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「One Developer, Two Dozen Agents, Zero Alignment」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。

Video Recording

This talk is the first public demo of Ace – a new research prototype we’ve been building within the GitHub Next team. Ace is a realtime, multiplayer coding agent workspace. It’s like Slack, GitHub, and Claude/Copilot had a baby. You work with agents, but also all your coworkers in the same space, sharing chats, context, and all using the same computers in the cloud to do the work.

At this point, in early 2026, all coding agents are designed as single player experiences. But building software isn’t a single player game. I talk through why we need collaborative AI engineering tools and show how we’re exploring the problem.

值得单独记下的观察

• Features that no one asked for, and that don’t solve real problems
• Receiving critical feedback after you’ve finished building something, so you have to toss the whole thing out
• Hairy merge conflicts – multiple agents touching the same files
• Duplicated work – you and another engineer assign agent to the same feature
• Giant stacks of PRs to review that no one has any context for
• Your business context and financial resources determine what the correct thing to build is.
• The political dynamics of who’s in charge and who gets to make decisions.
• The product vision from your leaders and PMs

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