不要把示例阈值直接当生产策略。 相关:风控体检 · 方案资源

常见问题 FAQ

什么是AI智能系统?

「AI智能系统」可概括为:With the recent rise of Roam Research , the idea of bi-directional linking is having a bit of a moment. 本文从定义、方法与实践要点展开说明。

为什么要关注AI智能系统?

关注AI智能系统,是因为它直接影响效率、风险与可复制性。文中指出:With the recent rise of Roam Research , the idea of bi-directional linking is having a bit of a moment.

如何落地AI智能系统?有哪些关键步骤?

建议按以下路径推进AI智能系统:1) 先写清这个工具在强化思考还是在替人思考。;2) 默认交互不要只会谄媚:该追问、该给反例、该要求证据。;3) 智能体界面要露出推理步骤,而不是只给一个光滑答案。;4) 知识发布用可生长的笔记,而不是一次性营销长文。;5) 改产品前先画隐喻:用户以为自己在做什么,系统实际在做什么。。细节见正文对应章节。

AI智能系统适合哪些人或团队?

AI智能系统更适合:产品/技术负责人、运营与增长团队、需要落地智能体或自动化的中小团队、关注「AI智能系统」方向的读者。若你只需要单次聊天式问答,可先读概念;若要上生产,请重点看步骤、权限与风控相关段落。

关于「Bi-directional links are not new」,本文给出了什么结论?

在「Bi-directional links are not new」部分,要点是:Web is built around. They act as one-way pointers we follow in a linear sequence. Bi-direction Linking in Personal Digital Gardens While we can link to any site, the destination page hasn’t a clue we’ve done so. We set

实践AI智能系统时常见误区有哪些?

常见误区包括:① 只追工具不建流程;② 没有权限/审计边界就上生产;③ 缺少指标与回滚方案;④ 把演示效果当成稳定 SLA。针对AI智能系统,请以正文中的检查清单与约束条件为准,小范围验证后再扩面。