Multimodal Collaborative Agents for Next-Gen Commerce — Nidhi Kaushik Vyas, Google DeepMind

频道: AI Engineer
视频: https://www.youtube.com/watch?v=AhQpRalYlyg
原文语言: en
统计: 共 21 轮 · Nidhi 19 · 观众 1

[0:13] Nidhi

Okay, good morning folks. Thank you for showing up. I'm Nidhi. I'm a product person at Google DeepMind. And today I'll be talking about multimodal collaborative agents. Typically, these are agents that work with fuzzy intent intent when the intent when it's not clear the user hasn't gotten the right keywords to specify and when they come in for a shopping intent, how can you have the agents still guide the user towards their goal with high agency execution, proactive elicitation, and a lot of hand-holding. The framework that we'll be discussing today are grounded in shopping or commerce because I wanted to show you a few patterns that are much easier to see in commerce, but they're quite applicable in other consumer verticals as well, finance, education, or whatever you guys work on. Um Yeah, so before we even start into the frameworks, I wanted to discuss about why this is an existing problem.

好，大家早上好，谢谢各位到场。我是 Nidhi，在 Google DeepMind 做产品。今天我要讲的是多模态协作式 agent。这类 agent 通常要应对的是模糊意图——也就是意图还不清晰、用户还没找到合适的关键词来表达的时候。当用户带着购物意图进来，怎样让 agent 依然能把用户一步步带到目标上？靠的是高自主执行、主动引导用户说出偏好，外加大量手把手的带领。今天讨论的框架都立足于购物，也就是电商场景，因为有几个模式在电商里看得最清楚，不过它们同样适用于其他消费类垂直领域，比如金融、教育，或者你们各自在做的方向。嗯，那么在正式进入框架之前，我想先聊聊为什么说这是一个现实存在的问题。

[1:05] Nidhi

Currently, a lot of the agents that we have act more like a wrapper to the search bar. They assume that the user has a well-defined intent, has the right keywords, already knows what they're looking for. And so when they come in, they just have the right vocabulary to interact with the agent. However, there is quite a huge articulation gap. When the users come in, rarely they have their intent well formed. Rather, they kind of have a fuzzy feeling or a vibe when they are kind of looking to shop. So, the agent needs to play quite a huge role in hand-holding them. They need to work with the user in first understanding their preferences or even eliciting these preferences more proactively. And then helping the user kind of show them different possibilities of what could be possible that they can shop and then eventually move towards kind of recommendations that work with these constraints that they have in mind. So, what we're going to be discussing is this kind of a flywheel or a loop that goes from very, very fuzzy intent all the way towards kind of achieving the user's goal.

现在我们的很多 agent，更像是给搜索框套了一层壳。它们默认用户意图明确、手里有对的关键词、早就知道自己要找什么，所以用户一进来就能用恰当的词汇跟 agent 交互。可实际上，这里存在相当大的表达鸿沟。用户进来时，意图很少是成形的；更多时候，他们想买东西时心里只有一种模糊的感觉，或者说一种 vibe。所以 agent 需要在手把手带用户这件事上扮演很重的角色。它得和用户一起，先弄明白他们的偏好，甚至更主动地引导用户把偏好说出来；接着帮用户看到各种可能性，给他们展示有哪些东西可以买；最后再一步步走向符合他们心中那些约束条件的推荐。所以我们接下来要讨论的，就是这样一个飞轮，或者说一个循环：从非常非常模糊的意图出发，一路走到达成用户的目标。

[2:15] Nidhi

So, this is how the shopping loop looks like right now. The very first thing that the agent prepares for when the user comes in is what we call the discovery phase. This is where the where the agent takes all the different contextual information that they have about the user. This could be past conversations, what the user has specified in their query. It could be information present in their personal context, or even the references that the user have provided. And then comes up with a collaborative strategy, and we'll be going to the details of this, but it comes up with a collaborative strategy on what more does the agent need to elicitate back from the user in order to help get the intent in a better shape, to get clarity on what exactly the user is looking for. And then it moves to the second phase, which is what we call the research phase. Which is again a two-step process. First is where it learns what is the best way to elicitate this preference. So, for example, a lot of times the text the text base elicitation may not be the best way to get the preferences from the user because sometimes a user don't know what they're looking for. So, then how can the agent start being more creative in terms of elicitating these preferences? Can they start using some kind of visual references or visual visual inspiration boards for grounding and speaking a common language with the user? And then the second phase to this is also coming up going into the background and doing the heavy lifting for the user, so taking the burden away from the user to describing what they want, and rather going into the background and doing all the comparisons, trade-offs,

那么，这就是目前这个购物循环的样子。用户进来之后，agent 首先要准备的，是我们所说的发现阶段。在这个阶段，agent 会调取它掌握的关于这位用户的各种上下文信息：可能是过去的对话、用户在 query 里明确提出的内容，也可能是用户个人上下文里的信息，甚至是用户提供的参考资料。然后它会制定一个协作策略——具体细节我们稍后展开——也就是想清楚：agent 还需要从用户那里引导出哪些信息，才能让意图更成形，搞清楚用户到底在找什么。接着进入第二个阶段，我们称之为研究阶段。这同样分两步走。第一步是摸清引导用户说出这项偏好的最佳方式。比如说，很多时候纯文字的引导并不是获取用户偏好的最好办法，因为有时用户自己都不知道自己在找什么。那 agent 怎样才能在引导偏好这件事上更有创意？能不能用一些视觉参考或视觉灵感板，来锚定讨论、和用户说同一种语言？这个阶段的第二部分，是 agent 转到后台替用户干脏活累活——不再让用户费劲描述自己想要什么，而是自己在后台去做各种比较、权衡、

[3:44] Nidhi

summarization of all the information that they're looking for, and coming back with the right set of potential options for the user. And then the third phase, once um the user and the agent is ready to go into some kind of a is ready to go into the last phase, which is where um the agent is ready to give out a response. This is where the agent needs to start adapting the response in a way that is most useful for the user. So, typically a lot of systems fail here where they just give out a text-heavy response. What the agent should rather be doing is adapting to the query that the user had in mind. So, should it be using um some kind of a bulleted list? Should it be using comparison tables? Should it be using um visual boards? So, this is where the there's adaptive response happening as well, where the uh agent starts to develop uh more more of a uh smarter uh presentation skills uh for the user to really find the answer that they're looking for. So, we'll be diving into all these topics as I uh kind of work through the presentation.

把用户要找的所有信息汇总起来，然后带着一组合适的备选方案回来交给用户。接下来是第三个阶段：当用户和 agent 都准备好进入最后一个阶段，也就是 agent 准备给出回复的时候，agent 就需要开始调整回复的形式，让它对用户最有用。很多系统通常就栽在这一步——只会甩出一大段满是文字的回复。agent 真正该做的，是根据用户心里想问的那个 query 来调整：该用要点列表吗？该用对比表格吗？还是该用视觉看板？所以这里还有一个自适应回复的过程，agent 要逐步练出更聪明的呈现能力，好让用户真正找到他们想要的答案。接下来我讲的过程中，会把这些话题一一展开。

[4:43] Nidhi

So, first and foremost, we're looking at discovery. Like I was mentioning, this is where uh the the the agent needs to remember what exactly matters. Um you the agent starts to look at the context across a bunch of different signals. It starts to look at past conversations. It looks at some of the reference images or reference links that the user might have provided. It also starts to look at personal context and starts to build out a working state. So, if you look at the sample code that we have here, like there is there is a goal uh one of the let's let's work with this query where the user is trying to redo their living room with a certain budget in mind. And some of the um some of the things that the agent develops as part of the working state is the session history. It has a user context. It also kind of extracts out the hard constraint that the user might have provided in the query.

那么首先，我们来看发现阶段。就像我刚才说的，在这个阶段，agent 要记住真正要紧的东西是什么。agent 会综合一系列不同的信号来看上下文：它会看过去的对话，看用户可能提供过的参考图片或参考链接，还会看个人上下文，然后开始构建一个工作状态（working state）。大家看这里的示例代码，有一个目标——我们就拿这个 query 来举例：用户想在一定预算内改造自家客厅。agent 构建工作状态时会生成的内容包括会话历史，还有用户上下文，另外它还会提取出用户可能在 query 里给出的硬约束。

[5:30] Nidhi

But, things start getting getting interesting when we come to the softer constraints. So, this is where the user may not be able to describe what they're looking for and may might have provided like a reference image on, you know, an inspiration that they had in mind or some kind of a layout design that they really liked and is trying to get to the agent in terms of uh this is what speaks more to me. So, this is where the agent starts to be more proactive and pulls out some of the salient signals from the from the reference images and starts to develop a mental model of what the user might really be looking to get at. So, here the user is uh so the agent has specified uh has identified that maybe the style that is working out well for them is of a certain kind. It also uh is also is also starting to work towards a confidence score on like how confident it is in terms of pulling out some of this information present in the multimodal inputs provided. And then the last thing uh that happens as part of developing this working state is also figuring out what are the variables that the agent needs to pull out almost in real time because these variables uh this variables do affect how the results will be displayed back to the user. This could be variables that need to be refreshed in real time like uh inventory because if if what you're providing back to the user is stale information, then it's kind of a moot point. So, these are the uh these are the variables that you want to refresh in real time and is and becomes a part of the agent's working state.

不过，到了软约束这块，事情就开始变得有意思了。这种情况下，用户可能说不清自己想要什么，可能会给一张参考图，比如他们心里的某个灵感来源，或者某个特别喜欢的布局设计，想借此告诉 agent：“这个更对我的胃口。”这时 agent 就得更主动一些，从参考图里提炼出一些显著信号，开始构建一个心智模型，揣摩用户真正想要的到底是什么。比如在这里，agent 识别出某一类风格可能比较适合这位用户。同时它也在得出一个置信度分数，衡量自己从用户提供的多模态输入里提取出这些信息有多大把握。构建工作状态的最后一件事，是想清楚哪些变量需要 agent 几乎实时地去拉取，因为这些变量确实会影响结果怎么呈现给用户。比如库存这类需要实时刷新的变量——如果你返回给用户的是过时信息，那就等于白搭。所以这些就是你需要实时刷新的变量，它们也会成为 agent 工作状态的一部分。

[6:51] Nidhi

Um few ways that you can evaluate this state uh the way we have developed our auto raters, we we do make sure that all facts are retained meaning that whatever was mentioned in the part of uh whatever was mentioned in part of the context is properly represented in the working state. We also capture if the confidence collaboration was within a certain error bound because uh the agent needs to be able to confidently pull out these signals from the input. We also focus on getting out um the counterfactual sensitivity uh counterfactual sensitivity. So, we do this by flipping some parts of the queries and making sure that when the query changes, the underlying constraints pulled out by the agent the those also change and the ones that are not relevant stay the same. So, we kind of want to measure the sensitivity both ways. And then the second part that happens in the discovery phase as well is once the agent knows what they have what they already know about the user what more do they need to know about the user. So what we call this what we call this is kind of discovering the intent gap.

评估这个状态有几种方式。按我们搭建 autorater（自动评分器）的做法，我们会确保所有事实都被保留下来，也就是说，上下文里提到过的任何内容，都要在工作状态里得到准确体现。我们还会检查置信度校准是否落在一定的误差范围内，因为 agent 必须能有把握地从输入里提取出这些信号。我们还关注反事实敏感度。具体做法是翻转 query 中的某些部分，确保 query 变了之后，agent 提取出的相应底层约束也跟着变，而不相关的约束保持不变。所以我们希望从两个方向来衡量这种敏感度。发现阶段里还有第二部分：agent 知道了自己对用户已经掌握了哪些信息之后，还要弄清楚它还需要再了解用户什么。我们把这一步称为发现意图缺口。

[7:55] Nidhi

There's a lot of times that there are a lot of unknown variables before the agent can provide the best answer and amongst all these unknown variables the agent doesn't need to go and find all the unknown variables up front. So what I mean by that is in this unknown in in our working example some of the unknown variables that the agent said they need to find out more about is maybe knowing what the room width would be for the user or even kind of working on improving the confidence for the style before they can recommend back the results. Now once these unknown variables are figured out the agent also needs to work on a collaborative strategy compare all the different moves possible and then figure out what is that one unknown variable that it should prioritize such that it has the maximal information gain at that point. So in this case I mean one could argue that maybe finding out the room width is the best next move for the agent because if the products that the the agent is recommending doesn't fit into the room then again it's a moot point and that is one variable that is going to meaningfully change the the direction of the conversation and that's what the agent works on in this step kind of figuring out what's the best next thing to ask to the user and what's why is that the best next thing to ask as well. Once it has okay so I'll go ahead into the auto data section on like why how do we evaluate this collaborative strategy we first focus on making sure that the agent is able to identify all the different blockers that are needed to be answered before the agent can come back with meaningful responses. We also work towards making sure that the agent is um optimal in trying to get some of these responses so we also don't want to have the agent constantly going into the loop and continually continuously asking these questions so over asking is definitely something we flag. We also work on question utility. So, again, how optimally is the question being asked?

很多时候，在 agent 能给出最佳答案之前，存在大量未知变量，但 agent 并不需要一上来就把所有未知变量都搞清楚。我的意思是，在我们这个示例里，agent 认为需要进一步了解的未知变量，可能是用户房间的宽度，或者是在推荐结果之前，先把对风格判断的置信度提上去。梳理出这些未知变量之后，agent 还需要制定协作策略：比较所有可能的下一步动作，然后找出应该优先处理的那个未知变量，让它在那个时间点带来最大的信息增益。在这个例子里，可以说弄清房间宽度也许就是 agent 最好的下一步，因为如果 agent 推荐的商品根本放不进这个房间，那又是白搭；而且这个变量会实质性地改变对话的走向。这就是 agent 在这一步要做的事：想清楚下一步最该问用户什么，以及为什么这是最该问的问题。一旦它有了——好，那我直接进入 autorater 这部分，讲讲我们怎么评估这个协作策略。首先，我们要确保 agent 能识别出所有必须先得到回答的卡点，这样它之后才能给出有意义的回复。我们还要确保 agent 在获取这些回答时做到最优——我们不希望 agent 老在循环里打转，没完没了地反复追问，所以过度追问绝对是我们会标记出来的问题。我们还会看问题效用，也就是说，这个问题的提问方式是否最优？

[9:42] Nidhi

Is the question indeed useful to get the right or elicit the right preference from the user? And many more. Okay. Moving on. The The second part that I was mentioning is the multimodal elicitation. This is where the research phase happens. So, play along, but like let's say the the agent has asked about the room width, the user has provided the response, and then the agent goes to the next step, which is where the agent is asking about the next constraint that it needs to know about is what was the style preference of the user. Now, the first first thing that the agent needs to do is kind of form this temporary bridge between the constraint itself and how that maps back to the the product catalog and the ontology in your knowledge knowledge database. And this is going to be important because when you start retrieving these products, you want to have a way to map these constraints back to your knowledge base. So, this almost happens in real time where we map the known constraint or the constraint that the agent is exploring back to the knowledge database. We also work towards um figuring out We also work on like the agent knowing what is the best way to get the response for this constraint as well. So, in this case, the agent has decided that maybe since this is this kind of a subjective constraint, the textual the actual elicitation is not the best way to do this. So, one of the ways that the agent thinks this could this could be elicited back from the user is using some kind of a visual preference board.

这个问题是否真的有助于从用户那里拿到——或者说引导出——正确的偏好？诸如此类，还有很多。好，我们继续。我刚才提到的第二部分是多模态引导，这正是研究阶段发生的事。大家跟着我想象一下：假设 agent 已经问过房间宽度，用户也回答了，然后 agent 进入下一步，去问它需要了解的下一个约束，也就是用户的风格偏好。这时 agent 首先要做的，是在约束本身和你知识库里的商品目录与本体之间，搭起一座临时桥梁，明确这个约束怎么映射过去。这一点很重要，因为当你开始检索商品时，你需要有办法把这些约束映射回你的知识库。所以这几乎是实时发生的：我们把已知的约束，或者 agent 正在探索的约束，映射回知识库。我们还会让 agent 弄清楚，针对这个约束，用什么方式获取用户的回答最好。在这个例子里，agent 判断，由于这是一个偏主观的约束，文字式引导并不是最好的办法。所以 agent 认为，从用户那里引导出这项偏好的方法之一，是用某种视觉偏好板。

[11:17] Nidhi

So, the agent then goes back to determining what is the best form of options to show to the user. This could be a combination of figuring out from the existing constraints, the past conversation, and then the temporary mapping that you've created from the constraints back to your product ontology. So, in this case, the the agent thinks that maybe coming up with a few styles that are most similar to what the user had provided as reference image could be a good way to start thinking or guiding the user towards a common language on what could be uh something that the user is interested in. And then the the then the agent also goes into kind of um observing the space of what kind of reactions the user is giving. So, it could start looking at these micro signals of if there was a hover or a click in a certain direction and starts updating its its confidence model on what kind of signals uh what kind of signals can be used to im- improve the confidence in like what could be the style preference for the user.

于是 agent 接着去判断，用什么形式的选项展示给用户最好。这可以综合已有的约束、过去的对话，以及你之前建立的那套从约束到商品本体的临时映射来决定。在这个例子里，agent 认为，挑出几种和用户所给参考图最相近的风格，也许是个不错的办法，可以由此开始琢磨、或者说引导用户和 agent 形成共同语言，弄清用户可能对什么感兴趣。接下来，agent 还会观察用户给出了哪些反应。它可能会关注一些微信号，比如用户有没有在某个方向上悬停或点击，然后据此更新自己的置信度模型，判断哪些信号可以用来提升它对用户风格偏好判断的置信度。

[12:14] Nidhi

Um some of the auto raters we use here, we do look at how efficient the how efficient the agent is in discovering hidden preferences. So, typically, we would use a user simulator, feed it with some constraints, and then we'll see how how efficient the agent was in kind of eliciting some of these constraints. We also focus on turn efficiency. So, how efficient was the user in how many turns did it take for the user to be able to to be able to uncover all these hidden preferences. Ideally, we don't want the user to go into this loop and keep asking the same questions again and again and again. Or also, we don't want to go into the loop of asking some um some questions which may not give you the best uh which may not give you the best information required to proceed the conversation. And then we also look at forma- format selection accuracy. So, we typically also look for if the agent is asking the right right question in the right format. So, for example, if the if the question was something that was easily statable, the right format could be a textual elicitation. But if if this was more of a fuzzy question where the user is clearly having an articulation gap and is not able to describe the preference, maybe the best way to do this is speak a common language and come up with some visual anchor points for the user to say what speaks more to them.

我们在这里用到的一些 autorater，会看 agent 发现隐藏偏好的效率有多高。通常我们会用一个用户模拟器，给它设定一些约束，然后看 agent 把这些约束引导出来的效率如何。我们也关注轮次效率，也就是用户要经过多少轮，才能把这些隐藏偏好全部挖出来。理想情况下，我们不希望让用户陷进这种循环，同样的问题反反复复问了一遍又一遍；也不希望陷进另一种循环，老问一些拿不到推进对话所需最佳信息的问题。然后我们还会看形式选择准确率，通常就是看 agent 有没有用对的形式问对的问题。比如，如果这个问题很容易说清楚，合适的形式可能就是文字引导；但如果这是个比较模糊的问题，用户明显存在表达鸿沟、描述不出自己的偏好，那最好的办法也许是和用户说同一种语言，给出一些视觉锚点，让用户说说哪个更对他们的胃口。

[13:29] Nidhi

Um Yeah, so then the last step in this process, once the So, to recap like basically the Now the agent knows exactly what they what the user is looking for. The agent has identified a collaboration strategy, has figured out all the preferences for the user, and knows what is going to be most optimal in terms of um the different priorities for the user. The last step in this process is to also use the model intelligence to figure out what is the best way to provide this response back to the user. So, in this working example, we found out that the agent knows what the style preference is, has figured out that the user is looking to buy products under a certain budget, and knows what are the different dimensions along which it needs to find uh these products for because through the conversation they figured out some of the different um different metadata information that is going to be relevant to surface when they're giving out this product information back to the user.

嗯，好，那么这个流程的最后一步，一旦……先回顾一下，基本上……现在 agent 已经确切知道用户在找什么了。agent 已经确定了协作策略，摸清了用户的所有偏好，也知道结合用户的各项优先级，怎样才是最优的。这个流程的最后一步，是同样借助模型的智能，去判断怎样把回复呈现给用户最好。所以在我们这个示例里，可以看到 agent 已经知道了用户的风格偏好，搞清楚了用户想在一定预算内买东西，也知道需要沿着哪些维度去找这些商品——因为通过对话，已经弄清楚了在把商品信息反馈给用户时，有哪些元数据信息是值得展示出来的。

[14:21] Nidhi

So, the one one important step that happens at this this stage is figuring out what's the best way to surface back this response. So, for example, like if the user was looking for a particular policy or review information about a particular product, maybe the best way to do this is to go give out a summary or a bulleted list. But if the if the user was looking more towards comparing two different products, maybe the best response is to give out a trade-off table or a comparison table across the different axis that the user cares about. Um and in case that in our example where the user was looking more towards kind of style inspiration or ideas on how they can kind of redo their room, then maybe the best way is to give out some visual references and product inspiration photos on like how What are the different options and possibilities uh for the user to uncover. So, some other ways that we focus on evaluating uh this stage is focusing on the format accuracy. So, we want to make sure that the response format is kind of optimal for the user query so that they they find out exactly what they're looking for.

所以，这个阶段有一个很重要的步骤，就是想清楚用什么方式把这个回复呈现回去最好。举个例子，如果用户想了解某个商品的某项政策或评价信息，最好的方式可能是给一段摘要或者一个要点列表。但如果用户更想比较两款不同的商品，最好的回复可能就是给出一张权衡表或对比表，按用户在意的各个维度逐项对比。嗯，而在我们这个例子里，用户更多是在找风格灵感，或者想看看怎么重新布置自己的房间，那最好的方式可能是给出一些视觉参考和商品灵感图，看看……有哪些不同的选项和可能性可供用户去发掘。我们评估这个阶段还有其他几个侧重点，其中之一是格式准确性。也就是说，我们要确保回复格式对用户的这个查询来说是最合适的，让用户能准确找到他们要找的东西。

[15:22] Nidhi

Uh ideally the information that they're looking for should not be buried in the response, but should be easy for the user to spot so they can come into the next stage in the intent journey, which is to basically buy the product. We also look at data fidelity, which is to make sure that the model is not hallucinating and it's really capturing the information in the correct format in the you know, the the information is just accurate and is captured across the response. We also look at user actionability. So, this is ensuring that the response format is such that the user is very confident and and commits to the next action, which is like I said, the action to purchase the product. So, just to recap so far, what we have is um you want to design the product. Um you want to you want to design the product such that you're prepared to accept vibes, like I say. So, that is to say that users will come with fuzzy intent. Users will not have a well-defined goal. So, you want to make sure that your system is able to work through queries that are not clean.

呃，理想情况下，用户要找的信息不应该被埋在回复里，而应该让用户一眼就能看到，这样他们才能进入意图旅程的下一个阶段，基本上也就是购买商品。我们还会看数据保真度，也就是确保模型没有产生幻觉，确实以正确的格式抓取了信息——你懂的，就是信息本身准确无误，并且在整个回复里都完整地体现出来。我们还会看用户可行动性，也就是确保回复的形式能让用户非常有把握，并且下定决心采取下一步行动——就像我说的，这个行动就是购买商品。那么，先回顾一下到目前为止讲的内容：嗯，你要设计产品。嗯，你要把产品设计成随时准备好接住 vibes，就像我说的。也就是说，用户会带着模糊意图而来，他们不会有一个定义清晰的目标。所以你要确保你的系统能够处理那些不干净、不规整的查询。

[16:21] Nidhi

Um the second takeaway is you want to focus on showing and asking rather than always asking with textual textual with textual elicitations. Again, like visuals and comparisons do reveal preferences much much faster. It allows you the agent and the user to speak a common language. Third one I would say is shape the answer. So, do focus on making sure that the presentation format is ideal for the user being able to find the right information. Um the way you have the model response structure is also very much part of the intelligence. And then the last one is make sure that you grade the loop. You have the right auto rater set up on every step of the process. Um and honestly, developing these auto raters is a is is almost like an evolving system. It starts very simple, but as and when you start the the system starts evolving, you want the auto raters to kind of gradually grow with your system and start um yeah, it which just gradually grow with your system.

嗯，第二个要点是，要侧重“边展示边提问”，而不是总靠纯文字去引导用户说出偏好。还是那句话，视觉素材和对比确实能快得多地揭示出偏好，它能让 agent 和用户讲共同的语言。第三个，我会说是“塑造答案”。也就是一定要注重呈现形式，确保它最便于用户找到正确的信息。嗯，你怎么组织模型回复的结构，本身也是智能很重要的一部分。最后一个是，一定要给整个闭环打分：在流程的每一步都配好合适的 autorater。嗯，说实话，开发这些 autorater 几乎就像是一个不断演进的系统。它一开始非常简单，但随着系统开始演进，你会希望 autorater 也跟着你的系统逐步成长，开始……嗯，对，就是跟着你的系统逐步成长。

[17:17] Nidhi

So, that's all I had. Um I can take a few questions, but hopefully the learnings we shared are useful for whatever you folks are building. Yeah. Yeah. Yeah. Yeah, great question. So, the question is about what should the how should the ontology be structured on the merchant side so that it's fair both for the agent and the merchants. So, yes, we do take a lot of advantage on the domain expertise of the merchant on as to what they're trying to sell and like we do work towards creating So, you remember how I was mentioning about the bridge between the constraints that the user might have specified and then what the agent kind of understands. That is where we do expect a lot of intelligence to flow from the merchant side where the ontology on how that constraint could map to the different metadata that the agent has. Sorry, the that the merchant has maps in. So, yes, we do partner a lot and then there's also like the UCP stuff that we launched recently which allows all the merchants to kind of start speaking the common language with the agent as well.

我要讲的就这些。嗯，我可以回答几个问题，希望我们分享的这些经验对大家正在做的东西有所帮助。好，好，好。对，好问题。问题是：商家那一侧的本体（ontology）应该怎么构建，才能对 agent 和商家双方都公平。所以没错，在商家想卖什么这件事上，我们确实大量借助了商家的领域专长，而且我们也在努力打造……大家还记得我前面讲到的那座桥吧，就是连接用户可能提出的约束条件和 agent 所理解的内容之间的那座桥。正是在这个环节，我们确实期待有大量智能从商家那一侧流入，也就是由那套本体来描述某个约束条件该如何映射到 agent 所拥有的各种元数据上。抱歉，是映射到商家所拥有的元数据上。所以是的，我们确实和商家有大量合作；另外还有我们最近推出的 UCP 那一套，它能让所有商家也开始和 agent 讲共同的语言。

[19:20] Nidhi

Yeah, so ideally, I mean, honestly right now we focus on making sure all of this flows back to the agent and the agent makes the decisions because you want to build like a horizontal common layer across all the different merchants. So, and also like it should be a seamless experience for the for the user who's interacting with our apps. So, right now the response format is very much part of the agent's intelligence. It is not something that the merchant gets to decide. Yeah. Yes.

对，所以理想情况下——我是说，老实讲，目前我们的重点是确保所有这些信息都回流到 agent，由 agent 来做决策，因为你想搭建的是一个横跨所有不同商家的横向通用层。而且，对正在使用我们应用的用户来说，这也应该是一种无缝的体验。所以目前，回复用什么格式完全属于 agent 智能的一部分，不是由商家来决定的。好。请讲。

[19:47] 观众

I'm just curious your opinion what happens when your user is not a user anymore, it's an agent.

我就是好奇你怎么看：如果你的用户不再是用户，而是一个 agent，会发生什么？

[19:53] Nidhi

That's a great question. We're in the early stages of building this out, but I think I mean there could be a case where um Yeah. Yeah, yeah, exactly. So, yeah, I would I would expect like an MCP to be the interface between the two for sure. Honestly, we haven't gotten to a point where we have agents interacting with our agents just yet. Also, like what we've realized at least from our user studies is users really like to be more involved in the process of choosing or even exploring the different possibilities. So, during the upper funnel journeys where users is looking more towards discovery, inspiration, that is where they would rather be interacting with the system than with their agent. I think where the agent typically comes in or even where what we've heard is like the was the lower end of the journey where they're just looking to compare or negotiate or compare prices across different merchants, but very much up there in the funnel, it's the users who kind of interact more with our systems. So, yeah.

这个问题很好。这块我们还处在早期搭建阶段，不过我觉得——我是说，可能会有这样一种情况，嗯……对。对对，没错。所以，是的，我肯定会预期由类似 MCP 这样的东西来充当两者之间的接口。说实话，我们还没发展到有别的 agent 来和我们的 agent 交互的阶段。另外，至少从我们的用户研究里我们意识到，用户其实很喜欢更多地参与到挑选、甚至探索各种可能性的过程中。所以在漏斗上层的旅程里，用户更多是在做发现、找灵感，这时候他们更愿意直接和系统互动，而不是和自己的 agent 互动。我觉得 agent 通常介入的地方——或者说我们听到的反馈是——在旅程的下游，也就是用户只是想在不同商家之间做比较、议价或者比价的时候；但在漏斗靠上的阶段，基本上还是用户自己在更多地和我们的系统互动。嗯，就是这样。

[20:46] Nidhi

Yeah, I think yeah, I can take questions outside, but thank you folks for coming.

好，我想……对，大家有问题的话我可以到外面再回答，谢谢各位的到来。

[21:05]

[music]

（音乐）