为智能体AI时代奠定基础

欢迎收听《实用AI》播客，我们在这里剖析人工智能在现实世界中的应用，以及它如何改变我们的生活、工作和创造方式。

Welcome to the Practical AI Podcast, where we break down the real world applications of artificial intelligence and how it's shaping the way we live, work, and create.

我们的目标是帮助每个人都能把AI技术用起来，让它变得实用、高效，并且人人都能上手。

Our goal is to help make AI technology practical, productive, and accessible to everyone.

无论你是开发者、企业管理者，还是只是对这股科技热潮感到好奇，你都来对地方了。

Whether you're a developer, business leader, or just curious about the tech behind the buzz, you're in the right place.

记得在领英、X或Bluesky上关注我们，及时获取每期节目、幕后花絮和AI洞察。

Be sure to connect with us on LinkedIn, X, or Blue Sky to stay up to date with episode drops, behind the scenes content, and AI insights.

你也可以访问practicalai.fm了解更多。

You can learn more at practicalai.fm.

现在，节目正式开始。

Now onto the show.

嘿。

Hey.

欢迎收听《实用AI》播客的又一期节目。

Welcome to another edition of the Practical AI podcast.

今天我一个人主持节目。

I am your cohost going solo today.

我是克里斯·本森。

I'm Chris Benson.

丹尼尔这次没跟我一起，但我们为你准备了一场非常精彩的对话。

Daniel's not with me this time, but we have an excellent conversation coming up for you.

今天和我一起的是安吉·琼斯，她是代理式AI基金会的副总裁，我觉得这个头衔听起来特别酷，而且所在的地方名字也很酷。

With me today, I have Angie Jones, who is the vice president of the Agentic AI Foundation, which I think is a super cool title to have at at a super cool name place.

我真的很期待了解更多。

And I'm really looking forward to finding out more about it.

安吉，欢迎来到节目。

Angie, welcome to the show.

非常感谢，克里斯。

Thanks so much, Chris.

就像我在开场白里说的，而且我在节目开始前也说过，在AI领域有人正在寻找像代理式AI这样的东西，我是说，那是最酷的头衔了。

So like I said there in the intro, and I said it before the show started and stuff, somebody in AI was looking for a play like the Agentic AI, mean, that is the coolest sounding thing you can have.

但在我们深入探讨这个基金会之前，我真的很想听听，一个人是怎么在职业生涯中发展到最终做这个的？

But before we dive too far into the foundation, I'd really like to kinda hear how does someone Like how do you develop in your career so that you end up doing that?

你能跟我们讲讲你的背景吗？

Could you tell us a little bit about your background?

因为如果你只是随便跟人说，我认识很多做Agentic AI的人，但领导这个基金会的人，那就不一样了。

Because that's one of those things if you went and just said something to I work with tons of people working on Agentic AI, but like leading the foundation of people.

所以我很好奇，你是怎么走到这一步的？

So I'm just curious, like, how do you get to that point?

对。

Yeah.

我是个传统的技术人员。

So I'm traditional techie.

我当工程师已经二十多年了。

So I've worked as an engineer for a couple of decades.

在IBM、Twitter这些地方工作过，最后一份工作是在Block做工程领导。

So, you know, at places like IBM and Twitter, and the last role was at Block in an engineering leadership capacity.

在那个岗位上，我的任务之一就是教全公司一万两千人怎么用AI智能体。

And so in that role, one of my tasks was to basically teach the entire company, 12,000 people, how to use AI agents.

而且我自己也是边学边教，因为说实话，这玩意儿根本没有现成的教材，一开始就是摸着石头过河。

And this is as I'm learning myself, because I mean, there's no book for this, you know, right out the gate.

那时候还挺早的，大概2024年初。

And that was early, like 2024.

所以很多东西都是全新的。

So a lot of this stuff was brand new.

在科技圈都不算普及，更别说其他行业了。

It was not even common in tech, let alone in others verticals.

对吧？

Right?

另外，我还负责开发者关系这块。

And so I also, like, lead developer relations.

所以我的工作很大一部分就是帮全球的开发者了解新技术，以及怎么用这些技术。

And so a big part of my role is helping developers worldwide understand new technologies and how to use them.

所以我们公司Block创建了一个内部AI代理，叫Goose。

And so our company, Block, created this internal AI agent named Goose.

开发者们用Goose来自动化工程测试、辅助编程之类的。

Goose, the developers were using Goose to automate engineering tests, help with coding and things like that.

所以我们当时在教全球的开发者，什么是AI代理。

And so we were teaching developers across the globe, what is an AI agent?

那时候我们还在非常早期的阶段。

Like, were very early in this.

然后，Block的负责人Jack Dorsey就跟我说，嘿，Angie，你一直在教大家用代理。

And so, Jack Dorsey, who leads Block, was like, hey, Angie, you're teaching like everybody else about agents.

我真的很希望公司里每个人都能学会怎么用代理。

I really would love for everyone in this company to learn how to use agents.

所以我就跟财务、市场、设计、人力资源这些部门的人说，所有人都需要了解AI，特别是怎么用代理。

And so I'm talking finance, marketing, like, you know, design, HR, everyone needed to learn about AI and more specifically how to utilize agents.

所以我和团队就特别深入地研究了这个。

And so me and the team went, like, really deep on this.

然后到了一个阶段，公司里几乎人人都对AI很熟悉，大家都用得得心应手了，我就需要深入工程团队了。

And then it got to a point, like, pretty AI fluent company where everyone is comfortable using this, I needed to go really deep on the engineering org.

那才是我真正的主场。

And so that was my home.

我们的工程师们也在用这个，但比如说，我们在开发效率上并没有看到很大的提升。

Our engineers were using this, but we weren't seeing a big difference in developer velocity, for example.

对吧？

Right?

所以我们去探究了一下，发现我们只是触及了冰山一角。

And so we explored that and learned that we're only at the tip of the iceberg.

我们真的可以做得更多，去实现这个自主工程团队。

We really could do a whole lot more to get to this autonomous engineering org.

对吧？

Right?

所以我几乎是拼命地吸收所有新闻、所有发布、所有新出的东西，就像对着消防水管喝水一样。

And so I pretty much drank from the fire hose of like all of the news, all of the releases, everything that's going out.

我会吸收这些信息，过滤掉很多噪音，然后把有价值的东西带给工程师们。

And I consume that, kinda filter out a lot of the noise, and then bring the things that are valuable to the engineers.

所以我会说，我对这个领域了解很多。

And so I would say, like, I know a lot about this space.

而且我在Block工作的时候，还参与了一个协议项目。

And also at my time at Block, I worked on a protocol.

这是一个跨境资金转移协议。

So this was like a cross border money movement protocol.

不了解Block的人可能不知道，这是一家金融科技公司，旗下有Square和Cash App。

So those who don't know Block, that's the company the finance tech company that houses Square and Cash App.

对吧？

Right?

所以钱是我们的专长。

So money is our jam.

所以我当时就在做这个协议。

So I worked on this protocol.

我从没想过自己会成为一个协议专家，但确实学到了很多关于开放标准以及它们如何运作的知识。

Never thought I would be a protocol girl, but learned a lot about, like, just kinda open standards and how all of that works as well.

在我的职业生涯中，我也一直非常重视开源。

Also really big and open source throughout my career.

我一直相信开源，参与开源贡献，并积极倡导开源。

I've always, like, believed in open source, contribute to open source, advocate for it.

对吧？

Right?

所以，当OpenAI、Anthropic和Block想要成立一个Agentic AI基金会时，所有这些因素就汇聚成了一个完美的契机。

So all of that kinda came together in this perfect storm as OpenAI, Anthropic, and Block wanted to form a foundation for Agentic AI.

他们明白，嘿。

They understood that, hey.

我们正在制定的一些标准和开源项目，可能不应该由我们独自编写或拥有。

Some of these standards, some of these open source projects that we're coming up with, we probably shouldn't be the sole authors or owners of these things.

对吧？

Right?

MCP就是一个很好的例子。

MCP is a great example.

MCP就是模型上下文协议。

So MCP is the model context protocol.

这是智能体用来连接应用程序和工具的东西。

This is what agents use to connect to applications and tools.

对吧？

Right?

我们在Block内部也看到了这一点。

Which we saw across block.

Block的每个人都需要MCP服务来连接他们使用的各种应用程序。

Everyone in block needed MCP service to connect to whatever applications they were using.

所以Anthropic意识到，这确实应该放在一个中立的机构里。

And so like Anthropic realized, yeah, this probably should live in a neutral home.

于是这三家公司联合起来，在Linux基金会下成立了Agentic Foundation。

And so those three companies came together to form the Agentic Foundation under the Linux Foundation.

Linux基金会已经存在几十年了。

So Linux Foundation has been around for decades.

大家都认识他们。

Everyone knows them.

所以，是的，这是一个新的基金会。

And so, yeah, so this is a new foundation.

我们一成立这个，我和我们的开源负责人就来到了基金会，我们觉得这太酷了，就开始全职在这里工作。

So once we stood this up, me and our head of open source came over to the foundation, and we thought it was so cool, we started working here full time.

非常酷。

Very cool.

我喜欢你提到杰克·多尔西。

And I like the Jack Dorsey name drop there.

那挺不错的。

That's pretty good.

所以你真的是一路上直接和他一起工作的。

So you actually you were actually working directly with him as well along the way.

是的，我确实在说这个。

And I and I'm being Yeah.

没错。

That's right.

所以我和杰克在推特一起工作，后来他们开始开发这些开源项目和协议时，他把我带到了Block。

So I worked with Jack at at Twitter, and then he brought me over to Block when they when they started developing, like, these open source projects and protocol.

非常棒。

Very cool.

我想稍微回顾一下，因为你刚才提到的事情让我有几个问题，其中一个就是教育。

I wanna back up for a moment because I got a couple of questions from things that you brought up there, and one is the education.

因为我觉得教育人们所在的组织，就像你正在探索的那样，很多组织现在都在努力做同样的事情。而且每年，尤其是2026年，进展速度和智能体技术的兴起都极其迅猛。

Because I think educating the organizations that folks are in, like you were pathfinding along the same kind of task that a lot of organizations are trying to do right now, and that is every year recently, but especially 2026, has been just insanely fast in terms of the level of progress and the onset of Agentics.

去年它们就已经存在了，但今年它们真的席卷了全球，所以现在每个组织都在应对这个问题。而你在教育方面走在了前列，不仅是对开发者，还包括整个组织以及那些可能人们不太关注的部分，因为大家往往非常关注开发者。

They were there last year, but this year it just has taken over the world, and so every org is dealing with that now, and you have taken point on this notion of education, not just for developers, but for the whole org and parts of the org that maybe people aren't thinking about as much because they tend to be very focused on developers.

你能谈谈创造这种变革是什么样的吗？我想把它分开来说。

Can you talk a little bit about what creating that kind of change looks like in terms of And I'm gonna separate it.

我想先问问非开发人员的情况。

I wanna ask about the non developers first.

你走进财务部门，走进其他那些不整天琢磨AI技术细节的组织部门，然后你想说，这里有个新工具，你不仅要从技能提升的角度，还要从让人们接受它的角度，怎么去推进这件事？

You're going into finance you're going into these other organizational departments that are not thinking about the bits and bytes of AI all the time, and you're trying to say, Here's a new tool, and how do you approach that, not only from the upskilling that's required, but also from of getting people to accept it?

因为我的意思是，你看外面的人，普通大众对AI有很多抵触情绪。

Because I mean, see people out there, there's a lot of resistance to AI in the general population out there.

那当你试图这样推动组织前进的时候，你是怎么应对这种抵触的？

And so how do you navigate that when you're trying to move the org forward like that?

对，这两个是非常大且不同的挑战，对吧？

Yeah, these were two very big and different challenges, right?

一个是整个变革管理的问题。

So one is the whole change management of it all.

基本上你是在要求人们用不同的方式思考，用不同的方式做他们的工作。

Like you're essentially asking people to think differently and do their jobs differently.

这些人都是各自领域的专家，对吧？

These are experts in their domains, right?

这些人可能已经干了二十来年了，然后你突然说，哎，把你们的流程什么的都扔掉，我们想让你这么干。

Who maybe been doing this a couple of decades and you're like, oh, kind of throw away like your processes and everything, and we want you to do this.

而且就像你说的，还有抵触情绪，对吧？

Not only that, to your point, resistance, right?

恐惧。

Fear.

这里面牵扯到很多不同的情绪。

Lots of different emotions involved in that.

然后还有整个技术层面的问题，就像我说的，那时候还很早，2024年、2025年。

And then the whole technical part of it where, like, these tools, like I said, this was very early on, 2024, 2025.

那时候还没有这些好用的桌面应用。

You didn't have these nice desktop application.

只有命令行工具。

You had a CLI.

对吧？

Right?

你得复制JSON才能让MCP服务器跑起来。

You were copying JSON to, like, get an MCP server work.

这对那些不天天用这些工具的人来说，简直太陌生了。

Like, this was foreign to folks who, like, don't use these tools every day.

所以这活儿真的不小。

So it was a really big job.

所以你得把所有这些因素都考虑进去。

And so, like, you have to consider all of that.

这不只是说，嘿。

It's not just, hey.

我教你怎么用终端。

Let me show you how to use a terminal.

对吧？

Right?

而是要帮他们明白，他们在这个流程里还能发挥什么作用。

It's helping them understand where they still fit into the process.

对吧？

Right?

有些事情，放手是可以的。

With things, it's okay to let that go.

比如，你可能不应该再做这个了，因为继续做下去已经不值得了。

Like, you probably should not be doing this anymore because it's not a good use of your time anymore.

对吧？

Right?

然后还有，我喜欢说，人们分两个极端。

And then also, I I like to say there's people on both spectrums.

有些人觉得AI是最棒的东西，什么都能做。

There's people that, you know, they think AI is the best thing ever and can do all the things.

还有些人觉得，哎呀，AI很蠢。

And there's other people who are like, Oh, AI is stupid.

什么都做不了。

It can't do anything.

我倾向于站在中间立场，既能现实地看待它的优势和劣势，也知道该用它做什么、不该用它做什么。

I like to kind of be in the middle there where, you know, I can be realistic about its strengths, its weaknesses, what I should use it for and what I shouldn't use it for.

而且从一开始就摆明这个态度帮助很大，因为我不是想让你盲目跟风。

And just leading with that helped a lot because I'm not trying to get you to drink Kool Aid.

对吧？

Right?

我是说，嘿，这里有一种不同的方法，可以帮你提速。

I'm saying, hey, here's a different approach that could speed you up.

对吧？

Right?

它还能让你接触到很多以前可能没有的资源。

That can also give you access to a lot of stuff that maybe you didn't have before.

而这一点是关键。

And that part was the key.

所以，比如说，当有数据的时候，对吧？

So when there's, let's say data, right?

每个人都需要数据，不管你在什么岗位。

Everybody needs data, no matter what role you're in.

如果我说，嘿，听我说，我能通过这个代理，比如某个MCP服务器，让你访问数据库里的记录，那你本来得去找另一个团队，提交申请，要一份报告，对吧，然后还得自己琢磨那份报告。

If I say, hey, listen, I can get you access with this agent and be like some MCP server to, let's say, records that are in this database, then you would have had to go to another team, put in a request, and ask for a report, right, and then try to figure that report out yourself.

我能在几秒钟内把数据给你，让你去做最好的工作。

I can get you that data in seconds so that you can go and do your best work.

所以人们很容易被这种事情打动，对吧？

So people are sold on that kind of thing, right?

所以你要一步一步带他们，给他们一些对他们有意义、但不是他们核心工作的事情，让他们慢慢习惯，开始建立信任，对吧？

So you take them step by step and give them things that are meaningful to them that might not be their core job, just so they could get used to it and they could start building some trust, right?

然后最终，他们会开始多委派一点，再多委派一点，直到他们找到那个合适的点，觉得，好吧，这个不该委派。

And then eventually, they start delegating a little bit more and a little bit more until they find that right spot of, okay, I shouldn't delegate this.

AI做不好这个。

The AI does not do well.

我猜也是。

I bet.

那部分，我来负责。

That part, I'll take.

对吧？

Right?

所以这就是我整体的处理方式。

So that was my my overall approach to it.

我真的很喜欢这个做法。

I really like that.

我知道，当我和别人聊到这个话题时，我经常说的一句话，我觉得和你的经历很契合，就是找到人类相对于AI有明显优势的地方，然后让AI去负责不同的部分，逐项分析工作要求，找出目前人类仍然更擅长的环节。

I know when I get in conversations with folks about this topic, one of the things that I often say, which I think is kind of resonating with your story there, is that find the place where the human has a distinct advantage from the AI and differentiate the AI, go down through the job requirements, and find where the human is still better at this point.

而且这可能是动态变化的。

And that may be fluid.

随着时间推移，这可能会改变。

That may change over time depending on that.

所以保持开放的心态很重要，但我觉得你给人们的建议非常棒，关于如何应对这个问题，因为根据我最近的交流，这确实是大家最关心的问题之一。

So having an open mind is good, but I think that's incredible advice that you're giving people in terms of how to navigate, because I think that's one of the biggest questions that people have out there based on the conversations I'm having.

换个角度，说到开发者，我自己就是一辈子搞开发的。

To flip to the other side of the coin when you're dealing with developers, and I'm a lifelong developer.

我干这行几十年了。

I've been doing it for decades.

而且你看，每天在社交媒体上，我都能看到两类人：一类是那些完全拥抱智能体技术的开发者，他们在编排各种流程；另一类就是那种，哎呀，这东西还是不行。

And see, every day on social media and stuff, I see people, you see the developers that are embracing Agentics fully, and they're orchestrating, and then you see the ones that are like, Oh, it still sucks.

你知道的，就是那些抱怨的话。

I'm You still know, all that stuff.

那你深入开发者群体，想推动大家接受这个技术的时候，你的经历是怎样的？

And was your experience as you dived into the pool of developers trying to get the embrace going here?

所以有一段时间，回头看，你会觉得，哦，这很棒，但其实没那么好。

So for a while, if we look back, so back then you're like, oh, this is great, But it wasn't that great.

对吧？

Right?

我的意思是，而且那还是在早期阶段。

I mean and and they're they're in the early days.

在当时算是不错，但跟现在比，那就不行了。

It was good for that time, but compared to now, it what it's not.

所以那些开发者，可能试了这些工具，但效果不太好。

And so developers who would, like, maybe try the tools and they didn't do a great job.

你让它写个功能什么的。

You ask it to write a feature or something.

它就像，什么玩意儿？

It's like, what?

这太蠢了。

This is stupid.

你懂吧？

You know?

我发现那些开发者，一旦试了一次，如果效果不好，他们基本就放弃了。

Those developers I found, once they tried it once, if it didn't work out well, they kinda threw their hands up.

直到大概2025年底，像是那个，是Sonic 4.5还是4.6来着？

And it wasn't until, like, end of maybe twenty twenty five when the like, was it '4, like, Sonic four five or '4 six?

我都不记得版本号了，但大概是在2025年11月的时候，对，那个模型真的变得很强了。

I don't even remember the versions anymore, but it was like this point in about November 2025 that Yeah, the model The model just powered really good.

对。

Yeah.

但我们等不到那个时候。

But we couldn't wait until then.

我当时有任务，要让所有人都用上AI，提高开发效率。

Like, I had a mandate to like, get everybody using AI and to increase developer velocity.

所以我想了想那个变革管理，要同时带动3500名开发者太难了，尤其是大家情绪复杂，还有抵触心理。

And so what I did, thinking back to that change management, and it was too much of a lift to get it's 3,500 developers to to lift everyone at the same time, especially when you have all of these emotions involved and you have this resistance.

对吧？

Right?

我得说，我们有不少人一开始很抵触这个。

And I would say, like, we had quite a few people who were resistant to this.

所以我换了个办法，有个原则，叫“一九九零原则”。

So what I did instead, there's this rule, it's called the nineteen ninety rule.

这个规则基本上是说，在任何社区里，都会有1%的人是创造者。

And this rule essentially says that in any community, there's gonna be 1% of that community that are creators.

想想社交媒体，或者类似的东西。

Think about social media, anything like that.

会有9%的人偶尔尝试一下，可以说是那些喜欢捣鼓的人。

You'll have 9% that they'll dabble here and there, the tinkerers, if you will.

然后剩下的90%，也就是大多数人，都是消费者。

And then the 90, the bulk of people are consumers.

所以我说，如果我用这个视角来看我们的工程组织，让我去找到那一个人。

And so I said, if I look at our engineering organization through that lens, let me go and put together the one person.

于是我在整个组织里找人，他们不一定非得是那种对AI特别狂热的人。

And so I went across the org and I pulled people, and they didn't necessarily have to be the the drunk off the Kool Aid, like AI peeled people.

但我只需要从我们每个主要的代码库，也就是那些最大的、最关键的项目里，找到代表。

But I just needed representation from every major repo that we had, you know, our largest ones, our critical ones.

我也希望有来自不同团队、不同类型代码库的人。

I wanted people from various teams, different types of repos as well.

所以我需要前端、后端、移动端，还有iOS和Android的人。

So I needed front end and back end and mobile, iOS and Android.

你知道，我需要这些人。

You know, I needed these people.

所以我搞了一个为期一周的小活动，在整个组织里跑了一圈。

And so I did this little week long campaign just going across the org.

这些人不一定是我的直属下属，对吧？

These people don't necessarily I'm not their first line manager, right?

所以我需要得到他们直属经理的支持。

So I need to get buy in from their first line manager.

那完全是另一回事，因为很多人当时根本不认同这个想法，对吧？

That's a totally different conversation because a lot of them weren't even bought into this, right?

但我说，嘿，听我说，你知道你有这个任务。

But I say, Hey, listen, you know you have this mandate.

你得让你团队的人用上AI。

You gotta get people to use AI on your team.

给我一个人，我只需要他30%的时间。

Give me one person that I can have 30% of their time.

我想做的是，第一，他们聚在一起学习这些东西，但这不只是为了他们自己。

And what I wanna do is, one, they all come together, we learn all of this stuff, but it's not just for them.

我需要他们做的是把这些知识融入到系统里，这样你们整个团队都能受益。

What I need them to do is build that knowledge back into the systems themselves so that your entire team benefits from this.

对吧？

Right?

所以他们当时就跟我一起。

And so they were there with me.

我们边喝边聊。

We're drinking.

有50个人。

It was 50 of them.

大家都在拼命吸收新东西，尝试各种方法，因为变化太快了。

Drinking from the fire hose, trying things out because things are changing so quickly.

现在噪音太多了。

There's so much noise.

你根本不知道什么行得通，什么行不通。

You don't know what'll work, what won't work.

对吧？

Right?

在推特上和小演示里，一切看起来都很棒。

Everything looks great on Twitter and a little demo.

但我们面对的是庞大的单体仓库，里面有成百上千个服务。

But we're working with huge, you know, mono repos with, you know, hundreds of services in them.

而且我们处理的是别人的钱。

Like, you know, we're working with people's money.

这些都是企业级系统，你得用不同的方式，更加谨慎地去处理。

You know, these are enterprise systems that you have to approach this a bit differently and much more carefully.

所以他们就会去尝试各种东西。

And so they would try things out.

我们会看到一些东西。

We'll see things.

我们会去尝试。

We'll try them.

有些东西可能只对特定类型的仓库有效。

Some things will work for maybe a specific type of repo.

比如，这在网页上效果很好，但在移动端就不行。

Like, this works great on web, sucks for mobile.

对吧？

Right?

我们不能用那种方法。

We can't use that technique.

但大家一起，我们五十个人能够尝试很多东西，找出什么有效。

But together, the 50 of us were able to try a lot of things, figure out what works.

也许我在我的iOS仓库里确实有一些有效的东西。

Maybe I do have something that works on my iOS repo.

嘿，其他iOS仓库的伙伴们，我发现了这个。

Hey, other iOS repos, here's what I figured out.

对吧？

Right?

然后，就像我说的，把这些东西嵌入到系统里。

And then, like I said, embed this stuff into the system.

所以像上下文工程技术、Agent的MD文件、代理技能这些，都直接内置到仓库里，这样不管谁把他们的代理指向这个仓库，代理都能按照你们团队想要的方式工作，因为已经内置到系统里了。

So things like context engineering techniques, things like, you know, Agent's MD files and agent skills and all of that baked into the repo so that no matter who was pointing their agent at this repo, the agent could work the way that your team wanted it to work because it was baked into the system.

所以我们不用费劲去教每个人怎么做。

So we didn't have to, you know, teach everybody how to do this.

这些骨干成员基本上替他们做了这件事，帮团队过滤掉了噪音。

These champions essentially did that for them and filtered out the noise for their team.

他们会带回那些真正有效、经过验证的东西，然后和团队开个午餐会之类的。

So they would bring back the things that actually work that are tried and true, and then they would do a brown bag session or something with their team.

比如，让我给你们看看我放进仓库的东西，以及为什么它突然对你们有效。

Like, let me show you guys what I put in the repo and why it's working for you all of a sudden.

你明白吗？

You know?

所以这就是我们当时用的方法，效果真的非常好。

So that that was the technique, that we used there, and it worked really, really well.

有时候作为企业主，要发布高质量、看起来像手工制作又有人情味的内容，同时还要用合适的工具、自动化和AI来快速上线，真的很难。

Sometimes as a business owner, it's so hard to put out quality material and content that looks handcrafted and human, but yet still use appropriate tools and automation and AI to make that fast to ship.

这就是为什么我非常欣赏我们的合作伙伴Framer在做的事情。

That's why I appreciate so much what our partner Framer is doing.

Framer是面向创作者、团队和企业的专业网站构建器，适合那些想要专业网站并且注重每个细节的人。

Framer is the pro website builder for creators, teams, and businesses that want a professional site and care enough to get every detail right.

但这不能以无尽的待办事项和漫长的开发流程为代价。

But that that can't come at the price of endless to do lists and long long development processes.

你需要快速实现，所以Framer把智能代理直接集成到他们的平台中，与创建网站的团队并肩工作。

You need to make that happen fast, which is why Framer has integrated agents directly into their platform that work right alongside the teams creating the site.

你可以了解更多关于Framer的信息，或者向Framer专家学习如何更好地利用你的网站，也可以今天就免费开始建站，访问framer.com/practicalai，年度Pro计划可享受30%折扣。

You can learn more about Framer and learn how to get more out of your site from a Framer specialist or get started building for free today at framer.com/practicalai for 30% off a Framer Pro annual plan.

网址是framer.com/practicalai，可以享受七折优惠。

That's framer.com/practicalai for 30% off.

framer.com/practicalai。

Framer.com/practicalai.

可能有一些条款和限制。

Rules and restrictions may apply.

那真是太酷了。

So that is super cool.

我自己也要借用你的这些技巧。

I'm going to, to borrow your techniques myself.

好的。

Okay.

我敢打赌，其他听节目或看节目的人也会这么做。

Bet a few other folks listening or watching will do the same.

在如何应对这个问题上，你确实很有见地。

Really insightful there in terms of how to approach that.

你一路走来经历了很多，现在到了Agentic AI基金会，而且它作为一个组织是全新的，你正在把它建立起来，承担起这些责任。你能谈谈创立这个基金会、让它聚焦、找到合适的人，并且确保自己在做该做的事情，这些过程是怎样的吗？

As you arrived having gone through a lot of this, and you arrive at the Agentic AI Foundation now, and it's brand new as an organization, you're standing it up, you're taking on the responsibilities, could you talk a bit about what was it like to get the foundation going and get it focused and get the right people and know that you were doing the things that needed and what those are?

是的。

Yeah.

这个Agentic AI基金会是在2025年底成立的。

So this Agentic AI Foundation was formed end of twenty twenty five.

所以到现在大概有八九个月了吧。

So it's been, what, about eight or nine months at this point.

大家都很兴奋，对吧？

Lots of excitement, right?

有几十家公司都想加入，因为大家都看到了这个需求。

We had dozens of companies that were interested in being a part because everyone sees the need for this.

而且每个人都在以闪电般的速度创新。

Everyone is also innovating at lightning speed.

现在真的有很多创新在发生。

There's so much innovation that's happening right now.

如果你正在开发的东西，比如，你知道，哦，我们还没搞定这个。

And if you have anything that you're creating that's like, you know, oh, we don't have this figured out.

我们需要为此制定一个新标准。

We need a new standard for this.

没人希望那个标准只在一家厨房里做出来，对吧？

No one wants that standard being cooked in one kitchen, right?

比如说，如果我们谈论智能体商务，PayPal可不想让Stripe自己搞定一切。

If we're talking about Agentic Commerce, for example, it PayPal doesn't want Stripe figuring that out by themselves.

对吧？

Right?

他们想一起合作，或者说他们必须合作，而且他们知道必须合作。

They wanna work together or they need to work together, and they know they need to work together.

所以智能体AI基金会做的就是提供一个中立的平台，让所有这些不同的公司可以聚在一起进行这些对话。

And so what the Agentic AI Foundation has done is provided this neutral home where all of these various companies can come and have these conversations together.

所以我们有工作组，基本上，成员们，他们，好的。

So we have, working groups essentially, where the members, they've okay.

你想加入哪个工作组？

Which working group do you wanna be a part of?

工作组太多了。

There's so many of them.

就像我刚才说的，有智能体商务。

There's like like I said, the Agentic Commerce.

对吧？

Right?

所以如果你在研究智能体怎么在网上买东西，好的。

So if you're figuring out how agents are gonna buy stuff on the web, alright.

我需要维萨。

I need all I need Visa.

我需要贝宝。

I need PayPal.

我需要斯特莱普。

I need Stripe.

我需要所有这些不同的公司聚在一起，共同制定这些标准。

I need, you know, all of these various companies together, and they work on these standards together.

我喜欢把它想象成他们在共同定义游戏规则，并一起搭建游戏棋盘。

I like to think of it as they are defining the rules of the game and creating the game board together.

一旦他们把这些搞定了，就像说，好了，现在我们可以竞争了。

And once they have that figured out, it's like, all right, now we can compete.

好，算我一个。

Deal, you know, deal me in.

对吧？

Right?

所以这就是Agentic Foundation所做的事情。

And so that's what the Agentic Foundation does.

它还容纳了那些标准或那些项目。

It also houses those standards or those projects.

所以目前的项目包括MCP、AgentsMD、Goose、Agent Gateway，而且就在这周，谷歌的A2A（即代理间协议）也加入了基金会。

So right now the projects are MCP, AgentsMD, Goose, Agent Gateway, and then also just this week, A2A, which is Google's agent to agent protocol, has come into the foundation.

所以这些项目，现在有来自各地的公司都在为这些项目或标准做贡献，对吧？

And so these projects, now you have companies from all over contributing to these projects, right, or these standards.

然后你给它更多的发言权。

You then give it more of a voice.

如果你想用这些项目之一，但它属于某一家公司，你可能会有点犹豫，对吧？

If you wanted to use one of these projects, but it lived in one of these companies, you might be a bit hesitant, right?

作为一家公司，如果这个项目属于某一家公司，你基于它来构建产品，你不知道他们会怎么做。

As a company, to build your products on top of this, if it lives with this one company, I don't know what they're gonna do.

你不知道他们会不会把它砍掉。

I don't know if they'll kill it.

你不知道他们的路线图会不会只反映他们自己的目标。

I don't know if they'll just The roadmap will only reflect their goals.

你明白我的意思吗？

You know what I mean?

所以，成为Agentic AI基金会的一部分，就给了你那种信心，嘿，这是一个中立的地方。

And so being a part of the Agentic AI Foundation gives it that confidence that, Hey, this is in a neutral place.

我现在可以在这个基础上进行开发了。

I now can build on top of this.

所以，这就是它的样子。

And so that's what it looks like.

我们围绕这些项目和协议做了很多教育工作，在全球各地举办会议。

We do a lot of education around the projects, the protocols, we throw conferences in all parts of the globe.

而且我要说，这个角色有一个非常酷的地方。

And I'll say, like, one one really cool aspect of this role.

在我上一份工作中，我深入研究了智能体，但同时我也在我的公司内部。

So in my last role, went deep on agents, but I'm also inside of my company.

对吧？

Right?

在开源方面也参与了一些。

A little bit in open source.

我虽然在使用，但我的圈子可能还是局限于北美。

I'm consuming, but I'm still my bubble is probably North America.

现在这是一个全球性的基金会，我的工作就是关注世界各地正在发生的事情。

Now this is a global foundation where my job is to pay attention to what is happening across the world.

在日本、中国、非洲，他们是怎么采用Augetic AI的？

How are they adopting Augetic AI in Japan, in China, in Africa?

你明白我的意思吗？

You know what I mean?

所以现在我有了这种全球视角，这真的非常吸引人。

And so now I have this global perspective, which is absolutely fascinating.

这个角色的一部分职责也是帮助这些不同的国家在标准、协议和项目上达成一致，这样它们就能全面互通。

And part of the role is also to help these various countries come together on these standards and protocols and projects so that they're interoperable across the board.

我很好奇。

I'm curious.

那听起来确实很酷。

So that does sound super cool.

我很好奇，你在这个角色中培养出的全球视角，你怎么评估？

I'm curious with that global perspective that you have developed in this role, how do you assess?

我觉得这很容易，基本上我觉得任何人从自己的视角和自己所在的小圈子里出发，很容易就会认为，我在做Agentyx，其他人也都跟我一样在做，或者有同样的需求，诸如此类。

I think it's very easy pretty much I think it's easy for for anyone kind of coming from their own perspective and their own little bubble that they're in to kind of assume, I'm doing Agentyx and everybody else is doing it just like me, or has the same needs, and stuff like that.

所以我觉得很容易忘记，地域的多样性、生活的多样性，所有这些都会改变用户对此的需求。

And so I think it's very easy to forget that diversity of location, diversity of life, all those things can change the user's need for that.

那么，从那个全球视角来看，你有没有什么特别突出的发现，比如让你惊讶或者引起你兴趣的事情？

And so do you have any particular highlights from that global perspective on things maybe that surprised you or that caught your interest?

我很想听听。

I'd love to hear some of that.

我想说，在像中国这样的地方，人们是移动优先的，对吧？他们使用技术的方式跟我们有点不同。

So I would say in places like China that are mobile first, right, The way they use technology is a bit different than us.

我们在北美，我觉得这里是非常软件即服务（SaaS）导向的文化，而那边一切都是移动端的。

So we're in North America, I would say a very like sass heavy culture, whereas everything is like mobile over there.

所以，比如说，他们对像代理对代理这样的协议有很大需求，就是需要这个应用能跟那个应用对话，而且它们都是代理型应用。

And so now, like they, for example, they have a big need for a protocol like agent to agent, where you need like this app to be able to talk to that app, and they're both Agentic apps.

对吧？

Right?

所以他们就可以用那个。

And so they could, like, use that.

比如说，微信就用到了这个，你知道的，和各种智能体之类的。

Like, for example, like, WeChat uses that, you know, with various agents and stuff like that.

所以对我来说真的很有意思，就是看到，哦，甚至你使用的应用类型都会影响你需要什么样的标准技术或者类似的东西。

So that was really fascinating to me to just see, like, oh, even the types of applications you're using essentially influence like the the types of tech that are standards or or like anything like that that you might need.

所以这只是一个例子，对。

And so that's just one example, yeah.

那挺酷的。

That's cool.

我很好奇，这里我要自私一点了。

I'm curious, and this is where I'm gonna be selfish on my part.

作为工程师和研究科学家，我非常关注自主性，而当你进入移动领域，这就非常接近边缘计算之类的考虑了，具身智能是一个非常热门的领域，当然也是我专注的领域，而且机器人在各个领域的快速崛起，无论是地面机器人还是飞行器之类的，真的是前所未有地起飞了。

As an engineer and a research scientist, I'm very focused on autonomy, and as you're getting into mobile, and that's getting awfully close to thinking about edge concerns and stuff like that, and embodied intelligence is such a hot area, and certainly the area that I'm focused on, and the rapid rise of robotics in all domains, whether they're ground robots or flying things or whatever, is truly taking off like it never has before.

这里没有双关的意思。

No pun intended there.

我很好奇，这种差异在世界某些地方比其他地方更明显。

I'm curious how, this kind of I think in some parts of the world you see that more than others.

我觉得在中国、日本，有些地方你会看到比美国多得多的机器人。

I think in China, Japan, there are certain places where you're gonna see a lot more robotics than you will in The US.

对于美国的听众或观众来说，我们这边远远没有那么多。

For US listeners or watchers, we don't have nearly as much

对，确实是这样。

of That's that right.

那么，当你试图把这些基金会项目推广到不同需求的地方时，你会看到美国人和加拿大人有一种做法，而中国人和日本人可能有另一种做法。

So like how does when you're looking from trying to take these projects that the foundation has and you're looking at those different needs and you're saying, well, the Americans and the Canadians and such kinda have one way of doing it, and the Chinese and the Japanese and other, like, that may have a different way.

这在使用代理的方式、配置方式、构建方式以及它们的用途上都有很大不同。

How do you because that's quite different in terms of how you're using agents in those ways and the way you're configuring it and the way you're constructing them and what their utility is.

当你试图制定真正全球通用的标准，并让所有人都满意时，你会怎么处理这种差异？

How do you approach that when you're trying to make everybody happy with standards that are truly meant to be global?

是的。

Yeah.

所以这就是为什么需要所有人都参与进来。

That is why you need everyone at the table.

对吧？

Right?

如果只有美国那些顶尖的大公司来决定这一切，而没有其他国家的人说，嘿，

And so if you only had, like, the your your top, like, fame companies in The US kinda determining all of this, and there's no one from these other countries that, hey.

机器人技术在这里可是大事。

Robotics is, like, a big deal here.

我们还得考虑实际应用。

Like, we have to think about the physical applications as well.

对吧？

Right?

那就会错过这些视角。

Then you miss that perspective.

对吧？

Right?