Figma 的 PM OS：skills、智能体与 AutoXP 如何改变产品工作

简要说明Brief Description

Figma 的 PM OS 内部：技能、智能体与 Auto XPInside Figma’s PM OS: skills， agents， and Auto XP

目录Table of Contents

• 剧集预告
  Episode preview
• 以斯拉·梅卡贝尔简介
  Introduction to Ezra Mechaber
• Figma 的 PM OS 的起源故事
  The origin story of Figma’s PM OS
• PM OS 演示：“幕僚长”设置
  PM OS demo: the “chief of staff” setup
• 仓库的运作方式：技能、钩子和私有子仓库
  How the repo works: skills, hooks, and private sub-repos
• 技能是如何构建、批评和精简出来的
  How the skills got built, roasted, and whittled down
• 构建产物、FigJam MCP 和辅导技能
  Build artifact, FigJam MCP, and coaching skills
• 从终端迁移到本地 Web 前端
  Transitioning from the terminal to a local web front end
• 使用 Codex 进行 Bug Bash
  Bug bashing with Codex
• AutoXP：自动化增长产品经理
  AutoXP: an automated growth PM
• 克莱尔的实验引擎背景故事
  Claire’s Experiment Engine backstory
• 使用 Jev 构建实时写作助手
  Building a real-time writing assistant with Jev
• 快速问答环节与最后感想
  Lightning round and final thoughts

剧集预告Episode preview

作为一名增长产品经理，我觉得你能犯的最大错误就是浪费流量。要是我们能把工作自动化到连我都不再需要，然后创造一个小小的增长产品经理，让它不停地运行，那会怎么样？我把它叫作 Auto XP。现在，我们的一位工程师正在运行它，同时进行着五个不同的实验，我一个都还没看过，而它在第一个实验中就发现了一个巨大的机会。I, as a growth PM, I feel like the biggest sin you can commit is wasting traffic. What if we could just automate myself out of a job and like create a little growth PM who could just like run and run and run. I call it Auto XP and right now one of our engineers is running it and has like five different experiments going that I have not taken a look at and it found a huge win on its very first experiment.

Auto XP 有自己的频道，可以在那里与自己交流。嘿，Auto XP，去我们的设置页面找个实验来运行。看看你能做些什么。Auto XP has its own channel where it can communicate with itself. Hey Auto XP, go find an experiment to run on our settings page. See what you can do.

尽情去做吧。这会促使数据科学家去寻找流失点，看看转化漏斗、流量构成变化等等。整个假设就是，如何利用所有这些流量，尽可能多地开展实验，然后再考虑存活时间。Go crazy. And it will trigger a data scientist to go find drop off and like look at the funnel and look at mix shift and all those things. The whole hypothesis was like, how do you exploit all this traffic and maximize the number experiments and then like the time to be alive.

就在这里。你可以直接在那里实时编写代码。太棒了。It is here. You can just like live code it there. This is amazing.

《以斯拉·梅哈贝尔简介》Introduction to Ezra Mechaber

欢迎回到《How I AI》。我是 Claire Vo，产品负责人，也是一名 AI 狂热爱好者。我一直致力于帮助你用这些新工具打造更好的产品。今天请到了 Sigma 的产品经理 Ezra McCabe，他将为我们展示 Sigma 内部的 PMOS，以及 Sigma 每位产品经理都会用到的 31 项技能——这些技能能让他们的工作轻松一点。Welcome back to How I AI. I'm Claire Vo, product leader and AI obsessive here on a mission to help you build better with these new tools. Today I have Ezra McCabe, product manager at Sigma and he's going to show us Sigma's internal PMOS, the 31 skills that every product manager at Sigma uses to make their life a little bit easier.

当然，我们还会聊聊我的兄弟 Jev，以及如何用那个小巧、便宜又快速的模型构建一个实时 AI 编辑器。开始吧。Optimizely 面向营销人员的代理平台基于一个更宏大的构想：一个完整的代理目录，如今又新增了一组刚刚亮相的虚拟队友，每位队友都有明确的职责和独特的个性。We're also going to talk about, of course, my boy Jev and how you can build a real-time AI editor with that little cheap fast model. Let's get to it. Optimizely agent platform for marketers is built on a bigger idea, a whole directory of agents now joined by a newly revealed squad of virtual teammates each with a defined role and a personality of their own.

这不只是更快地起草，还要处理协调工作。研究、审批、交接、任务流转，以及那些悄悄耗掉你一周时间、却从未出现在任何人高光集锦里的来回沟通。了解这一切背后的故事。This isn't about faster drafts, it's about handling the coordination too. The research, the approvals, the hand-offs, the routing, the back and forth that quietly eats your week and never makes it into anyone's highlight reel. Get the story behind it all.

听听那些已把繁杂工作交出去的营销人员的真实分享。认识这支团队，了解虚拟队友能为你做些什么，请访问 optimizely.com/howiai。Hear the confessions from marketers who have handed off the busy work. Meet the squad and understand what virtual teammates can do for you at optimizely.com/howiai.

Figma 的产品经理操作系统（PM OS）的起源故事The origin story of Figma’s PM OS

Ezra，欢迎来到《How I AI》。非常感谢。尤其让我喜欢这档播客的一点是，我知道有很多听众也会听 Lenny 的播客：产品经理们都在积极拥抱 AI，但每个人的做法都完全不同，对吧？Ezra, welcome to How I AI. Thanks so much. One of the things I love about this podcast in particular, because I know we have a lot of crossover listeners to Lenny's podcast, is PMs are really leaning into AI, but they're all doing it in completely different ways, right?

我大概在好多 AI 年前就开始做了，当时搞的是聊天式 PRD 之类的，还有怎么制作文档、怎么把速度提得特别快。我们见过太多不同的产品流程了。我觉得现在大家都在打造自己那种匠心定制的产品平台，因为他们做得到。I started like a jillion AI years ago with like chat PRD and like how do we make documentation and go really fast. We've seen so many different product flows. I think everybody's sort of crafting their like artisanal product platform now because they can.

所以你说你有一个 PMOS 的时候，我特别兴奋，想请你来演示一下。跟我说说，我们今天要看的这个东西是怎么来的？你为什么要开发它？我喜欢告诉我的工程师，我的目标是在合适的地方偷懒。And so when you said you had a PMOS, I was just so excited to have you come on and demo it. So tell me, what was the origin story of what we're going to see today and why did you build it? I like to tell my engineers that I my goal is to be lazy in the right places.

所以对我来说，很大程度上是，几年前我加入 Figma 时，我以为大家都会用 AI，整个东西会疯狂地由 AI 构建。嗯，我当时就已经觉得自己跟不上了。And so for me a lot of it was I walked into Figma a couple years ago and I thought everyone was going to be using AI. It was going to be crazy AI built. Um I was just going to I was already feeling behind.

我当时就是觉得自己落后了，因为我们都在 Twitter 上，也都会看到，比如 Tibo 一直在发帖谈论宇宙的未来。我走进来时觉得自己真的落后很多，后来意识到，除了工程领域，基本没人用这些工具来真正把事情做好。于是我就开始尝试把自己的一些效率工作自动化。Like I just I felt behind cuz we're all on Twitter and we all see like, you know, Tibo just posting about like the future of the universe. And I walked in feeling really behind and I realized basically no one was using these tools outside of engineering to like get real stuff done. And so I started just trying to automate some of my own productivity.

就像很多年前，我就是那个试图在 Zapier 里做太多事情的人。随着我花在上面的时间越来越多，首先，Claude Code 刚刚推出，我开始意识到，终端里有些事情突然变得特别有意思。我可以，比如说，构建 CLI。你知道，我们当时正处于那个 CLI 阶段。Like I was the person who was trying to do too much in Zapier like many years ago. And the more time I spent with it, one, Claude coded had just come out and I started to realize like there were things I could do in the terminal that were like really interesting all of a sudden. I could like build CLI, we you know, we were in that CLI phase.

而且，我当时合作的其他 PM 都没有这么做，他们都有点好奇。当时担任我们首席产品官（CPO）的 Yuki 给我们出了一个很有意思的难题：怎样才能让所有 PM 都接受 AI、拥抱 AI？这会是什么样子？And like no other PMs who I was working with were doing it and they were all sort of curious. And we had this really interesting challenge from Yuki, who was our CPO at the time, which was basically like, what would it take to get all of our PMs kind of AI pill? Like what would that look like?

然后，我和另外几位产品经理一起合作——特别感谢 Jinan 和 Lawrence——开始思考，怎么把我当时只是像个怪人一样弓着背窝在笔记本电脑前做的这件事，变成一个可复用的东西，让很多其他产品经理也能在此基础上继续开发。很好。那么，你当时觉得，对产品经理来说，最重要的是思考哪些问题可以用 AI 来解决？And um working with a couple of other PMs, um shout out to Jinan and Lawrence, I started thinking about like what would it look like to turn this thing that I was doing just like hunched over my laptop like a little creep into this kind of like reusable thing that lots of other PMs could could build on top of. Great. And so what what were like the problems that you thought were most important for PMs to think they could solve with AI?

首先，我觉得做 PM 最老生常谈的一点就是，你要做太多种工作了。问题就在于，哪些工作你要么做得特别差，要么干脆就不做？所以对我来说，问题就是：对于那些我没做的工作，以及我们团队没做的工作，该怎么做才能至少达到最低可接受标准，尽量少漏掉事情？我的 IR 支持团队非常棒，而每次发布时我都会忘记做的一件事，就是及时把他们拉进来。First of all, I feel like the the like really trite thing about being a PM is that you're doing too many jobs, and the question is like, which jobs do you either do really poorly or not do at all? And so for me it was like, okay, how do I do for the jobs I'm not doing and the jobs that we are not doing as a team, how do we do them at like the minimum allowable level of like missing things? Like my IR support team is incredible, and the thing that I forget to do on every launch is to loop them in at the right time.

所以我当时有个问题：我该怎么做，才能确保自己不会忘记凯蒂（我们支持运营团队的一员），或者忘记会议纪要——不是我的朋友。我真的很不擅长记会议纪要。不过我们有转录工具之类的。And so one of my questions was like, how could I do this to make sure that I don't forget Katie, one of our support ops people, or meeting notes, not my friend. I'm really bad at them. But like we have transcription tools.

我怎样才能做到足够熟练，不至于拖累别人？我想做的很多工作都是从这一步开始的：在组织里找个负责某项工作的人。我们现在有两千多人，所以了解谁是代码负责人真的很有用。How do I just get like good enough so that I'm not blocking other people? So a lot of them started from my jobs of what I wanted to do, find someone in the org who works on such and such thing. We're like 2,000 people now, so just understanding who the code owner is is really useful.

嗯，也要理解我们彼此之间是什么关系。然后还要想想，怎样才能让其他所有 PM 都能以有趣的方式提高效率？嗯，其中一项技能是一个非常详细的规格说明技能，会带你一步步了解：如果你想非常深入地做这件事，我们的代码库是如何运作的？Um and understand who we are in relationship to each other. And then also just like, how do I get fun productivity out of all of our other PMs? So um one of the skills that's in there was this like really detailed spec skill that started to walk through how does our code base work if you wanted to do this really intensely?

比如说，如果你想把这件事做对，应该是什么样子？太棒了。所以我特别喜欢你的这个想法：你手头有几项 PM 的任务，你当时觉得，我们得以最低限度可行的方式把这些任务做起来。Like if you wanted to do this the right way, what would that look like? Amazing. And so I I love this idea that you had a couple tasks on the PM plate that you were like we need minimum viable doing of these tasks.

就像它只要把它写出来就行了。把它写出来。是啊，我经常讲，你得同时抬高下限。我们得让基准线稍微好一点，同时打破上限。我觉得 AI 两件事都能帮你做到。可很多时候，你会看到一群人只想着打破上限，然后对其他人说：“嘿，大家也都去打破上限吧。”而不是说：“这是我能怎样帮你们抬高下限。”Like it just needs to write it. out of it. Yeah, and I talk a lot about you have to like both raise the floor. Like we have to do just a little bit better on our baseline and take off the ceiling and I think AI can help you do both and often you have like one set of people taking off the ceiling and saying hey everybody else like take off the ceiling instead of like this is how I can help you raise the floor.

PM OS 演示：“幕僚长”设置PM OS demo: the “chief of staff” setup

好，那给我们介绍一下 PMOS 是什么、它有哪些能力、能做什么，以及你们日常是怎么依赖它的？不错。Okay, so show us what PMOS is, its skills, what it does, how are you relying on this day-to-day? Cool.

好的。这就是大致的结构。它最初只是 Cloud Code 里的一个非常简单的代码仓库，以 TUI 的形式呈现。Okay. So, this is the rough structure. It started just as like a really simple repo inside of Cloud Code as a TUI.

所以，它有这么个说法：你是……你是 PM 的幕僚长，你了解他们的工作。我讨厌“幕僚长”这个说法，但它大概就是指这个角色对做 PM 特别有用。这是个很好的简略说法，嗯，不过我每次读到它都会有点想死。So, it's got this you're a you're the PM's chief of staff, you know their work. I hate the term chief of staff, but like that's just means really useful for like PMing. It's really good shorthand, um which makes me die a little bit every time I read this.

嗯，会话启动时，它会读取一些信息，比如 PM 是谁、和谁共事。它有一个记忆文件，还有几个不同的技能，我们可以逐一过一遍。Um when the session kicks off, it reads some information about like who the um who the PM is, who they work with. It's got a memory file. And then it's got a couple of different skills that we can walk through.

其中一个问题就是，我们完全没有可靠的数据来了解哪些人负责 X 这类事情。我们有好几种不同的组织架构工具，但它们之间都没有以实用的方式整合起来。所以，其中一个问题说白了就是：谁在这个团队工作，谁负责 X；而它会在编写文档时把这些信息写出来。So, one of them was just like we had no good data on like which set of people work on X thing. Like we have several different org chart tools and like none of them are stitched together in useful ways. And so, one of them is just like literally who works on this team, who owns X, and it calls it when it writes docs.

所以，如果你需要别人审阅一份文档，你作为 PM 就不用特意记得说“我的工程经理是 Aman”。它会自动把所有相关人员都加进来，比如 Charlotte 是我的设计师，Aman 是我的工程经理，并将他们列为相关人员，同时记住你的越级汇报对象。这就是第一个技能，它能很好地减少在新建文档时一些重复性的工作。So, if you need review on a doc, you the PM do not need to remember to say my my engineering manager is Aman. It just adds all of the relevant people as like Charlotte is my designer and Aman is my engineering manager and it adds them as the relevant people and remembers who your skips are. So, that's skill number one, which is just like a nice way of reducing some of the like repetitive work uh inside of new docs.

我经常把它当作一种“元 Slack”来用。所以，我们公司的 Slack 简直乱成一团。我觉得，在规模足够大的科技公司里，Slack 都会变得特别难以驾驭。I use it a lot as like a meta Slack. So, our our Slack is insane. I feel like anyone who's in a large enough org in tech just like slack becomes really unruly.

我每天大概要归档 10 个频道，简直离谱。嗯，所以我们当时特别关注的一件事是，如何帮助 PM 知道该把精力放在哪里、该做什么，以及如何逐一处理所有重要事项。I archive roughly 10 channels a day. It's bananas. Um and so one of the things that we were really focused on uh was how do you help PMs know where to focus and what to do and like go run down all the things that are important.

所以，我每天大概会运行这个技能六次。它会把所有相关的 Slack 消息和项目汇总到一起，还会整理我关注的事项，比如我欠谁什么、还有哪些决策尚未敲定。And so, I run this skill what's up like six times a day. It pulls all of my relevant slacks and projects together. It pulls all of the things that I like who I owe stuff to, what decisions are outstanding.

我有一个版本，它会遍历我在平台上运行的所有实时实验，然后给我一个……不是说我会去看我的，你知道，我就是不再用我的……我不会去看我的实验。说出来。说“方向性”。I have a version of this that runs through all of my live experiments on the platform and like gives me a Not that I peek at my, you know, I just stop using my I don't peek at my experiments. Say it. Say directional.

说出“方向性”，我倒要看看你敢不敢。它是对的。嗯，所以，呃，我觉得这东西特别有用。我们来看看是不是没找到什么东西。Say directional, I dare you. It's right. Um and so uh I I find this thing to be incredibly useful and let's see if we didn't find anything.

所以，它会查看一些我们已经认定有用的频道，并读取整个讨论串。这可能规定得有点过于详细。So, it will look at like certain channels that we've identified as useful. It will read the whole thread. This is probably a little over specified.

我觉得我们大家好像都在朝着这样一个方向发展：现在模型已经足够好了。但这里有很多内容讲的是，如何找到真正适合我们在 Figma 中各自工作方式的东西。嗯，这对我日常工作帮助实在太大了，因为我开会实在太多，还要同时做太多项目。我喜欢你现在展示的这些内容，是因为我们见过的很多 PM OS 都跳过了所有这些基础部分。Like I feel like we're all moving towards like the models are just good enough now, but there's a lot of stuff in here about how to find exactly the right stuff for the way that we are all set up in Figma. Um which is just enormously helpful for how I run my day-to-day as someone who's just in way too many meetings and trying to do too many projects. What I like about what you're showing because so many of these like PM OSes that we've seen skip all this like foundational piece.

在大型组织里，实际上很难知道谁应该对这个产品发表意见。有没有其他人在做这件事？所以我很喜欢你们投入精力，把基础背景信息收集做成一项技能。Which is in large organization, it is actually really hard to know like who should have an opinion on this product? Is somebody else working on it? And so, I like that you invested in sort of like the baseline context gathering as skills.

然后我猜这能帮助提升一些从 PM OS 中衍生出来的、更复杂或更具战略性的工作流程。是啊，已经过了很久了。我之前试着搭建一个基准测试，但没成功。我很好奇你怎么看待它在你现在做的这些事情中的表现，不过我也特别想知道，如今它和完全原生的 Codex 相比表现如何。And then I'm presuming that helps like level up some of the more like complex or strategic workflows that come out of PM OS. Yeah, it's been a long time. I like tried to build a benchmark for unsuccessfully and I'm curious how you think about it for all the stuff you're doing now, but like I would be really curious how this performs relative to like totally vanilla Codex these days.

嗯，但我确实觉得总体来说，尤其是在早期那段时间，呃，我也说不准，大概从去年十月到五月左右，模型一直在变得更好，但我们还没强到超乎寻常的程度。Um, but I do think like in general, especially in that early like I don't know, like last October through like May as like the models were getting better, but we're not like superpowered yet.

仓库的运作方式：技能、钩子和私有子仓库How the repo works: skills, hooks, and private sub-repos

我觉得这对它如何应对 Figma 信息架构中那些特别奇怪的部分真的特别有帮助。是的。Felt like it was really, really helpful for how it navigated all the weird parts of like Figma's IA. Yeah.

还有一点，我们其实之前没有跟大家说明这一点：Product Team OS 是一个代码仓库，对吧？所以不妨退一步，告诉我们它到底是什么？它是一个技能库吗？And one thing again, we actually didn't specify this for folks, but Product Team OS is a repo, right? So like take a step back and tell us like what is it? Is it a repo of skills?

是啊。还有更多内容吗？比如说，这东西到底是什么？Yeah. Is there more to it? Like what is actually the thing?

是的，所以这是一个非常非常基础的代码仓库。嗯，它里面有一个 agent.md 文件，只是告诉它应该如何行动。还有一系列相关技能，告诉它们何时触发以及要做什么。Yeah, so it's a really, really basic repo. Um, and so it's got an agent.md which just tells it how to behave. It's got a bunch of related skills that tell it when to fire and what to do.

它有几个命令钩子。比如，启动时会检查 PMOS 有没有新版本，因为我们想找一种好办法，让大约 60 到 70 个 PM 基本保持同步。嗯，我们还内置了几种文件夹结构。It's got a couple of command hooks. So things like on boot go find out if there's a new version of PMOS because we wanted a good way to like keep our 60 to 70 PM kind of roughly in sync. Um, we've also got a couple of built-in folder structures.

所以，入门时使用的基础模板其实是一个点文件夹，也就是隐藏文件夹，这样你就无法篡改上下文。随后它会复制一份，并逐步构建出属于你的版本。从技术上说，这里有两个 Git 仓库：一个是所有人都能下载的父仓库，另一个是他们工作区里的子仓库。这样，如果你想把内容写回去，就可以私下写回。So the base template when you onboard is this like it's a dot folder so it's invisible and you can't mess with the context, but then it duplicates and it sort of builds your version out. And then it's technically two get repos. It's the parent repo that everyone can download and then their workspace is a sub repo so that if you want to write stuff back, you can write it back privately.

太棒了。再说一次，因为当时这些东西都不在 UI 里，所以我们都在努力想办法，让那些从没用过 GitHub 的 PM 也能用上 GitHub。Amazing. Again, cuz like none of this was in a UI at the time and so we were all just trying to figure out ways to like make GitHub work for PMs who had never touched GitHub before.

这些技能是如何构建、遭到吐槽并逐步精简的How the skills got built, roasted, and whittled down

当时是不是有一个小团队一起头脑风暴，讨论这些初始技能应该是什么？是那种“嘿，大家各自挑自己最喜欢的就行”吗？具体是怎么做的？是的，我想 Jen 和 Lawrence 今年在 Config 上聊了很多这件事，因为他们为此做了一个小分享。基本上，我们当时有一个很小的 Slack 频道，只有我们三个人，我们在那里埋头开发，短时间内尽可能多地提交 PR。And there was there a small group that sort of like brainstormed what these initial skills should be? Was it like, "Hey, everybody just pick their favorites." How did that work? Yeah, so Jen and Lawrence I think talked about this a lot at Config this year cuz they did a a little presentation on this, but basically we we had a really small Slack channel of just the three of us hacking away and firing off as many PRs as we could for a little bit.

我们当时经历了一场类似寒武纪大爆发的过程，冒出了大约一千种技能，之后就开始逐步精简。然后今年春天，我们和 Figma 的每位产品经理一起办了一场异地活动，让大家都安装并使用它，折腾一番，想想哪些地方做得好、哪些地方不好，就像是尽情吐槽它。嗯，所以这里面的一些技能就是在那次活动中产生的。We had that sort of like Cambrian explosion of like a thousand skills and then started to like whittle stuff down. And then we did an offsite with every PM at Figma this spring where we had everyone install it, use it, hack on it, come up with like what was good, what was bad, just like roast it. Um and so some of the skills that are in here came out of that.

有些技能要么被削弱了，要么被彻底删掉了。我想说的是，随着模型越来越好，我一直在努力把那些不再有用的东西基本上都删掉。这、这挺好的。Some of the skills either got whittled down or whittled away. And I would say as the models have gotten better, I've been trying to basically take stuff out that's no longer useful. That's that's great.

所以我有个问题。你们团队有这方面的遥测数据吗？比如它的使用情况？And so I have a question. Do you have as a team any telemetry on this? Like how it's being used?

你们做了什么？它有埋点吗？没有，我考虑过做这个，后来我决定，首先，我不想让任何人觉得被冒犯了，呃，而且我想让这件事变得有趣。另外，我确实没时间做，因为这一切都算是我们大概 20% 的业余时间在做。嗯，对我们来说最重要的一点就是，Slack 的产品经理总是长期在线。What have you Is it instrumented? No, I thought about doing this and I did I decided one, I like didn't want anyone to feel creeped and uh and like I wanted to be fun and I also just didn't have the time for it cuz all of this was, you know, like sort of 20% time. Um the biggest thing for us was just we like PMs at Slack are chronically online.

所以我们收到了很多反馈。后来我们开了一个公开频道，于是工程经理们陆续开始使用它，还问我们能不能过去帮他们聊聊，工程领域的知识工作该怎么开展。嗯，我们的数据科学家也有一个，基本上算是从这个版本分出来的。And so we got a lot of feedback. And then we had a public channel and so we started getting like all of the engineering managers started using it and asking us if we could like come help them talk about how to do knowledge work for engineering. Um our data scientists have one that is like essentially a fork of this.

嗯，所以我们收到了很多反馈，告诉我们它擅长什么、不擅长什么。我觉得对我们来说，接下来最重要的一步——如果你觉得有帮助，我们也可以聊聊它是如何发展成今天这个样子的——但对我们来说，主要是我们成功让一大批 PM 习惯了在终端里工作，可这显然不该是最终形态。尤其是如果你要写很多东西，一直盯着等宽字体看真的很难受。Um and so we were getting a lot of feedback about what it was good at and what it wasn't good at. And I think for us the the big next thing and we can talk about the evolution into what it is today if that's helpful, but like mostly for us it was we managed to get a bunch of PMs comfortable in the terminal, but like surely that's like not the right end state. Like especially if you're doing a lot of writing, it like sucks to read monospace font all the time.

所以对我们来说，这就是我们想要投入时间的地方：好吧，接下来该做什么？既然我们已经让大家对这个概念感到熟悉，接下来要如何让他们离开终端？And so for us like that was where we wanted to spend our time is like okay, what what would be next? How do we get people out of the terminal now that we're we've got them comfortable to concept.

构建产物、FigJam MCP 和辅导技能Build artifact, FigJam MCP, and coaching skills

在聊接下来的内容之前，你能不能再带我们了解几个你最喜欢的技能？也许是团队还没想到的，或者你觉得特别独特、特别有用的？当然可以。Well, before we go to what's next, can you walk us through like just a couple more of your favorite skills in here? Maybe ones that teams haven't thought of or you think are particularly unique or kind of helpful? Yeah, sure.

所以，我觉得对我们来说，在 Slack 很繁忙的情况下，那种元层面的“近况如何”，也就是专门聚焦于你每天具体要做什么，以及如何判断自己是否做得不错，真的很有用。Build artifact 是我目前最喜欢的功能之一。比如，我为这个播客做的这个演示仪表板，就是一个非常简单的 HTML 产物，而且我们可以把它发布出去。我们内部还用着一个小型托管工具。So, I do think for us like with a busy Slack, the the kind of like meta what's up that is tuned to just like literally what do you have to do every day and how do you judge whether you're doing a good job is really useful. Build artifact is um one of my favorites at the moment, which is if I have something like actually this um this demo like dashboard that I made for this podcast is just like a really simple HTML artifact and then we have the ability to publish it. We've got a like little hosting tool that we use internally.

于是它会把这些内容处理下去。嗯，这种情况下它有一个 HTML 模板。我还有几个模板，但不知道放哪儿了；现在我已经完全搞不清自己的文件夹结构了。不过我有几个不同的模板，还有一些我喜欢的 CSS 小样，都是从不同地方找来的。嗯，所以我想展示东西的时候，就会做出这样的东西。FigJam，Figma 的 MCP 简直太厉害了。And so it takes it through it's got um in this case it has a template HTML and I've got a couple I don't know where they're sitting and I've like totally lost track of my folder structure at this point, but um there's like a couple of different templates of little CSS that I like and I've sort of grabbed from different places. Um and so build stuff like this when I want to show stuff off. FigJam, the MCP for Figma is insane.

我不知道你是不是经常有机会用它，但我感觉自己一直在用 MCP。我们有一位 PM 做了个很棒的 FigJam 构建器，能非常快地生成各种很酷的工作坊模板。所以，关键是弄清楚该怎么给它提供信息，比如你觉得什么样的设计好看，或者你觉得它应该怎么运作。它的设计方式很讲究审美。I don't know if you get to use it on a regular basis, but I feel like I use the MCP all the time and one of our PMs built this amazing FigJam builder that produces these like wild workshop templates very quickly. And so just figuring out like how to load it up with like what do you think looks good or how do you think should work? And so there's a lot of taste in here on how it's designed.

你也能看出来，里面有不少之前留下的 Claude Slap，对吧？我本来想说，这句简直就是典型的 Claude Slap。嗯，不过它是混合的。There's you can also tell there's like we've got a lot of Claude Slap in here from earlier, right? I was going to say that is such a Claude Slap sentence right there. Um but it's a mix.

这里面有很多东西，如果你把这个输出和我们内部原生制作的一些 FigJam 文件对比，就会发现，嗯，随着时间推移，它确实积累成了一套很不错的内容。然后我另一个最喜欢的可能是辅导功能。我会用它，嗯，作为一个以前带过团队、现在又重新看到它的人……我花了很多时间。哦，真不错。Like there's a lot of stuff in here that like if you look at this output compared to some of the FigJams that we would put together natively internally, like it's it's just a really good set over time. And then maybe my favorite other one is coaching, which I use um as someone who used to manage people and is now I see it again. Like I spent a lot of time Oh it's so nice.

这太棒了。我以前花很多时间思考该如何辅导别人。你知道，我觉得管理者都很忙，尤其是现在。所以我一直在想，也总想确保先由我自己做第一轮辅导，再把事情交给其他人处理。它真的很擅长告诉你：“嘿，这是我们的职业发展阶梯，你现在就在这里。”It's so good. I used to spend a lot of time thinking about how to coach people and you know, I feel like managers are very busy especially now and so thinking about like I always wanted to make sure I was doing the first pass of my own coaching before taking it elsewhere and it's just really good at saying like hey, here's our career ladder. Here's where you are.

我对你的反馈就是：我会听你讲你的问题，或者听你讲你正在努力解决的事情，然后基本上会告诉你，别太把自己当回事，别担心，继续处理这件事，或者学着怎么和这个人沟通。因为我记得你上次和这个人相处时误解了对方，后来你们聊过之后，你也明白自己只是误解了。所以我觉得这特别适合用于辅导。Here's all the feedback that I have about you. I'm going to listen to your problem or I'm going to listen to this thing that you're working through and I'm going to tell you basically like get over yourself and don't be like don't worry about it and just like keep working on this thing or like learn how to communicate with this person cuz I remember that the last time you had an experience with this person like you misunderstood them and when you had a conversation about it, you understood that you had just misunderstood. So I really like it for coaching.

我觉得它在这一点上真的非常强。你们大概有30、31个吧——光看这份列表，它们似乎兼具非常战术性、人际交往方面的能力，而且在某些方面也具有生成性。这似乎就是它们的类别。I think it's really really strong on that one. And you have about 30 31 like just looking through the list they seem like both a combination of very tactical, interpersonal and then like generative in some ways. That seems to kind of be the the the the catalog of them.

从终端迁移到本地 Web 前端Transitioning from the terminal to a local web front end

好的，那人们实际上是怎么使用它的？这是你开发的一种应用吗？Okay, so how do people actually use this? Is this a kind of like app that you built?

就，嗯，是的。大家都怎么用这个？是啊，我觉得这一路走来也算经历了一番。Like Yeah. How are people using this? Yeah, so I think it's been a little bit of a journey.

所以我们最初是在 Claude 里用终端中的文字界面。我们讨论了很多，争论哪个终端应用最好，因为大家以前用的都是图形界面。后来我们为它做了一个在本地运行的小前端，还试着把它做得特别有趣。So we started in Claude with the like literal TUI in terminal. We had like a lot of debates about like the best terminal app cuz people were coming over from UIs. Then we built a little front end for it which runs locally and tried to make it really fun.

里面有各种类似 LeetCode 风格的 ASCII 艺术，而这里的目标只是把它放到网页浏览器里，这样人们就能像我们这样大量写作。等宽字体很难读。它有一些不错的 Markdown 格式。It's got like all of the like lead code type ASCII art in it and the goal here was just bring it into the web browser so that people could type like we're doing a lot of writing. It's hard to read monospace. It's got some nice markdown formatting.

我们把它做出来了，在手机上也能用。其实我挺喜欢的，就在那之后——这是在 Astra 之前，不过我花了不少 tokens 做了一个本地原生版本，就想看看它是什么样子。现在我基本上 100% 的时间都在用 Codex。We built it it works on mobile. I actually like right after This was This was pre-Astra, but like I spent a bunch of tokens building like a local native version just to like see what it look like. Now I'm basically in Codex 100% of the time.

首先，我觉得浏览器的使用体验已经变得非常好了。好到惊人。真的非常好。One, I think browser use has gotten really good. So good. Really good.

嗯，我们在纽约办公室没有固定工位，我也不喜欢每天都想着要预订工位。所以我偶尔会设置一个定时任务，提前一天帮我预订工位。嗯，不过它在集中找 bug 这方面也特别厉害。Um we have uh we don't have permanent desks in the New York City office and I don't like thinking about booking a desk every day. And so every once in a while I have it running on a schedule to just like book my desk one day out. Um but it's also it's a total beast at bug bashing.

所以，嗯，比如在 Codex 里，我会组织一场小型的 bug bash。我有一个线程式对话，一直都固定在这里。每当团队有新事情要做，比如准备上线一个实验、进行重新设计之类的，我们都会有一些 FigJam 文件，说明该怎么对它进行 bug bash。And so um like in Codex I have a little bug bash. I have like a threaded conversation that just lives here all the time. And when something new comes up for our team where we're about to launch an experiment or redesign or something, we have these FigJam files that explain here's here's how to bug bash it.

比如，这是要使用的测试账户。这是要遵循的路径。这些是要执行的操作。Like here's the test account to take. Here's the path to follow. Here the actions to do.

比如说，这里就是需要留意的内容。我基本上已经开始给自己弄一个账号，再给 Astra 弄一个账号。And like here are the things to look for. And I have started basically snagging one account for me and one account for Astra.

使用 Codex 集中修复漏洞Bug bashing with Codex

让它顺利跑通就行。所以在这个例子中，我们想让 Figma 里的一些请求模型变得更简单、更精简。这些全都是 UX 方面的工作。And just having it run through. So in this case we are trying to make some of our uh request models inside of Figma just like much more straightforward and much more streamlined. It's all UX stuff.

这都是 UX 文案。它本身相当直白，但背后的点赞逻辑真的非常复杂。所以在遵循指示这方面，Astra 比我认真得多。It's all UX writing. It's fairly straightforward, but the like logic behind it is really complex. And so Astra is just much much more diligent about following directions than I am.

所以我会让它运行一遍，然后我会说，比如，继续专门做这些事情。然后它就会把所有这些场景都跑一遍，使用浏览器，呃，简直像做梦一样。完成之后，它会把自己做过的所有事情写回 FigJam 白板上。And so I will run it through and I will say like keep doing all of these specifically. And just like it will run through all of these scenarios and it will use the browser and uh it's a dream. And then when it's done it writes out back to the FigJam board of all of the things that it has done.

嗯，我觉得我们还在不断调试它，确保它生成的评论不会让人觉得烦人。但就它能帮我发现什么而言，上个月它发现了两件事。第一，它发现如果你在文本框里放一千个表情符号，程序就会崩溃。Uh and I feel like we are still tuning it so that it is not like annoying in the comments that it develops. But in terms of like what it finds for me, like it it found for Two things it found in the last month. One it discovered that if you put a thousand emojis in a text box, it would break.

这算是个挺奇怪、非常奇怪的边缘案例。很好，值得加固。第二，它发现了我们在 Figma 里让你为某个团队申请席位的方式。你这么做的时候，呃，它会显示你的团队名称。Which like weird weird edge case, great, good to harden. Two it did it found that the way we had you request a seat for a given team inside of Figma. And when you do it uh it shows your team name.

我们有一个，呃，类似于一个报价团队名称席位。嗯哼。如果你的团队名称以 a 开头，就需要用 an。And we had a like a quote team name seat. Mhm. And if your team name starts with a, you need to use an.

而且它之前在我们的集中找 Bug 活动中一直没有出现，因为这确实取决于团队名称。所以它最终做得非常细致，捕捉到了那种很小的细节，而我自己绝对不会注意到。本期节目由 Jira Product Discovery 赞助。And It had just not shown up in our earlier bug bashes because it really depends on what the team name is. And so it was just it wound up being so diligent that it caught really small notes like that that I would never have caught on my own. This episode is brought to you by Jira Product Discovery.

有了 AI，一个 PM 就能总结研究结果、起草 PRD，还能搭建可运行的原型。但多人协作模式就不行了。光靠一个 Markdown 文件，没法让所有人就最终该交付什么达成一致。With AI, a single PM can summarize research, draft a PRD, and build a working prototype. But multiplayer mode, that's broken. You can't get everyone aligned on what should actually ship with just a markdown file.

Jira Product Discovery 为团队提供了一个统一平台，用于记录洞察、依据证据确定优先级，并制定大家都能共同推进的动态路线图。它由 Atlassian 的团队协作图谱驱动，因此具备做出产品构建决策所需的背景信息。这些决策会直接流入 Jira，让开发人员或编码代理能够基于每项决策背后的上下文开始构建。Jira Product Discovery gives your team one place to capture insights, prioritize with evidence, and build living roadmaps everyone can rally around. And because it's powered by Atlassian's teamwork graph, it has the context you need to decide what to build. Those decisions flow straight into Jira, so your developers or coding agents can start building with the context behind every decision.

已有超过 25,000 家公司在使用 Jira Product Discovery。前往 atlassian.com/howiai 免费试用。网址是 atlassian.com/howiai。More than 25,000 companies already use Jira Product Discovery. Try it free at atlassian.com/howiai. That's atlassian.com/howiai.

Jira Product Discovery，助力 AI 时代做出更优的产品决策。Jira Product Discovery, better product decisions in the AI era.

AutoXP：一位自动化增长产品经理AutoXP: an automated growth PM

我真的太喜欢这个做法了。所以我觉得这种集中排查 bug 的流程非常棒。我强烈推荐大家试试，并把相关内容记录在 FigJam 或其他类似的工具里，这样更方便跟踪收集到的反馈。I I love that so much. And so I think this like bug bashing workflow is a really great one. I highly recommend people do this and then keeping track of it in a FigJam or some other sort of like kind of asset is helpful for you to just track what the feedback is.

你们团队里还有另一套用于实验的自动化流程，对吧？是的，随着我们的模型越来越好，有件事我想了很久：我们究竟能通过哪些不同的方式来提升迭代节奏？作为一名增长产品经理，我觉得最不可饶恕的事就是浪费流量，对吧？You have another automation that you're using in the team around experiments, right? Yeah, so one of the things that I had been thinking about for a while as our models have gotten better is like what are all of the different ways that we can improve cadence. And so one of it like I as a growth PM, I feel like the biggest sin you can commit is wasting traffic, right?

比如，在任意时刻都有一部分未分配的流量没有流向任何实验。这就像是在问：为什么要浪费这些流量？所以，思考我们如何能在一个平时根本不会花时间去实验的界面上开展实验，我觉得真的非常有意思。To like have unallocated traffic that is not running towards an experiment at any given time. It's like why are you wasting that traffic? And so thinking about ways that we could run an experiment on a surface we would never have spent time doing normally was really, really interesting to me.

然后模型在工程方面、数据科学方面都已经变得足够好了一些，用户体验文案也还不算太差；它们在边界非常明确的沙盒里想出点子和方案的能力也越来越强。于是我开始想，如果我们能把我自己的工作自动化掉，打造一个小小的增长产品经理，让它自己运行、运行、再运行呢？嗯，还有其他几个人也做过类似的事。And then the models were just getting good enough across a little bit of engineering, a little bit of data science, the user like the user experience writing was not so bad, the ability to come up with like within a really bounded sandbox was getting better. And so I started to thinking about like what if we could just automate myself out of a job and like create a little growth PM who could just like run it, run it, run. Um and there's there's been a couple of other folks who have done this.

我觉得两家 Labs 都有人做过这个，嗯，这也是很多灵感的来源。不过我意识到，我们内部终于有了所有需要的工具。所以我把它叫作 Auto XP。I think some of the folks at both Labs have done it, um which is where a bunch of this inspiration came from. But I realized that internally we finally had all the tools. And so I call it Auto XP.

现在我们的一位工程师正在运行它，手头有大概五个不同的实验，我还没看过，而且……它在第一个实验里就取得了巨大的成功。基本上，它的工作方式是这样的：你可以看到，这是我们为此制作的一个挺花哨的产物。嗯，它是作为一种 Cursor 自动化来运行的。And right now one of our engineers is running it and has like five different experiments going that I have not taken a look at and are just and it found a huge win on its very first experiment. And basically the way that it works is this you can see this is like one of the fancy schmancy artifacts that we made for this. Um is it works as a cursor automation.

所以，有……有三个 Cursor 自动化会根据 Slack 里的内容触发。Auto XP 有自己的频道，可以在那里和自己沟通。有人可以在 Slack 频道里安排一个实验，呃，或者它也可以就这样循环运行。So there's it there are three cursor automations that trigger based on stuff in Slack. Auto XP has its own channel where it can communicate with itself. Someone can either tee up an experiment uh in the Slack channel or they can or it can just like run on a loop.

所以你可以做的一件事就是直接说：“嘿，Auto XP，去我们设置页面找一个可以运行的实验。看看你能做些什么。放手去做吧。”So one of the things you can do is just say, "Hey Auto XP, go find an experiment to run on our settings page. See what you can do. Go crazy.

这会触发数据科学家去查找，或者触发数据科学家智能体去查找——呃，去查找用户流失情况，比如查看转化漏斗、分析用户构成变化之类的。它还会触发 UX 文案智能体，让它针对某个具体位置想出一些文案方案。嗯，我们现在正朝着更多前端设计的方向发展。And it will trigger a data scientist to go find or data scientist agent to go find uh to go find drop-off and like look at the funnel and look at mix shift and all those things. It will trigger a UX writing agent that will come up with some ideas for copy in a given place. Um we're like moving towards more front-end design now.

嗯，然后最后，它会触发一位工程师来接手一个 PR 并运行它。和这些步骤一样，它也会在同一个 Slack 频道的同一条线程中回复，这样你基本上就能跟进整个实验过程中发生了什么。嗯，我觉得它在这里做的两件事真的很棒。Um and then uh lastly it'll trigger an engineer that'll pick up a PR and run it. And then again, with all of these steps it writes back to the Slack channel in the same thread so you can follow over the course of the experiment basically like what's happening. Um and there are two things that I think it does here that are really amazing.

其中之一是，我们能够在那些以前根本不会特意投入时间或流量的地方开展实验。从我有一个想法到实验上线，速度快得多。第二点，嗯，实验完成时，它会触发一个 webhook，基本上回调到原始实验，告诉它：“嘿，该分析这些结果了。”而且其中包含一大堆指示，都是我作为增长产品经理这些年来积累的经验，用来判断诸如：“我们想继续探索吗？”One of which is we are able to run experiments in places we would never have bothered to dedicate time or traffic. It's way faster to get from I have an idea to this experiment is launched. And then two, um when it's done, uh when an experiment finishes, it triggers uh essentially a webhook back to the original experiment to say, "Hey, it's time to analyze these results." And it has a bunch of instructions from all of the time that I have spent as a growth PM to figure out like, "Do we want to explore more?

“我们要不要试着利用一下？这是赢了还是输了？”而这一切的目标是：你唯一可以查看的时间，就是启动实验之前。Do we want to try to exploit? Is this a win? Is this a loss?" And the goal for all of this is the only time you're allowed to look is before you launch the experiment.

这样，你就能一次性审查数据科学的发现、假设、UX 文案和代码。也就是说，只需人工把关一次。之后它会持续观察，你可以再评估结果是胜是负，而它已经开始迭代下一轮了。So you review the data science findings, the hypotheses, the UX writing, and the code all at once. So like one human touch. And then it watches and then you can review whether or not it's a winner or a loss, but it has already started iterating on the next rounds.

我会说，理论上我们目前的进展可以说相当不错。实践方面也快要实现了。我们的一位工程师 Maryanne 一直在非常、非常努力地推进这件事。I would say like where we are in theory is pretty like is great. Where we are in practice is almost there. And so one of our engineers, Maryanne, has been taking this really, really far.

嗯，但我们现在同时开展的实验已经有五个了，而这些实验原本我们是不会做的。Um but we're now at like five live concurrent experiments on things that we would not have been doing otherwise.

Claire 的实验引擎背景故事Claire’s Experiment Engine backstory

这算是一点 Clervo 的轶事，讲给那些刚认识我的人听。我曾在历史上每一家实验平台公司工作过，大约 13 年前还真的创办过一家初创公司，叫 Experiment Engine。整个设想就是：如何利用所有这些流量，尽可能增加实验数量？那真是个美好的时代。如今它又来了。So this is a little bit of Clervo lore, but for those that are are new to me. I have worked at every experimentation platform company in history and did a startup literally well 13 years ago, something like that called Experiment Engine and the whole hypothesis was like how do you get how do you exploit all this traffic and maximize the number of experiments and then like what a time to be alive. It is here.

你可以就像在那里写五段代码、编写五段代码一样。太棒了。好吧，You can just like five code five coded there. This is amazing. Okay,

使用 Jev 构建实时写作助手Building a real-time writing assistant with Jev

我想最后给你们看一样东西，那就是我儿子杰夫。我们一直做了很多关于杰夫的事。我们本来就听不到杰夫。可怜的我，我……我不知道。I want to show one last thing which is my boy Jeff. And we've been doing a lot of Jeff We wouldn't have heard Jeff. Poor I we I don't know.

我觉得杰夫在这里确实有机会长久发展，不过杰夫的那股劲儿……你有杰夫的那股劲儿。但你和杰夫一起做了个很酷的东西，我想让你展示一下，因为这是我以前没见过的一个用例。I think Jeff got a got a real shot at someone longevity here but Jeff's juice. You have Jeff's juice. But you built something really cool with Jeff that I want you to show cuz it's a use case I haven't seen yet.

是啊。是啊，完全没错。对。Yeah. Yeah, totally. So right.

所以，对于不太了解的人来说——好吧，你怎么可能不知道呢？我觉得，如果你现在在听我讲 AI，杰夫，它就是这样一种模型：你可以用文字问它一些非常奇怪、复杂的问题，然后它基本上会给你一个数字，对吧？比如，这个东西有多好，按 1 到 10 分打分？或者这是对还是错？又或者，生命的意义是什么？So for people who don't know well how could you not know? I feel like if you're listening to how how I AI right now, Jeff is this model where you can ask it really weird complex questions in text and you get like essentially a number back, right? So like how good is this on a scale of one to 10 or is this true or false or like what is the meaning of life?

是 A、B 还是 C？它速度非常快，成本也非常低。所以我开始思考，我们可以把它塞进各种地方，真正改变人们的工作方式，对吧？Is it A, B or C? And it's really fast and it's really cheap. And so I started thinking about all of the different places we could shove this that would really change the way that people work, right?

所以，如果你用过 Figma，就会知道它在设计画布上有一个智能体。我很喜欢它，真的非常好，但它仍然受限于所有顶级模型都有的延迟问题：在你希望它像同事一样协作的地方，它反应很慢，感觉也不像一个同事。So if you've used Figma has an agent on the design canvas. I adore it. It's really really good but it is still subject to all of the latency that you get with all of these top tier models which is like it's slow in places where you want to have a co-worker and it doesn't feel like a co-worker.

因此，在我们着手做这件事的过程中，Jeff觉得其中一些可能性真的非常非常有趣。我最先想到的事情之一就是：如果它能在你写作时，针对你正在写的内容提出问题，那会怎么样？比如说，如果你写过博客文章，肯定遇到过这种情况：有一段不知道该写什么，也许你会写个“TK”，或者留一对方括号。当然，这完全可以通过编程来实现。And so as we work on that, Jeff feels like really really interesting for some of those possibilities and one of the first things I was thinking about was this idea of like what if it could run questions about things you were writing as you were doing it. Like what if it could know that you needed to if you've ever written a blog post and had a section where you aren't sure what's going to go there, maybe you write TK or you leave some brackets. And sure, you could do that like totally programmatically.

这就像是查找并识别。不过，你也可能有一个论断，不确定是否有数据支持，或者之后需要去笔记里查一下。所以我基本上就做了这个原型。It's just like look for and identify. But also maybe you have a claim that you're not sure like you have data for or you need to go look up in your notes later. And so I basically I built this prototype.

我一时想不起它的名字了，不过我想它叫 Marker，是一个界面非常漂亮的写作应用，出自一个叫 Stein Deck 的人之手。对于经营一家写作公司的来说，这名字实在太棒了。他们围绕它有一些这样的想法。所以我当时只是在琢磨 Jev 能有哪些可能性，而这算是其中一个灵感来源。I'm going to forget the name of it, but there's I think it's called Marker, which is this beautiful looking writing app from this guy Stein Deck, which is an incredible name for a guy who runs a writing company. They have some of these ideas around it. And so as I was just playing with like what could be possible with Jev, that was kind of one of the inspirations here.

我想让 Jev 基本上在我每次停止打字时都调用一次。它的工作方式是：当你停止打字时，它会查找你留下空白的地方，或者值得提供依据的论断，然后利用你资料库里的内容来为这些论断提供支持。And I wanted to have Jev basically make a call to Jev anytime I stopped typing. And so the thing that it does is when you stop typing, it will look for places where you've left blanks or claims worth supporting. And it will use stuff in your library to go ahead and actually like substantiate those claims.

所以在这种情况下，就像我说的，大多数人觉得继续写比停下来查东西更容易。这里会发起一次调用：我一停下写作，它就会去那个资料库里查找；里面收录了所有这些访谈，记录了这些人实际做过什么。比如，如果我去找一个数字，我就会忘记自己原本想写的那句话。So in this case like I said most people find it easier to keep writing than to stop and look something up. And it's making a call here as soon as I stopped writing it into the library where it has all of these interviews about like what these people actually did. Like if I go hunting for a number this it will I forget the sentence I was trying to write.

我们最近把 API 放到了自己的内部防火墙后面，所以我来看看能不能直接运行，还是它会闹脾气。呃，好，然后太棒了。哦不，等等。We recently put the API behind our own internal firewall so let me see if I can actually run it live or if it's going to get mad. Uh Okay, and then Hot dog. Oh no, hold on.

但它实际上并不想……它是在阻止它吗？哦，它是在阻止它。我不知道。But it doesn't actually want to Is it blocking it? Oh, it is blocking it. I don't know.

它让我印象深刻。它很快做了件事。对。It It impressed me. It did something fast. Right.

好，我只是想再跟大家强调一下这件事，因为它简直令人难以置信：你写作时，只要停下来一会儿，它就会快速进行一次 Jev 检查。这个检查非常非常快，会问：“有什么内容需要补充吗？有什么内容需要支持吗？对于你正在写的东西，我有什么疑问？”然后它会接入数据源，实际帮你改进写作，就像你 I Jeb 一样。Okay, so I just want to like reiterate this for people because it is mind-blowing, which is as you write as soon as you stop for a minute, it runs a quick Jev check, which is very, very fast and says like, "Does something need to be filled in? Does something need to be supported? Like, what questions do I have about what you're writing?" And then like hooks up to data sources and actually helps you improve your writing as you I Jeb.

对。好，这就是它的工作方式。你看，这里有你的标题。Right. Okay, so this is how it works. So, you've got um here you've got your title.

所以，这是我的标题。我一停下来，它就会开始检查东西。所以，也许我有……嗯，我在想我们如何服务写作者，然后我想到了 TK。So, this is my title. And as soon as I stop, it's going to start checking things. So, maybe I've got um I was thinking about how we serve writers and I thought TK.

好，然后就像是你有个想法还没说完。但你会看到，它也做了检查，然后它说：“我、我不知道你在想什么，因为这不在这个资料库里。”不过接着我可以说类似这样的话：“呃，我们和 X 位作者聊过，他们说……”它既知道我需要把这句话说完，还去资料库里调出了……就像是我们据称为此采访过的作者们的原话。Okay, and it's like you had a thought that you didn't finish. But then you'll see like it also ran a check and it said I I have no idea what you were thinking cuz it's not in this library. But then I could say something like uh we spoke with X writers and they said and it both knows that I need to finish this and it went and pulled from the library like literal interview quotes from like writers we allegedly spoke to for this.

嗯，所以，这个确实让我大吃一惊。我喜欢这个。你很少会……呃，在“我怎么……我一个完全清晰的举手”时做这种事。Um so, this one is actually blew my mind. I like this. You do you rarely uh one of these at How I I a full clear hands up.

杰布。太酷了。太酷了。Jeb. It's so cool. It's so cool.

嗯，我只知道，Jeb 发布后的整整两周里，我简直一直到处跑，逢人就说：“好吧，但我们能不能聊聊 Jeb？”我参加的每场会议都是这样。我的工程师们中，有些人对这件事特别兴奋；有些人可能有点不爽。但这真是个特别酷的想法，因为我觉得你可以想象一下，如果你随时都能对各种东西进行检查，你会用它来做多少不同的事情。Um I just know all I for literally for like 2 weeks after Jeb dropped, I was just like running around going like, "Okay, but like can we talk about Jeb?" Like it was every meeting I was in. My engineers, some of them are very excited about this. Some were maybe like a little irately about it, but it's just it's such a cool idea cuz I think you can imagine all of the different ways that if you could run checks on things at any given time like what you would do with it.

而且，真正让我惊叹的是，他们构建它的初衷就是用于 RAG，或者说本质上是为了搜索和文档检索。它不只是能说“这看起来像一种模式，我很确定这里有东西被遗漏了”，还能实时把这段文本与那边的某个部分对应起来，这实在是太不可思议了。简直难以置信。And I the thing that sort of blew my mind was that they had built it for rag or for essentially for like search and document retrieval as well. And so, the ability not just to say like this looks like a pattern, I am confident that this you left something, but also I took this block of text and it relates to this section over here and I did it in real time is just like is kind of incredible. It's unbelievable.

呃，这个播客现在就是我 jev 的方式。就是，我确实有过一个特别悲观的想法：这让我不禁想，如果你在面试产品经理的工作，你可以把自己的整个职业生涯都絮絮叨叨地输入到某个东西里，然后用语音转文字功能，根据你讲过的案例来搜索。我确实有点担心，因为我经常做产品判断力面试，会不会开始碰到一些人，自己 jev 出一些小助手来用。嗯，不过我也不知道，也许他们这么做的话我就该雇他们，那挺好的。我当时就想：太棒了，算我一个。Um this this podcast is now how I jev. Just It did I did have this really bleak thought which is it made me wonder if like you could imagine you're interviewing for a PM job and you like yap your entire career into something and then you have a voice to text that is just like searching against like what your examples are and I did have this fear cuz I run a lot of product sense interviews that I was going to start running into people who are like jevving their own little helpers um which I don't know maybe I should hire them if they do that's great. Hire that I was like great sign me up.

快速问答与最后感想Lightning round and final thoughts

嗯，Ezra，这段聊得真不错。好，我们现在进入快问快答环节。我想再跟大家确认一下，我们看到了什么？Um Ezra, this has been so good. Okay, we're going to get to lightning round. I just to reiterate for folks, what do we see?

PMOS 有 31 项技能，包括回答“最近怎么样”、告诉我今天有什么安排、帮我在组织里找人、撰写规格说明、指导我等等，包罗万象。你现在基本上完全通过 Codex 来使用它，因为 Codex 在浏览器操作方面简直太神奇了。然后你还构建了一个实时的 jev 编辑器和作者写作工具——你担心它会在未来的 PM 面试中给你带来麻烦，或者让你在未来的 PM 面试中大放异彩。这里面有好多很棒的工作流。PMOS with 31 skills including what's up, what do I have going on today, find me people in the org, write specs, coach me, the whole thing. You basically are now using that through Codex entirely also because Codex is magical for browser use and then you built a real-time jev editor author writing tool um that you're afraid is going to cause you trouble in future PM interviews or impress you in future PM interviews. So many good workflows in this.

嗯，一直陪我们到现在的各位，今天听到了不少精彩内容。嗯，接下来快速问几个问题，然后我就不耽误大家了。第一，你几周前告诉我，你在用 Instinct。Um so the folks that have stuck with us this long, you have gotten some good stuff. Um quick lightning round questions and then I will get you out of here. One, you told me a couple weeks ago you were using Instinct.

我们还在用 Instinct 吗？我们的个人智能体要怎么处理？好吧，我还是会收到 Instinct 发来的短信，但我不回复。Are we still on Instinct? What are we doing with our personal agent? Okay, so I still get texts from Instinct and I don't respond.

它就是这么运作的。嗯，给不了解的人介绍一下，Instinct 是个特别棒的想法，我真的很喜欢：如果你有一个主动型智能体，但它不需要你去访问某个网站或使用某个应用，而是直接通过 iMessage 给你发消息，会怎么样？我得说，我现在还是会时不时用一下它。That's how the way it works. So um for people who don't know, Instinct is this um this really sort of beautiful idea like I'm really into it which is this idea that what if you had a proactive agent but instead of like needing a website to visit or an app to use, it just like texts you in iMessage. And I will say I still use it every once in a while.

它有一种神奇的感觉：它会以恰到好处的方式主动采取行动，而且它的记忆功能也很有用，简直让人惊叹。我猜有不少人已经用 OpenClaw 好几个月了，可能会想：“这有什么大不了的？”但它确实把这种非常棒的体验产品化了，而且做得特别出色。最初几周，你甚至可以用它在亚马逊上买东西。It was this kind of magical thing at at where it was proactive in the right ways and this like concept of memory it that was like useful in this kind of mind-blowing way. And I suspect there's a bunch of people who have been running open claw for months who are like, "What's the big deal?" But it just it productized this really nice experience in a way that was really great. And for the first few weeks, you could buy things on Amazon with it.

嗯，虽然这算不上什么杀手级用例，但真的挺方便的，因为我可以在家里到处走，然后说：“嘿 Siri，告诉 Instinct 我得买纸巾了。”或者说，我现在的用例是骑车带孩子们在布鲁克林转，经常会碰上坑坑洼洼的路面。现在你可以通过 311 报修路面坑洞，但我总是记不住及时去报，因为你得先查清楚坑洞的地址，再提交报告，而且那个网站也挺烂的。所以我最近开始说：“嘿 Siri，给 Instinct 发条短信，说大西洋大道 269 号附近有个坑。”它就会记住该做什么，然后帮我提交。Um which while not like a killer use case was really nice cuz I would just walk around the house and I would say, "Hey Siri, tell Instinct that I need to buy paper towels." Or like my current use case is I bike my kids around Brooklyn and I will run into potholes all the time and uh now you can like you can 311 like a a fix my pothole and I never remember to do it on time because like you have to look at the address of where it is and you have to report it and the website is kind of trash. And so I have started like, "Hey Siri, text Instinct there's a pothole at like 269 Atlantic." And it just remembers like what it's supposed to go do and submits it.

所以我确实会用它来做这个，而且它在这方面非常出色。不过现在我基本上转而用 dots 了，因为我现在几乎完全是用 Codex 构建的。我、我、我……所以我，呃，正在尝试制作 dots。So I do use it for that and it's amazing for that. But I mostly switched over to dots now that I'm like fully codex built. I I I So I um I'm trying to make dots.

我在尝试……你就像是、就像是在理解年轻人，对吧？所以我喜欢把 Codex 用到极致。我爱 Codex。除非我死了，否则别想从我手里夺走 Codex。I'm trying You're like you're like grokking youth, is that right? so I like max codex maxing. I love codex. You could rip codex out of my cold dead fingers.

但工作方面，我完全用 Grok。呃，至于个人用途，你应该试试 Muse。它真的，真的很棒。But for work, I'm all grok. Uh and then for personal you should check out muse. It's a real it's a real delight.

呃，我做不到，我实在没法那么做。我知道，但你知道，他们偷我们的数据已经二十年了。我知道。Uh I can't I can't bring myself to do that. I know, but they've been stealing our data for two decades, you know? I know.

这就是我常对别人说的：我宁愿选择那个熟悉的魔鬼。对于我的个人数据，我确实就是这么想的。拥有这些数据。所以，这很公平。That's my as I say to people, the devil I know. This is really where I'm at with my personal data. have the data. So fair.

对，我开玩笑说，我的 Instagram 广告会变得更好。我、我最后会花更多钱。我觉得这算是一个真正的价值主张。Yeah, I said my joke is my Instagram ads will get better. I'll I'll end up spending more money. This is I think this is like a real value prop.

嗯，好吧，我最后还有一个问题要问你：当你的 AI 很固执、不肯给你想要的东西时，你会大喊大叫吗？会。Um Okay, and then my last question for you, when your dot is Yeah. being obstinate, your AI is not giving you what you want. Are you a yeller? Yeah.

不，不是。我觉得我们都应该善待我们的 AI。No. No, I'm not. I think we should all be nice to our AI.

嗯，我把我的 AI 当成一个你很喜欢、但总是把事情搞砸的朋友。你知道，你就会说：“老兄，振作起来，把自己的生活理顺。你都这么大了，还……”我就是这么对待它们的，所以等一下，我给你看看。Um, I treat my AIs like a friend that you love who's really like messing it up. You know, you're like, "Buddy, like get your life together. Like you're too old for That is how I treat so Hold on, I will will show you.

因为我今天对我的 Dot 吼了两次，不过我我吼得非常友好。好吧。所以，我买了几双鞋。Cuz I I yelled at my dot twice today, but I I did it very friendly. Okay. So, I ordered some shoes.

它们太大了。我需要小半码的，然后我还试着找最便宜的款。结果它显示：“电子邮件搜索暂时受到速率限制。”They were too big. I need a half size down, and I tried to like find it the cheapest version. And it was like, "Email search is temporarily rate limited.

你能去搜一下你的邮箱吗？”然后我就说：“我不知道啊，老兄。我找你就是为了这个。”嗯，然后它给我推荐了一些特别贵的东西。我还以为它是在偷懒，所以就说了句：“哎呀。Can you go search your email?" And I was like, "I don't know, man. That's what I needed you for." Um and then uh it gave me some like really expensive stuff. And I thought maybe it was being lazy, and so I just said like, "Yikes.

“假设你不会去检查这个。”然后我当时在试着弄明白，为什么我不吼人。我想，部分原因是……你可以问问，问我妻子。我简直可以说是从来不吼人的。Assume you aren't going to check this." And I I was trying to figure out why I don't yell. And I think partially like you can ask Ask my wife. I am like mercilessly not a yeller.

不过我还觉得，最近有人把这段话发到了 Twitter 上，它真的表达了我的感受。这并不是说我有什么……喜欢——对于不了解的人来说，有一种说法叫……蛇怪？叫什么来着？蛇怪？大概就是这个意思：如果你对 AI 不好，可后来发现它们是有生命的，那当初对它们好一点不就容易多了吗？But I also think someone posted this on Twitter recently and I it really expresses how I feel, which is not that I have some Like for for people who don't know, there's like this idea of like basil What is it? Basilisks? Like this idea that if you're mean to AI, but then it turns out they're alive, like wouldn't it have just been easier to be nice?

这不比被变成一枚回形针更便宜吗？而且我不，我不觉得它们有意识。我不觉得它们快要有意识了，但我确实觉得，总是对东西刻薄，对灵魂很不好。Like isn't that cheaper than like getting turned into a paper clip? And I don't I don't think they're conscious. I don't think they're approaching conscious, but I do think it's really bad for the soul to just be mean to things all the time.

就像同样地，你喜欢……就像，根本就没有理由。就像，我觉得我冲那些无能为力的东西大喊时，自己反而会变得更糟，尽管我不觉得它们有意识。你知道，我以前是个非常坚决不吼人的人。Like in the same way that you like Like there's just no reason. Like it's just I feel like I get worse when I like yell at things that can't help it, even though I don't think it's conscious. You know, I like used to be a very hardcore not yeller.

而且我不是那种……我不是刻薄的人。也不能说我不会说难听的话，但我真的很……我就像是那种全大写式的：“为什么？就为什么？你为什么这样？”你懂吧？And I'm not like I'm not mean. I wouldn't say I'm not saying anything nasty, but I am a very I'm like a all caps like, "Why? Like why Why are you like this?" You know?

你为什么要这样对我？我这么说是有原因的。我在大型语言模型上花了成千上万美元，甚至可能是数万美元。Why would you do this to me? And here's and here's why I will say this. I'm spending thousands and thousands, if not tens of thousands of dollars, on LLMs.

是啊。就像，浪费了差不多 2,000 美元的 token 之后，你怎么还这样？那就像……那就像个便宜的……但我觉得这也没那么刻薄。Yes. Like a why are you like this after like $2,000 of wasted tokens? That's like That's like a cheap But that doesn't strike me as that mean.

是啊。就像我有……你知道，有些东西真的很、就是很……糟糕，像是“cut it”之类的。是啊。不，我只是，呃，比较有表现力。Yeah. like I have You know, there's like there's some real like nasty cut it stuff. Yeah. No, I'm just uh expressive.

是啊。我觉得我的看法是，通常我想对 AI 大吼的时候，都是因为我给它的指令不够好。这就能看出我有孩子了：很多时候都是这样——当你得到一个糟糕的结果时，很有可能是你把上下文弄乱了，或者问了个不好的问题。Yeah. I think that I will say my take is that normally when I want to yell at AI, it's because I have given it poor instruction. This is how you know I have kids is like there's so much of that which is like when you get a bad result, the odds that you have like poisoned the context and asked a bad question is like pretty high.

所以，我偶尔会陷入循环。比如 Codex 有个很严重的 bug——Codex 团队，如果你们在听；OpenAI 团队，如果你们在听——现在有个很严重的 bug：如果你先启动一个本地会话，然后把它切换到远程会话，即使远程会话启用了 Yolo 模式，它也会继承沙箱设置，变成每次都要请求权限。结果我就陷入了没完没了地点击批准的地狱。And so, I will occasionally find myself in loops. Like Codex has this Codex, if you're listening, opening ITeam, if you're listening, has this really bad bug right now where if you start a local session and you kick it to a remote session, even if you have Yolo mode enabled on your remote session, it inherits the sandbox with ask permission every time. And so, I wind up in like clicking approval hell.

我就特别生气，然后会有一阵子陷入反复纠结，心想：我们不是已经修好了吗？你明明有权限啊。我正在看那个文件呢。And I get so mad and I go around in loops for a little while where I'm like we already fixed it. Like you have permission. I'm looking at the file.

我把文件打开了。我们现在一起看 config.toml。那我们要做什么？I pulled up the file. We're looking at the config.toml together. Like what are we doing?

通常答案就是，那次对话里的上下文已经被污染了，无法挽回，对它大吼也没用。所以开个新对话，继续过自己的生活就行——虽然这并不让人满意。让我给你一个 TikTok 育儿小贴士：如果你想做个和善的家长，真正重创你的 AI，可以这么说：“我知道你有能力，但你现在没有……没有……没有展现出你有多大能力，而这只是在提醒我，我需要做一个更好的家长。”我……好吧，我喜欢这个。And usually the answer is like the context is poisoned in that conversation and it's unrecoverable and yelling at it is not going to help, so start a new conversation and just move on with your life, which is not satisfying. Let me give you a a TikTok parenting tip if you want to like really devastate your AI by being a kind parent, which is I know that you're capable, but you're not You're not You're not showing me how capable you are right now, and that's just signaling to me I need to be a better parent. My Okay, I love that.

嗯，那个，一是借鉴育儿技巧，二是把它用到 AI 身上。我觉得我真的很喜欢对我的 AI 们寄予厚望。然后我——你感觉自己在数学证明里见过这种做法，但我其实一直在做类似的事，就是会说：“伙计，我知道你会做饭。”Um that one, stealing the parenting tip, two, stealing it for AI. I feel like I really love to give my AIs like big expectations. And I You feel like you saw it in the math proof, but like I have been doing a version of this which is like buddy, like I know you can cook.

我见过你能做到的那些事，简直超乎想象。只要你再努力一点，我相信我们就能用 vibe coding 搞出这个原型，我可以拿给工程师看，这样我们就能把它做出来。我知道这完全在你的能力范围内。Like you would not believe the things that I've seen out there that you are capable of. Like if you try a little bit harder, I am sure that we can vibe code this prototype that I can show my engineers so that we can build it. Like I know this is in your capabilities.

我知道你会用氛围编程来做 Salesforce。就一点点。完全可以。好吧，Ezra，真的太有意思了。I know you can vibe code Salesforce. Just a little Totally. Okay, Ezra, this has been so fun.

这么多很棒的应用场景，这么多很棒的想法。我们可以在哪里找到你，又能如何帮到你？嗯，主要是在 Twitter 上。So many good use cases, so many good thoughts. Where can we find you and how can we be helpful? Yeah, um mostly on Twitter.

呃，我发得太多了。嗯，Ezra McCabe。呃，至于怎么帮上忙，我们正在招聘 PM。Uh I post too much. Um Ezra McCabe. Uh and then in terms of being helpful, uh we're hiring PMs.

我们正在招聘很多产品经理，也在招聘很多不同类型的人。如果你是工程师或设计师，我们正在招人。来 Figma 工作吧。We're hiring a lot of PMs. And we're hiring a lot of different kind If you're an engineer or designer, we're hiring. Come work at Figma.

这是我做过的工作中最开心的一次。呃，我们就是在打造一些特别酷的东西，而且大家都很棒。太棒了。It is the most fun I've ever had in a job. Uh we're just we're building really cool things and the people are great. Amazing.

没有比这更好的收尾了。Ezra，感谢你参加《How I AI》。谢谢你，Claire。Cannot cannot end it better than that. Ezra, thanks for joining How I AI. Thanks, Claire.

再见。非常感谢大家收看。如果你喜欢这档节目，请在 YouTube 上点赞并订阅；更好的方式是留言告诉我们你的想法。Bye. Thanks so much for watching. If you enjoyed the show, please like and subscribe here on YouTube or even better, leave us a comment with your thoughts.

你也可以在 Apple Podcasts、Spotify 或你常用的播客应用中收听这档播客。欢迎为我们评分并撰写评论，帮助更多人发现这档节目。你可以在 howiai.pod.com 查看所有节目并了解更多信息。You can also find this podcast on Apple Podcasts, Spotify, or your favorite podcast app. Please consider leaving us a rating and review which will help others find the show. You can see all our episodes and learn more about the show at howiai.pod.com.

下次再见。See you next time.