Building signals that trade themselves
频道: Claude
视频: https://www.youtube.com/watch?v=EOg4gY0Yln0
原文语言: en
统计: 共 54 轮
[0:18]
I'm Tashara Fernando. I'm head of data and AI at Mang Group. Mangroup are an alternative investment manager. We manage over $200 billion of assets. Our clients are pension funds, sovereign wealth funds, and large institutions.
我是 Tashara Fernando，担任 Man Group 数据与 AI 负责人。Man Group 是一家另类投资管理公司，管理着超过 2000 亿美元的资产。我们的客户是养老金、主权财富基金这类大型机构。
[0:38]
We manage real people's money, thousands of people's pensions and investment capital. So when we think about AI, the stakes are high for us. Our clients are real people from their teachers in Canada, their metal workers in Japan.
我们管的是普通人实实在在的钱——成千上万人的养老金和投资本金。所以一谈到 AI，对我们来说风险是很高的。我们的客户都是活生生的人，可能是加拿大的老师，也可能是日本的金属工人。
[0:57]
So, we really need to get AI right. If we get this wrong, we could lose real money. One of the really large parts of our business is systematic trading. And that represents a huge opportunity to be aided by AI.
所以我们真的得把 AI 这件事做对。一旦做砸了，那就是真金白银的亏损。我们业务里很大的一块是系统化交易（systematic trading），而这块恰恰是 AI 能大显身手的地方。
[1:13]
By systematic trading, I mean algorithmic trading capabilities that look across thousands of securities and hundreds of markets to make investment decisions. So systematic trading is really about trading signals.
我说的系统化交易，是指那种横跨上千只证券、上百个市场来做投资决策的算法交易能力。归根结底，系统化交易的核心就是 trading signal。
[1:34]
And you can think of a signal like a fantasy football team. You can think that we want to pick the best players for our squad based on some intuitive strategy. So the green bars here would be a starting lineup. The red bars would be the reserve squad, the people that you don't want in the team. And the people in the middle, they might come in, you might kind of transfer them in, but
你可以把一个 signal 想象成梦幻足球（fantasy football）里的球队。我们要凭某种直觉策略给阵容挑出最好的球员。这里的绿色柱状就是首发阵容，红色柱状是替补席上你不想要的那批人，而中间这些人，可能会被换进来、转入阵容，
[2:00]
they're they're not the star players at the moment. Maybe a subs bench. So, a signal is really about thinking about a striker maybe hitting form, but you need to transfer them in before the Friday deadline when the price might go up.
但目前还算不上是明星球员，大概就是替补席上的角色。所以一个 signal，本质上就是去判断某个前锋可能要进入状态了，但你得在周五截止前把他转进来，因为之后他的身价可能就涨上去了。
[2:19]
And then you have savvy managers who are really thinking about form fixtures and what might happen to get the most points in the season. And they want to transfer the right players in at the right time and at the right cost. So this is quite similar to systematic trading. A trading signal is really just this with stocks. So the bars here would represent company
厉害的经理会真正去琢磨球员状态、赛程，以及整个赛季怎样能拿到最多积分。他们想在对的时间、用对的成本，把对的球员转进来。这跟系统化交易其实很像。一个 trading signal 说白了就是把这套思路套到股票上。所以这里的柱状代表的就是公司的
[2:45]
stocks. We want to back the ones that would make money and we want to short the ones that won't. So in this example, we've ranked the stocks by the past 3 month returns and we run that through history to see if it would have made money.
股票。我们想做多那些会赚钱的，做空（short）那些不会赚钱的。在这个例子里，我们按过去三个月的收益率给股票排了序，然后把它放回历史数据里跑一遍，看看这么做到底能不能赚钱。
[3:04]
The interesting question is always what is that factor that you want to rank things by? What's the strategy to get the right stocks in your team? And does it work? And how do you know whether it works or not? Well, the truth is you never really know. I'd love to be able to tell the future, but I can't. So, the best thing that we can do is look at what happened
有意思的问题永远是：你到底该用哪个因子来给标的排序？要把对的股票挑进队伍里，该用什么 strategy？它到底管不管用？你又怎么知道它管不管用？说实话，你永远没法真正确定。我也很想能预知未来，可惜做不到。所以我们能做的最好的事，就是回看历史上
[3:32]
historically. We run that strategy, we codify it, and we run it against 15 years of history or even longer. And what that does is it runs that strategy through lots of macroeconomic environments, through lots of stresses.
到底发生了什么。我们把这套 strategy 跑起来、把它代码化，然后拿它去回测（backtest）15 年甚至更长的历史数据。这么做的意义在于，能让这套策略经历各种各样的宏观经济环境、各种各样的压力测试。
[3:49]
And we can see how it performed. And that back test produces lots of statistical factors. Some examples might be how much money did it make? So what's the annualized return? When it lost money, and they always do at some point, how much did it lose? And we call that a draw down. And we look at some even more complex statistical factors. One's called a sharp ratio which compares the
然后我们就能看到它表现如何。这次 backtest 会产出一大堆统计指标。比如：它赚了多少钱？也就是年化收益是多少？当它亏钱的时候——而且总有亏的时候——它亏了多少？这个我们叫回撤（drawdown）。我们还会看一些更复杂的统计因子，其中一个叫夏普比率（sharpe ratio），它衡量的是这套策略的
[4:15]
volatility of that strategy versus how much it returned. And it's this process, this systematic trading workflow that we think that we can use AI to really enhance to come up with those ideas to run the back tests and that has been our focus.
波动率相对于它的收益是个什么水平。而正是这整个流程、这套系统化交易的工作流，我们认为可以用 AI 来大幅增强——用它来产生想法、跑 backtest，这也一直是我们的发力点。
[4:38]
So there are trading signals running right now in production at Mang Group, a regulated investment firm running real capital that were researched, back tested and proposed by AI. By that I mean humans came up with the sorry AI came up with the idea. AI got the data. AI ran the back test. AI then wrote up the strategy proposal and AI productionized the signal.
所以现在，Man Group 这家受监管、动用真实资金的投资公司，生产环境里正运行着一些 trading signal，它们的研究、回测和提案都是由 AI 完成的。我是说，AI 想出了点子——不好意思，是 AI 想出了点子，AI 取了数据，AI 跑了 backtest，AI 接着写出了策略提案，然后 AI 把这个 signal 产品化上线。
[5:13]
Humans of course reviewed all of the output to make sure that it was sensible. But a AI was at the center of that process. And I'm sure you want to know what was that signal? What was that investment idea?
当然，所有产出都经过人类审核，确保它合情合理。但 AI 是整个流程的核心。我相信你们肯定想知道，那到底是个什么 signal？那个投资点子又是什么？
[5:31]
How much money did it make? How can I use it? Sorry, I'm not going to tell you that today. That's our IP. What I'm here to tell you about today is our journey. What was the foundation that allowed us to do that? And how can you apply those learnings in your company?
它赚了多少钱？我又该怎么用它？不好意思，这些今天我可不能告诉你们，那是我们的核心 IP。我今天来要讲的，是我们这一路走来的历程：是什么样的基础让我们能做到这一点？以及你们又该如何把这些经验应用到自己公司里？
[5:52]
And it really starts with AI understanding our workflows. And to do that, we use skills. Can I have a show of hands in the audience as to who's written a skill? Okay, that's great. Most of you. So, coming up with the signal is the quick bit. The hard part is everything that you need, everything that's underneath it, all of the workflows that make it happen, that allow you to act on
这一切的起点，是让 AI 真正理解我们的工作流。为此我们用到了 skills。台下有写过 skill 的朋友能举个手吗？很好，大部分人都举手了。其实想出 signal 是最快的那一步。真正难的是它底下所有的支撑——所有那些让它能跑起来、让你能据此行动的工作流。
[6:24]
it. Think of it like an iceberg. The signal is the tip. Underneath it are all of the workflows that make it possible. How do you clean the data? How do you stitch prices? How do you detect outliers? How does it run? What's the infrastructure it runs on? How do you run those back tests?
你可以把它想象成一座冰山。signal 只是露在水面上的那个尖。水面之下是所有让它成为可能的工作流：数据怎么清洗？价格怎么拼接？异常值怎么检测？它怎么运行？跑在什么样的基础设施上？那些 backtest 又是怎么跑的？
[6:47]
And this is where it can quickly go wrong. If different teams are running different versions of those workflows, you get different answers. One team's back test looks amazing. and other teams looks average. And because they're using different workflows, you don't really know whether it was the idea that was better in one team than the other or whether they're just
这就是事情很容易出岔子的地方。如果不同团队跑的是不同版本的工作流，你得到的答案就会不一样。一个团队的 backtest 结果亮眼得不行，另一个团队却平平无奇。可因为他们用的是不同的工作流，你根本说不清，到底是一个团队的点子真的更好，还是他们只是
[7:11]
measuring things differently. Shared workflows fix that. One common foundation means that effort isn't duplicated and you have consistency. The outputs are comparable. And that's extremely important in systematic trading when we're comparing signals.
度量方式不一样而已。共享工作流就能解决这个问题。有了一个共同的基础，工作就不会重复，而且能保证一致性，产出之间才有可比性。在系统化交易里，当我们要拿不同 signal 做比较时，这一点极其重要。
[7:35]
Out of the box, Claude is an amazing general purpose tool. It does a lot, but it doesn't know us. It doesn't know our data. It doesn't know our systems. It doesn't know how we work. And it's the same for everybody in this room. So the first thing that we had to do was teach it. Not by retraining it, not by doing fine-tuning, but by giving it access to our data, our capabilities, and our
开箱即用的 Claude 是个非常出色的通用工具。它能做很多事，但它不了解我们，不了解我们的数据、我们的系统，也不了解我们的工作方式。在座各位都面临同样的情况。所以我们要做的第一件事就是去教它——不是重新训练它，也不是做 fine-tuning，而是让它能访问我们的数据、我们的能力、我们的
[8:07]
workflows. That's our superpower. We have decades of institutional knowledge in systematic research and some of the best technical capabilities on the street. And if we can connect that with AI, then AI can leverage that superpower.
工作流。这才是我们真正的杀手锏。我们在系统化研究领域积累了几十年的机构经验，还拥有业内顶尖的技术能力。如果能把这些跟 AI 接上，那 AI 就能把我们这身本领发挥出来。
[8:29]
Skills are the connective layer that allow AI to leverage that superpower. So getting them right is paramount and that was our focus. But we got it wrong before we got it right. And I want to tell you about our story today.
Skills 就是那一层连接层，让 AI 能借力发挥我们的看家本领。所以把 skill 做对至关重要，这也是我们的重点。不过我们是先做错了，才慢慢做对的。今天我想跟大家讲讲我们这段经历。
[8:49]
We really focused on adoption. We went all in. We were doing skills workshops. Anthropic helped us with that. We were doing hackathons. We wrote a blog. We were doing showand tell sessions. Everybody was writing skills. The adoption was really out of this world.
我们一开始非常聚焦于推广采用，全力以赴：办 skills 工作坊（Anthropic 在这方面帮了我们不少忙），搞黑客松，写博客，开成果分享会。人人都在写 skill，采用率高得简直离谱。
[9:09]
But we started to see some cracks in our approach. It was really the power users that were building the skills. It wasn't the process owners. And what that meant is that all of the skills really represented a local optimization for one user. They weren't common organizational solves.
但我们开始注意到这套做法有些裂痕。真正在写 skill 的是那些高阶玩家，而不是流程的负责人。这就意味着，所有这些 skill 其实只代表了单个用户的局部优化，而不是面向整个组织的通用方案。
[9:32]
And nothing was really more symptomatic of this than when we ran one of the showand tell sessions one day and there was a guy who used to travel a lot at Mang Group and he had loads of expenses to do and he spent loads of time doing this. So he wrote a skill for it. He gave lots of pictures of receipts to Claude and it would do the expense report for him and he brought this to
最能说明这个问题的，莫过于有一次成果分享会上的事。Man Group 有个员工以前经常出差，要报一大堆账，光做这事就得花他不少时间，于是他写了个 skill。他把一堆收据照片喂给 Claude，它就替他把报销单做好了。他把这个带到了
[9:55]
the show and tell session and he even shared it with a few people in his team and it was working really well. And then a few days later, the expense approver came to us and was like, "Why is Claude creating so many expense reports for my cost center? People from technology, people from the people team. Why do I have to approve all of them? I'm in sales. I I don't want to approve
成果分享会上，还分享给了团队里几个人，用起来效果相当不错。可几天之后，报销审批人找上门来说：“Claude 怎么往我这个成本中心（cost center）里塞了这么多报销单？技术部的、HR 的人都有，为什么这些全要我来批？我是销售部的，我可不想去批
[10:16]
everybody else's expense reports." And we dug into it and it was just because the the cost center code was hardcoded. And it was really just that that was this um this local optimization. Nobody had reviewed that skill. It worked for him. it worked for his team, so it was going to work for everybody.
别人的报销单。”我们一查才发现，原来是因为成本中心的代码被写死了（hardcoded）。说到底就是这个局部优化惹的祸。没人审过这个 skill。它对他管用、对他团队管用，他就觉得那肯定对所有人都管用。
[10:33]
But that's not the case. And he wasn't accountable for that. He kind of thought it was quite funny. And I mean, so did I, to be honest. Um, but it was really symptomatic of a broader problem. People were just codifying their ways of doing things. They weren't the organizational ways of doing things. And in many cases, they weren't actually the workflow owner.
但事实并非如此。而且他也不对这事负责。他还觉得挺好笑的——老实说，我也觉得挺好笑。但这其实正是一个更大问题的缩影：大家只是把自己的做事方式给代码化了，而那并不是整个组织的做事方式。很多情况下，他们甚至根本不是那个工作流的负责人。
[10:57]
And this is a huge problem when it comes to things like back testing and systematic trading. It starts to become a blocker to scaling to enterprises. Agents can't leverage those. There's no commonality.
一旦碰到回测、系统化交易这类事情，这就是个大问题。它开始成为企业级规模化的拦路虎。agent 没法去借力这些东西，因为根本没有共通性。
[11:13]
And we saw that something had to change. Has anyone else faced this problem when they've been writing skills? That it was actually the process. It was the people who were the power users of a process rather than the owners of it that were writing the skills. Can I have a show of hands for that?
我们意识到，必须得变了。在座有谁在写 skill 的时候也遇到过这个问题——真正在写 skill 的，其实是某个流程的高阶使用者，而不是这个流程的负责人？遇到过这种情况的能举个手吗？
[11:30]
Good. Yeah, we really saw that across the board. But we saw that skills governance started to be the secret source that unlocked these enterprise use cases. If you could connect your common workflows to AI, give it access to your data and your capabilities, you could really allow agents to act on those skills.
很好。是的,我们在各个领域都看到了这一点。但我们发现,skills 的治理才是真正解锁这些企业级用例的秘密武器。如果你能把日常工作流连接到 AI,让它访问你的数据和能力,你就真的能让 agent 基于这些 skills 去行动。
[11:57]
And if you can do that, you can allow Claude code to do problems as complex as systematic trading. So our solve for this was to have a common marketplace. Every skill was visible, tagged and tested with evals.
而一旦做到这一点,你就能让 Claude Code 去处理像系统化交易这么复杂的问题。我们的解法是搭一个统一的 marketplace,每个 skill 都是可见的、打了标签的,而且都用 evals 测试过。
[12:20]
We wanted to ensure consistency. Imagine a library. It captures decades of institutional knowledge. There are sections for the finance department, the people department, the research department. We care for every item. We care for every skill in those departments.
我们想确保一致性。你可以把它想象成一座图书馆,里面沉淀了几十年的机构知识。有专门给财务部门、人事部门、研究部门的区域。我们用心对待每一件藏品,也用心对待这些部门里的每一个 skill。
[12:45]
The skill is owned by the workflow owner. They're all tested. Usage is tracked. They're all reviewed. They have a life cycle. And they're all visible to everybody to install. It's really that care that makes this work. And it's the foundation that moves skills from individual productivity solves to a foundation that can set you up for the agenda cage.
每个 skill 都归对应的工作流负责人所有,全部经过测试,使用情况会被追踪,也都经过评审,有完整的生命周期,而且对所有人可见、随时可以安装。正是这份用心让它真正跑起来。它就是那个根基,能把 skills 从解决个人效率问题,提升为一个能为 agentic 时代做好准备的基础。
[13:14]
And it's through that that we were able to apply skills to systematic trading. So now I will give you a bit of a flavor for what it's like to build a systematic signal. We've got a demo and a video on that.
也正是靠这个,我们才得以把 skills 应用到系统化交易上。下面我给大家展示一下,构建一个系统化 signal 大概是什么感觉。我们准备了一个 demo 和一段视频。
[13:28]
This is my knowledge. It's where you'll find our collection of skills and manroup's context store. The skill suggestions are tailored to each business unit. They have clear ownership and are organized into managed and community skills.
这就是我的知识库,在这里你能找到我们整套的 skills,以及 Man Group 的 context 存储。skill 推荐会针对每个业务部门做定制,归属清晰,并被组织成「受管理 skills」和「社区 skills」两类。
[13:43]
Skills and plugins can easily be installed in Claude. Plugins are useful groups of skills. For example, here we have a data plugin which gives us access to mangroups data sets. We can also install skills individually.
skills 和 plugins 都可以很方便地装到 Claude 里。plugin 就是把一组有用的 skills 打包在一起。比如这里有一个数据 plugin,它能让我们访问 Man Group 的数据集。我们也可以单独安装某个 skill。
[13:58]
For example, this is the data set skill which allows me to search man groups alternative data sets. Now those foundational skills are installed, we can start to get a flavor of what it's like to build a systematic trading signal. We can use the alternative data set skill to search for research such as credit card data.
比如说,这个是数据集 skill,它让我可以搜索 Man Group 的另类数据集。现在这些基础 skills 都装好了,我们就可以开始体验构建一个系统化交易 signal 是什么感觉。我们可以用这个另类数据集 skill 去搜索研究素材,比如信用卡数据。
[14:19]
We ask Claude what credit card data sets are available and it identifies a data set of US consumer transactions. We can plot Amazon's monthly credit card spend against its stock price returns. These are the results of the credit card data compared to the stock price for the same period.
我们问 Claude 有哪些信用卡数据集可用,它找到了一份美国消费者交易的数据集。我们可以把 Amazon 每月的信用卡消费额和它的股价回报画在一起对比。这就是同一时期信用卡数据和股价的对比结果。
[14:44]
The blue bars are credit card spend and the line is the stock price. Interestingly, in the graph, you can see spikes for seasonal spend, such as Black Friday and Christmas. Next, we run a back test to see if credit card spend is predictive of the stock price by comparing the peaks in credit card spending with the profits and losses of the stock.
蓝色柱子是信用卡消费额,那条线是股价。有意思的是,在图里你能看到一些季节性消费的尖峰,比如黑色星期五和圣诞节。接下来,我们跑一个 backtest,把信用卡消费的高峰和股票的盈亏对照起来,看看信用卡消费是不是对股价有预测能力。
[15:08]
In the results, the signal shows better performance than a buy and hold strategy. We can see that investing $1,000 in 2021 using this signal would now be worth around $2,500. This could be a fluke for Amazon. So, let's run it on a broader universe of retail companies. As there are multiple companies, we'll run it using our distributed compute infrastructure.
从结果看,这个 signal 的表现比买入并持有(buy and hold)的策略更好。我们可以看到,2021 年用这个 signal 投入 1000 美元,现在大概值 2500 美元左右。这有可能只是 Amazon 一家碰巧的结果。所以我们把它放到一个更大的零售公司池子里跑一跑。因为公司很多,我们会用分布式计算基础设施来跑。
[15:32]
Each company is running an individual worker and then the findings are collected. In this case study, we leveraged four skills to create a systematic trading signal. In reality, our signal research is much more nuanced, accounting for things like seasonality, inflation, and broader sets of securities. We do this with agents as well as humans exploring these ideas. The key takeaway is that
每家公司由一个独立的 worker 来跑,然后再把各自的发现汇总起来。在这个案例里,我们用了四个 skills 来构建一个系统化交易 signal。实际上,我们的 signal 研究要精细得多,会考虑季节性、通胀,以及更广泛的证券范围等因素。我们既用 agent 来探索这些想法,也有人来一起做。最关键的一点是——
[15:58]
the governance of these skills is key. It ensures that everyone has access to the same data and everyone uses the same workflows. Okay, so hopefully what you can see is that if you get that foundation right across the board, if you've got access to all of the data, you can start to leverage more capabilities. Everything from scaling your compute to getting alternative credit card data sets. And
这些 skills 的治理才是核心。它确保每个人都能访问同样的数据,每个人都用同样的工作流。好,希望大家能看到:如果你把这个根基在各个层面都打牢,如果你能拿到所有数据,你就能开始释放更多能力——从扩展你的算力,到获取另类信用卡数据集,各种各样的能力。而且
[16:28]
these are often owned by different teams. And it's really that that allows you to scale to the Agentic platform. So what did we learn along the way? These are the things that I would tell past me and that you can take away.
这些往往分别归不同的团队所有。正是这一点,让你能够扩展到 agentic 平台。那么一路走来我们学到了什么?这些就是我想对过去的自己说、也能让你们带走的经验。
[16:47]
Firstly, focus on that organizational context. That is your IP. It's your moat. It's one of the few safe spaces left in AI. The frontier labs are not going to solve context for you. It's not on the internet. They don't know your workflows. And you already have that context.
第一,聚焦在组织的 context 上。那是你的知识产权,是你的护城河,也是 AI 时代为数不多还安全的领域之一。前沿实验室不会替你解决 context 这件事,它不在互联网上,他们不了解你的工作流,而你本来就已经拥有这些 context。
[17:08]
You have decades of it. The work is on exposing it, not reinventing it. And skills are how that those decades of institutional knowledge become leverage. Treat those skills like production code because that's what they will become.
你拥有几十年积累的 context。要做的是把它暴露出来,而不是重新发明一遍。skills 正是把这几十年的机构知识转化成杠杆的方式。要把这些 skills 当成生产代码来对待,因为它们最终就会变成生产代码。
[17:27]
Plan your approach before you plan the roll out. Who's going to own the skill? Who's going to review it? How does it get retired? How does it get tested? Decide this be before shipping the first skill, not after the hundth like us.
在规划推广之前,先规划好你的方法。谁来负责这个 skill?谁来评审它?它怎么退役?怎么测试?这些要在发布第一个 skill 之前就定好,而不是像我们一样,等到第一百个的时候才想。
[17:46]
Adoption is not a licensing problem. It's a people problem. Once you've got that platform in place, you need to encourage people to engage with it. We need to really think about how we capture that organizational context and rethink our workflows rather than just augmenting them.
采用率不是一个授权(licensing)问题,而是一个人的问题。当你把平台搭好之后,你还得鼓励大家去真正用它。我们得认真思考怎么把组织的 context 沉淀下来,并重新设计我们的工作流,而不只是给它们做点增强。
[18:08]
And that's a training problem. It's an engagement problem. So you really need to outreach to people who are using this platform. And it's through this it's through these ideas that we've been able to scale. man groups about 17 800 people 1,700 people something like that and we now have 750 of them using claude code across developers quants the people team the
这是一个培训问题,也是一个参与度问题。所以你真的需要主动去触达那些在用这个平台的人。正是靠着这些做法,我们才得以规模化。Man Group 大概有一千七八百人左右,现在其中已经有 750 人在用 Claude Code,涵盖开发者、quant、人事团队、
[18:38]
finance team everybody across all of the departments is using claude code we're seeing a lot of engagement because they're able to use those capabilities in a simple way they don't need to know about everything they have this skills platform that understands our workflows We now have over 100 governed skills and at least as many community skills that are looked after in a library and
财务团队——各个部门的人都在用 Claude Code。我们看到了很高的参与度,因为他们能以很简单的方式用上这些能力,不需要事事都懂。他们有这个 skills 平台,它理解我们的工作流。我们现在有超过 100 个受治理的 skills,还有至少同等数量的社区 skills,都被妥善地维护在一个库里,
[19:06]
they're well governed. And what this has done is it has allowed us to unlock the capability to use AI in systematic trading. So skills governance really unlocks AI at that enterprise scale. The thing that I'm most proud of is that I feel that we've got our eyes on the prize. We have a solid bedrock built on decades of institutional knowledge.
而且治理得很到位。这一切带来的结果,就是让我们解锁了在系统化交易中使用 AI 的能力。所以说,skills 的治理真正解锁了企业级规模上的 AI。我最自豪的一点是,我觉得我们始终盯着真正重要的目标。我们有一块坚实的基石,建立在几十年的机构知识之上。
[19:38]
And in the not too distant future, I can see us having swarms of agents leveraging those skills to look for new investment opportunities. So what's the takeaway for you? Really think about how you're going to capture that context. Which department owns it?
而在不远的将来,我能想象我们会有成群结队的 agent 利用这些 skills,去寻找新的投资机会。那么对你们来说,要带走的是什么?认真想清楚你要怎么沉淀那份 context,它归哪个部门所有?
[20:04]
What's the process for governing them? Where will they live? How will you test them? How will you retire them? connect a golden path from your AI platform to your capabilities and your context. Once you have that basis of knowledge, if you care for it and AI can leverage it, that will really set you up for the agenda age.
治理它们的流程是什么?它们放在哪里?你怎么测试?怎么让它们退役?把一条「黄金路径」从你的 AI 平台一直连通到你的能力和你的 context。一旦你打下这份知识的基础,只要你用心维护它、让 AI 能利用它,这就真的能为你迎接 agentic 时代做好准备。
[20:34]
Thank you very much everyone.
非常感谢大家。