On AI and Knowledge — Pablo Castro, Distinguished Engineer & CVP for AI Knowledge, Microsoft
频道: AI Engineer
视频: https://www.youtube.com/watch?v=RGSFUqzqErE
原文语言: en
统计: 共 11 轮 · Pablo 11
[0:01] Pablo
[music]
[音乐]
[0:12] Pablo
Now taking the stage is CVP and distinguished engineer at Microsoft, Pablo Castro.
接下来登台的是 Microsoft 的 CVP 兼 Distinguished Engineer——Pablo Castro。
[0:22] Pablo
Hello everyone. Hello everyone. Good morning. It's great to be back here at the AI Engineer World's Fair. Now, my job at Microsoft is to connect the dots between AI and knowledge. As an information retrieval nerd, like that's great for me. Like I spend a lot of time on looking at knowledge representation, extraction, search, and whatnot. And thinking about agents and knowledge really invites to reflect on, you know, what it means to know something. And uh, you know, the the the nature of how do we get things done based on what we know. Next slide. All right. There. So, this morning what I thought we would do is spend a little bit of time talking about the nature of knowledge and split it into these three categories of intrinsic, extrinsic, and learned. Intrinsic knowledge is just the knowledge that comes with the models. You know, it's what we uh train the models on, the training data, and what um uh stored in the models' kind of parametric memory. And while it's kind of the obvious thing, I would argue this is the knowledge that actually threw us into the exponential we are in today. It's what started many of the scenarios that then grew on all the things we're doing with agents today. Let me give you an example with code. So, I wrote these two pieces of code about 25 years apart. And yet, the process to put this thing together was surprisingly similar. Like I had to sit down with what I knew or what I had to go look up and then just write it up. And while, you know, I'm illustrating this with knowledge, you could say the same thing about, you know, writing an email or creating a summary of a document. Now, you can see this exponential at play in tasks like these where, you know, I'm sure you can go further back. But an interesting point in time to start looking at this would be when Microsoft introduced IntelliSense.
大家好，大家好，早上好。很高兴再次回到 AI Engineer World's Fair。我在 Microsoft 的工作，就是把 AI 和知识这两件事串起来。作为一个信息检索（information retrieval）的狂热爱好者，这对我来说简直太对口了——我花了大量时间研究知识表示、知识抽取、搜索等等。而思考 agent 与知识的关系，其实自然而然会让人去反思：「知道」一件事到底意味着什么？以及我们究竟是如何基于自己所知去把事情做成的。下一页。好，就是这页。今天早上我想和大家花点时间聊聊知识的本质，并把它分成三类：内生的（intrinsic）、外部的（extrinsic）和习得的（learned）。内生知识就是模型自带的知识——也就是我们用训练数据训出来、存在模型参数化记忆里的那部分。虽然这听起来是最显而易见的一类，但我要说，正是这类知识把我们推上了今天这条指数增长曲线。它开启了很多早期场景，而今天我们用 agent 做的一切都是从那些场景生长出来的。我用代码举个例子。这两段代码，我写作的时间前后相隔大约 25 年。但有意思的是，把它们写出来的过程竟然惊人地相似：我都得坐下来，靠自己已经知道的东西、或者去查资料弄明白的东西，然后一行行写出来。虽然我这里用写代码来说明知识这件事，但写邮件、给文档做摘要，道理其实完全一样。在这类任务上你能清楚看到指数曲线的作用。当然你可以追溯到更早，但一个很有意思的起点，是 Microsoft 推出 IntelliSense 的那个时刻。
[2:30] Pablo
That was in '96. And, you know, it was great. You didn't have to remember function signatures anymore and whatnot. It takes 22 years from there to go for the next step where machine learning helps us actually rank the options we give you in IntelliSense, so it's quicker to pick the right choice. Just 3 years after that, GitHub Copilot launches. And that was one key inflection point. This was even before ChatGPT was announced. And, you know, I would argue that GitHub Copilot, ChatGPT, that sort of experiences were heavily grounded on this intrinsic memory, what the models already knew. From there, of course, things shifted. You know, a couple of years later, Cursor launches, GitHub Copilot X launches, and how we do things kind of evolved really quick, which takes us to kind of late last year. Opus 4.5 ships. And then rapid succession, you know, GPT, Opus, and other models keep getting better and better at coding. Which takes us to early this year, where incredibly successful software like like Open Claw comes out to existence with not a single line of code written by hand. So, this is the shape of the exponential we're in. And a lot of this was powered by the by the intrinsic knowledge in models and of course their ability to reason. Now, in the context of Microsoft, we want to make available all these models and make it easy for you to integrate them into the agents you're building. We do this from our agent platform that starts in GitHub where we all go and build. It has a contextualization system so you can ground your agents. And when it comes to agent hosting, observability, and management, we all do all of these in Foundry. Microsoft Foundry is also where we offer thousands of models in our model catalog so you can pick whatever is the right model for the right task.
那是 1996 年。它当时确实很棒——你再也不用去记函数签名之类的东西了。从那之后花了整整 22 年才走到下一步：用机器学习给 IntelliSense 的候选项做排序，让你更快选中正确的那一个。而仅仅 3 年之后，GitHub Copilot 发布了。那是一个关键的拐点——要知道那甚至是在 ChatGPT 发布之前。我认为 GitHub Copilot、ChatGPT 这类体验，很大程度上就是建立在这种内生记忆之上的，也就是模型本身已经知道的东西。当然，从那以后事情开始变化：几年后 Cursor 发布了，GitHub Copilot X 发布了，我们做事的方式演化得非常快。这就把我们带到了去年年底——Opus 4.5 发布。紧接着，GPT、Opus 以及其他各家模型在编程能力上一个接一个地快速提升。再到今年年初，像 Open Claw 这样极其成功的软件问世了——没有一行代码是手写的。这就是我们身处的这条指数曲线的形状。而这一切很大程度上是由模型的内生知识、当然还有它们的推理能力驱动的。回到 Microsoft 的语境：我们想把所有这些模型都提供给大家，并且让你能轻松把它们集成进你正在构建的 agent 里。我们的 agent 平台从 GitHub 开始——那是我们所有人写代码的地方；它有一套上下文化系统，让你可以给 agent 做 grounding；而到了 agent 的托管、可观测性和管理，这些我们都放在 Foundry 里做。Microsoft Foundry 还在模型目录里提供了数千个模型，你可以针对不同任务挑选最合适的那个模型。
[4:19] Pablo
And we keep adding more every day. In fact, just yesterday we announced that Claude in Microsoft Foundry is generally available so you can use all the capabilities of Claude in the context of the unified experience in Foundry. So you get best of both worlds. Now, an interesting model got us here, but it only gets you so far if you're building a system that or an agent that needs to participate in what's happening in an organization or a company. And you know, as an industry we realized this early and we, you know, we saw the the rag pattern emerge. That started as a pretty low-tech technique, but quickly evolved and what we do today with context engineering and you know, it became a pretty sophisticated system for connecting agents and the knowledge they need to get their job done. Of the many dimensions of of which this got kind of complicated, I'm going to pick on two. One is kind of the evolution from simple and isolated data sets to whole company-wide grounding. And the other one is how we started with simple vector search and whatnot and we really saw this evolve into fairly complicated retrieval systems. So let's start with company grounding. Like at Microsoft, you know, spending time with customers, one of the things we saw early was that whenever you build an agent, you you always have the knowledge you care about for that agent and you'll manage that yourself, but you also need to ground the agent often on the kind of ambient data of your organization, you know, whenever the agent leaves. This includes maybe your documents, your emails, your chat threads, or the information in your data warehouse and whatnot. So, we built Microsoft IQ as a way to give you a single entry point into all these kind of ambient data that agents need to get the job done in addition to the specific information that you build into the agent.
而且我们每天都在往里加新模型。事实上就在昨天，我们宣布 Claude 在 Microsoft Foundry 正式全面可用（GA）——你可以在 Foundry 的统一体验里使用 Claude 的全部能力，两全其美。不过话说回来，一个厉害的模型能把我们带到今天，但如果你构建的系统或 agent 需要真正参与到一个组织、一家公司正在发生的事情里，光靠模型本身是走不远的。作为一个行业，我们很早就意识到了这一点，于是 RAG 这个模式出现了。它一开始是个技术含量不高的手段，但很快就进化了——发展到今天我们做的 context engineering，它已经变成一套相当复杂精密的系统，用来把 agent 和它完成工作所需的知识连接起来。这件事在很多维度上都变复杂了，我挑其中两个来讲。一个是从简单、孤立的数据集，演化到覆盖全公司范围的 grounding；另一个是我们从简单的 vector search 起步，最终看着它演化成了相当复杂的 retrieval 系统。先说公司级 grounding。在 Microsoft，我们和客户打交道时很早就发现一件事：每当你构建一个 agent，你手上总有一份你为这个 agent 专门维护的知识，这部分你自己管理；但你往往还需要让 agent 在你组织的那些「环境数据」（ambient data）上做 grounding——尤其当 agent 走出它的小圈子去干活时。这可能包括你的文档、邮件、聊天记录，或者数据仓库里的信息等等。所以我们打造了 Microsoft IQ，作为一个统一入口，让 agent 除了你专门为它构建的特定信息之外，还能接入所有这些完成工作所需的环境数据。
[6:16] Pablo
Microsoft IQ is not one feature, it's more like a set of capabilities that goes from work IQ that connects your agents to all the documents in say SharePoint, all the emails, calendar, your chats, and the connections between people to fabric IQ that gives you access to all the all your analytics assets, you know, from data warehouses and data lakes to Power BI reports, and foundry IQ, which is what you use for your all agents where you can push your own data and then use it for grounding. And of course, sometimes you have your agents need to go out to the web to ground on data maybe not yours, it's public information, but but you need to use it to complete the picture of what the agent world's view is, and for that we have web IQ. Now, this first part allows agents to ground on the kind of these ambient data. Now, the second dimension I mentioned before is the evolution of the actual retrieval systems. You know, when drive first emerged, I think, you know, what we saw is like an initial adoption for vector databases that really unblocked us from getting a lot of these systems off the ground, and that was great. Um, I think, you know, for a hot second as an industry, we thought that if we could get really, really good at computing cosine similarity between vectors, we were all set for retrieval. It turns out, you know, things never are are never that easy. Uh, so, you know, what evaluations show over and over again is how, you know, if you combine methods, you just get better results. Like in this case, this is an evaluation from actually I search, the search technology behind Foundry IQ. And you can see how individual methods don't do as well as combined methods, particularly when you apply them to real-world customer scenarios. Now, the trick is how you build a platform that allows you to combine all these building blocks without putting the complexity right in front of you.
Microsoft IQ 不是单一功能，而更像一组能力的集合：Work IQ 把你的 agent 连接到 SharePoint 里的所有文档、所有邮件、日历、聊天，以及人与人之间的关系网络；Fabric IQ 让你访问所有分析类资产——从数据仓库、数据湖到 Power BI 报表；Foundry IQ 则是给你自己的 agent 用的，你可以把自己的数据推上去，然后用它做 grounding。当然，有时候你的 agent 还需要到网上去获取不属于你的公开信息，用它来补全 agent 世界观的完整拼图——为此我们提供了 Web IQ。这是第一部分，让 agent 能在这些环境数据上做 grounding。第二个维度，就是我前面提到的 retrieval 系统本身的演化。RAG 刚兴起的时候，我们看到的是 vector database 被率先大量采用，它确实帮我们把很多系统从零跑了起来，这很好。我觉得有那么一小段时间，整个行业都以为：只要我们把向量之间的余弦相似度算得足够好，retrieval 这件事就算搞定了。结果呢，事情从来没有那么简单。各种评测一遍又一遍地表明：把多种方法组合起来，效果就是更好。比如这里展示的这个评测，来自 Azure AI Search——也就是 Foundry IQ 背后的搜索技术。你可以看到，单一方法的表现不如组合方法，尤其是放到真实的客户场景里时差距更明显。而真正的难点在于：如何构建一个平台，让你能把所有这些积木组合起来，同时又不把复杂性直接甩到你面前。
[8:08] Pablo
You like let you opt into it when you need control, but when you have a scenario that is clear, then you can have an easy system. So, in Foundry IQ, that was one of our core design goals. And the way we do this is we actually layer the system. So, you can start at the top, you can go to Foundry and say, "Hey, I have a bunch of, I don't know, PDFs or pictures over there. Just deal with them." And then we'll do everything under the covers, do like, I don't know, chunking, vectorization, deal with relevance and ranking, deal with agentic retrieval and whatnot. Now, if you're an expert and you want control, you can also do that. You can go to the bottom of the stack, you want to build vector indexes and tell us how to quantize the vectors or control lexical retrieval and whatnot. You can do all of that and you can do it in the same stack, which means you can go up and down as you as your needs change. Now, on on top of the core retrieval system, we also introduced an agentic retrieval stack because we see that for easy cases, like, you know, quick single-shot retrieval is great, but for more sophisticated cases, you do want a system that can reflect on on what's in the data set and decide whether or not we've satisfied the information need as stated in the input before we come back with results. Of course, we see a lot of patterns like this emerge and they always the question is, is this actually useful? Like, are the results better? Our experience in our own evaluations is for for difficult cases, agentic retrieval can a difference. You across the many metrics that we we track, you know, things like um the actual actual evidence recall or answer completeness, we see like the agentic retrieval approach continuously does better than than simple that's uh individual simple parts.
就是说，当你需要控制力的时候可以主动选择深入，但当你的场景很清晰时，就该有一套简单易用的系统。在 Foundry IQ 里，这正是我们的核心设计目标之一。我们的做法是把整个系统分层。你可以从最顶层入手，直接去 Foundry 说："嘿，我那边有一堆 PDF 或者图片，你帮我处理掉就行。"然后我们会在底层把所有事情都做好——比如 chunking（切块）、向量化、处理相关性和排序、做 agentic retrieval 等等。而如果你是专家、想要控制权，也完全可以。你可以直接下到技术栈的底层，自己构建 vector index，告诉我们该怎么量化向量，或者控制词法检索（lexical retrieval）等等。这些你都能做，而且是在同一套技术栈里完成的，这意味着随着需求变化，你可以在这个栈里自由上下移动。另外，在核心检索系统之上，我们还引入了一套 agentic retrieval 栈。因为我们发现，对于简单场景，快速的单次检索（single-shot retrieval）就很好用了；但对于更复杂的场景，你确实需要一个系统，能够对数据集里的内容进行反思，在返回结果之前判断我们是否已经满足了输入中所表达的信息需求。当然，我们看到很多类似的模式不断涌现，而问题永远是：这真的有用吗？结果真的更好吗？从我们自己的评测经验来看，对于困难的案例，agentic retrieval 确实能带来差异。在我们追踪的众多指标上——比如实际的证据召回率（evidence recall）、答案完整度（answer completeness）——我们看到 agentic retrieval 这种方法持续优于那些简单的单一组件方案。
[9:54] Pablo
Now, let me show you some of these in action if you can go to laptop. Can we switch to the laptop? There you go. So, here I'm in I'm in Foundry, and uh Foundry is where you you manage your agents, manage models, but also the place where you can manage all the knowledge that you give your agents in order to uh do their jobs. Um when here, you can you can create knowledge bases as the kind of the entry point of energy agents into the knowledge you care about. In this case, I'll create a knowledge base. I have a data set about movies. These are agentic retrieval systems, so I'll give it a model to power the retrieval workflow. And I can say how much effort you want the model to uh to make or the system to make. And this is effectively a trade-off between latency and quality. I can configure a number of other things, but critically, I want to say where the data I want to ground is coming from. And uh I can start from scratch, or in this case, I have a bunch of unstructured data like PDFs and whatnot in in blob storage. I have structured, you know, parquet tables with statistics, and I also want to ground on the web. So, if I take these three steps, and then I save this knowledge base, now I have this asset, this knowledge base that I can connect to an uh Foundry agent right here, and it'll take a second. Uh but also it's a standalone asset that if I have already a harness that I'm using in other in other places, every knowledge base is an MCP server, so you can just connect to it uh without having to write any glue code in the middle. Now, a knowledge base like this has uh you know, has a bunch of parts. Some of them, like uh for example, this uh storage uh content, you usually build indexes uh and you you know, vectorize these things and whatnot. Uh and if you want control over that, like if I if you don't, you can just use it here. But, if you do, let me just switch to Azure and show you the service behind that particular instance.
现在让我给大家实际演示一下，可以切到笔记本电脑吗？好的。现在我在 Foundry 里，Foundry 是你管理 agent、管理模型的地方，同时也是你管理所有知识的地方——这些知识是你提供给 agent、让它们完成工作用的。在这里，你可以创建 knowledge base（知识库），它是 agent 接入你所关心的知识的入口。这个例子里我来创建一个 knowledge base，我有一个关于电影的数据集。这些是 agentic retrieval 系统，所以我要给它指定一个模型来驱动检索工作流。我还可以设置希望模型（或者说系统）投入多大的"努力程度"，这本质上是延迟和质量之间的权衡。我还能配置很多其他东西，但最关键的是，我要指定用来做 grounding 的数据从哪里来。我可以从零开始，或者像这个例子里，我在 blob storage 里有一堆非结构化数据，比如 PDF 之类的；我也有结构化数据，比如带统计信息的 parquet 表；另外我还想基于 Web 做 grounding。把这三步做完，保存这个 knowledge base 之后，我就拥有了这个资产——这个 knowledge base 可以直接连接到 Foundry agent 上，就在这里，稍等一下。同时它也是一个独立的资产：如果你已经在其他地方用着自己的一套 harness，那么每个 knowledge base 本身就是一个 MCP server，你可以直接连上它，中间不需要写任何胶水代码。像这样一个 knowledge base 包含很多组成部分。其中一些，比如存储里的这些内容，通常你会为它们构建 index、做向量化等等。如果你不需要控制这些细节，直接在这里用就行；但如果你想要控制权，让我切到 Azure，给你们看看这个实例背后的服务。
[11:55] Pablo
Where if I go to knowledge bases, this is the knowledge base we just created a second ago. And I can go peek inside. For example, I can go fish out the indexes that back this particular uh piece of content. And in that index, I can see what is the structure of the index. Uh if I'm opinionated about, I don't know, maybe the quantization uh approach I want to use or which indexing algorithm I want for my vectors, I can say all of that. And of course, I can actually go and explore the data. And you know, see what's inside, how chunks were organized, and and whatnot. So, the goal of this is to again give you high product a highly productive environment when you need uh when you don't need uh the sophistication, and when you need it to make sure you have it to get your job done. We go back to slides. And of course, the other aspect of this is, you know, top of mind these days for all of us is token uh is token efficiency. And uh so, uh we carefully evaluate this system to make sure that we give you the most information dense answer that has the fewest tokens uh so that you you know, the the your consumption of tokens has a high value when it comes to all retrieval tasks. The last category of knowledge I wanted to talk about is learned knowledge. Now, learned knowledge is the result of us doing the work we do as individuals and as organizations every day. And the the idea that we can actually observe the processes and get better at them by reflecting and improving every step of it is something that is really uh changed now that we have agents doing the work and we can go tune the agents automatically. Satya wrote about this recently and reflected on the fact that people and agents can really compound in in how they do the work and how they can create this learning loop that effectively captures what's unique about the company or or the organization you're working on and inputs that to work to differentiate the work that you do.
在这里，进入 knowledge bases，就能看到我们刚才创建的那个知识库。我可以进去看看里面的东西。比如，我可以把支撑这份内容的那些 index 找出来。在这个 index 里，我能看到它的结构。如果我对某些细节有自己的主张——比如想用哪种量化方案，或者向量要用哪种索引算法——我都可以在这里指定。当然，我还可以实际去浏览数据，看看里面有什么、chunk 是怎么组织的等等。所以这一切的目标还是那句话：在你不需要复杂性的时候，给你一个高生产力的环境；在你需要的时候，确保这些能力就在那里，让你把活干完。我们切回幻灯片。当然，另一个方面是最近大家都最关心的话题——token 效率。我们对这套系统做了细致的评测，确保在所有检索任务上，我们用最少的 token 给你信息密度最高的答案，让你消耗的每个 token 都物有所值。我想讲的最后一类知识是 learned knowledge（习得知识）。习得知识是我们作为个人和组织每天工作的产物。我们其实可以观察这些工作流程，通过反思和改进其中的每一步来变得更好——这件事在今天发生了根本变化，因为现在是 agent 在干活，而我们可以自动化地去调优这些 agent。Satya 最近就写过这个话题，他谈到人和 agent 可以在工作方式上真正形成复利效应，构建起一个学习闭环——这个闭环能有效捕捉你所在公司或组织的独特之处，并把它注入到工作中，让你做的事情形成差异化。
[13:54] Pablo
Now in Foundry we wanted to offer like a material a materialized version of this that you can use today. So we built a component called the agent optimizer that effectively goes through this process and allows you to evaluate a baseline, generate candidates, and then you know, evaluate the new candidates and we have a strong result, then deploy that to production. Let me give you a kind of a quick flavor of what this looks like if we can switch back to the laptop. All right. So here I'm I mean VS Code, I have the Foundry toolkit installed. And I have a simple agent, it doesn't matter how you write your agent as long as you externalize configuration like you know, your instructions, tool definitions, skills, and whatnot. So once you have one of those, it takes two key steps to do this. So first oops. Um I can actually so usually you have an evaluation already, but if you don't, you can actually say eval generate and what we'll do is we'll look at what we know about the agent like traces and instructions and whatnot and we'll produce a task adherence focused evaluation for you. In this case I run this a little bit earlier. So just to give you a flavor of what this looks like, you you have a bunch of tasks and then you know, the questions and the criteria and whatnot. Once you have a dataset you can evaluate then next step is you can say uh optimize. And uh I could just run optimize on its own and that will run In this case, this run for maybe 45 minutes or so and you get an optimized version by effectively hill climbing the metric that's established from by evaluation. Um so I run this earlier and so let me show you the output for this particular one. Where you can see that, you know, we established the baseline first and then we kept iterating on candidates uh using different combinations using a J power style kind of loop uh and uh looking for options that perform better given uh the rubric that we have. And uh the interesting thing is that once you found one that is that is better, then you can simply just say optimize apply and what this does is since you externalize the configuration, it allows you to swap one configuration for the other. Um if I if if we look here, you can see that for example, I have baseline and the one we just applied. And just to pick on instructions, these are just the uh trivial instructions for this example agent.
在 Foundry 里，我们想提供一个今天就能用的、具象化的版本。所以我们构建了一个叫 agent optimizer 的组件，它就是走这样一个流程：先评估一个 baseline，然后生成候选方案，再对新的候选方案做评估，如果得到了显著更好的结果，就把它部署到生产环境。让我快速给大家展示一下这是什么样子，可以切回笔记本电脑吗？好。现在我在 VS Code 里，装了 Foundry toolkit。我有一个简单的 agent——你怎么写这个 agent 都无所谓，只要你把配置外置化就行，比如 instructions、工具定义、skills 等等。有了这样一个 agent 之后，只需要两个关键步骤。首先——哎呀——通常你手头已经有评测集了，但如果没有，你可以运行 eval generate，我们会分析我们对这个 agent 的了解，比如 trace、instructions 等等，然后为你生成一套以任务遵循度（task adherence）为核心的评测。这个我之前已经跑过了。给大家看看它长什么样：你会得到一批任务，还有对应的问题、评判标准等等。有了数据集、能做评估之后，下一步就是运行 optimize。我可以直接单独跑 optimize，这次运行大概要 45 分钟左右，然后你就会得到一个优化后的版本——本质上是对评测所确立的指标做爬山优化（hill climbing）。我之前跑过了，所以让我给大家看这次运行的输出。你可以看到，我们先建立了 baseline，然后不断迭代候选方案，用类似 GEPA 风格的循环尝试不同的组合，寻找在我们的评分标准（rubric）下表现更好的选项。有意思的是，一旦找到了更好的版本，你只需要运行 optimize apply——因为配置是外置的，它就能直接把一套配置换成另一套。如果我们看这里，可以看到比如有 baseline 版本和我们刚刚应用的版本。就拿 instructions 来说，这是这个示例 agent 原本那些很简单的 instructions。
[16:18] Pablo
But if I look at the optimized one, then you can see like a bunch of instructions that are not handwritten but that that they emerged out of the hill climbing process to get to make this particular um agent better given what we have in terms of instructions and skills and tools, but also based on reflecting on the actual uh traces from the agent as users are using it. So this is a real learning loop materialized in practice. You can go back to slides. So this was like a very quick overview about how do we think about knowledge in the context of AI and how do how we think we can enable these learning loops that will capture, you know, these differentiated capability that lives in each one of the companies and organizations we work on. If you want to try anything of what I talked about or showed today, you can head to ai.azure.com and get going. And with that, thank you all for listening this morning. I hope you have a great rest of the event. Thanks.
但如果看优化后的版本，你会看到一大堆 instructions——它们不是人手写的，而是从爬山优化的过程中自然涌现出来的，目的是让这个 agent 变得更好。这个优化不仅基于我们现有的 instructions、skills 和工具，还基于对用户实际使用过程中 agent 产生的真实 trace 的反思。所以这是一个真正落地的学习闭环。可以切回幻灯片了。以上就是一个很快速的概览：我们如何在 AI 的语境下思考"知识"这件事，以及我们认为如何才能构建这些学习闭环——它们能捕捉存在于每一家公司、每一个组织里的差异化能力。如果你想试试我今天讲到或演示的任何东西，可以去 ai.azure.com 上手。最后，感谢大家今天上午的聆听，祝大家接下来的大会愉快。谢谢。