应对多代理协作的瓶颈
早上好，伦敦。我是 Edo Salomon，Agent Craft 的创造者。我同时也是 MC I 的创造者，以及 MC apps 的创造者和共同维护者。我正在构建 David 之前谈论过的一些东西。正如大家在过去一天中所听到的，代理（agents）非常强大。但如果一个代理已经如此强大，为什么我们不扩展到 10 个、20 个或 100 个不同的代理，从而变得强大 100 倍呢？这很简单，我们只需要启动一堆代理，将它们放在一个漂亮的界面里，看起来非常辉煌。但实际上它不会奏效。原因在于，启动它们本身不是问题。问题是我们。我们是协调所有这些代理的瓶颈。现在，如果你仔细想想，工程师去管理几十个失控的“员工”的角色，通常不是我们在大多数公司里做的事情。所以，我们需要找到这些新的、潜在的新技能来管理所有这些代理。幸运的是，它们并不是全新的。这不是我们从未做过的事情。它只是隐藏在意想不到的地方。我的意思是，如果你是一个玩家，或者曾经玩过游戏，管理几十个单位听起来可能有点熟悉。
在理解了多代理协作的根本挑战后，Agent Craft 应运而生，它通过借鉴游戏领域的经验，为提升人机协作效率提供了创新的解决方案。
Original English
So, good morning London. My name is Edo Salomon. I'm the creator of Agent Craft. I am also the creator of MC I and creator and co-maintainer of MC apps. So, I'm building some of the stuff that David has been talking about. As you've all heard in the past day, agents are amazing. But if one agent is so amazing, why don't we scale up to 10 or 20 or 100 different agents and be 100 times more amazing? It is pretty simple. We just spin up a bunch of agents. We put them in this like nice screen and it looks really glorious. But it won't actually work. And the reason is that spinning in them up isn't a problem. It's us. We are the bottleneck in orchestrating all of these agents. Now, if you think about it, the role of the engineer to actually go and manage dozens of reckless employees is not typically what we do in most companies. So, we need to somehow find these new potentially new skills to manage all of these agents. Luckily, they're not really brand new. It's not something that we've never done before. It's just something that's been hiding in unexpected places. I mean, if you're a gamer or used to play games at any point, managing dozens of units probably sounds a little bit familiar. Which is why I built Agent Craft, which is an orchestrator that aims to raise the ceiling of human agent collaboration by taking learnings from gaming and transferring them into productivity.Agent Craft：可视化与追踪代理工作流
所以，这就是 Agent Craft。有很多内容需要深入探讨，所以我们先从基础开始。这是一个代理（agent）。不是比喻意义上的。这实际上是一个编码代理的物理体现，就像一个实时会话。它可以是一个光标，可以是云代码、Code X、Open Claw，或其他任何东西。它是我们可以在设备上检测并可视化的东西，但它也可以直接从这里生成。所以，现在我们有了这个代理，并且可以提示它。我们可以像使用我们 CLI 或其他工具中的任何其他代理一样使用它。我们可以告诉它做什么？它拥有所有这些特性。我们有语音、文本、图像等等。我们可以直接告诉它做事情。例如，我们可以让它为我们开发某个功能。现在代理正在工作，它正在做它的工作。所以，它正在工作，正如你所看到的，如果你看 UI，还有很多其他的东西。我们有这些“建筑”，每个建筑代表某种功能。例如，其中一个建筑管理着技能和插件等。还有集成的终端，可以实现端到端的整个工作流。提升天花板的第二部分，在掌握了基础知识后，就是可见性。我们需要能够快速理解每个代理正在做什么。所以，我们这里有一个漂亮的侧边栏，它真正向我们展示了高层级的任务状态摘要等。它们到底在做什么？但 Agent Craft 的酷之处在于，我们不仅仅是看到一个它们能做什么的列表。我们实际上可以看到它们在工作。所以，如果我们看地图，你会注意到它实际上是我文件系统的投影。我的文件系统的每个部分实际上都在地图上。所以我在这里有这些目录，每个目录都有文件。这些文件被表示为房间，正如你在这里看到的。所以我可以实际跟踪并直观地看到代理正在处理什么，哪个文件。我可以看到在那里发生的所有更改列表。而且因为我们在编排它，我也知道是哪个代理在何时做了什么。所以，我们可以拥有完整的操作流程。我们可以更进一步。如果我知道所有这些东西，为什么不创建一个热力图呢？我可以尝试可视化碰撞，甚至可以主动预防它们。
在建立了对 Agent Craft 核心机制和可视化能力的认知后，下一步是深入探讨它如何通过增强代理自主性来进一步优化工作流。
Original English
So, this is Agent Craft. There's a lot to unpack. So, we'll just start with the basics and go from there. This is an agent. Not a metaphorical one. This is actually a physical manifestation of a coding agent like a live session. It can be a you know, cursor. It can be cloud code, code X, open claw, whatever. It's something that we can detect on the device and visualize it, but it's also something that we can spawn directly from here. So, now we have this agent and we can prompt it. We can use it like just any other agent that we have from our CLI or whatever. And what can we tell it to do? It has all of these quirks. You know, we have voice and we have text and we have images and so on. We can just tell it to do stuff. So, for example, we can tell it to develop some feature for us. And now the agent is working. So, it's doing its work. So, it's doing work and as you can see, if you look at the the the UI, there's like a bunch of other stuff. We have these buildings and each building represents some functionality. So, for example, you know, one of these buildings manages the skills and plugins and so on. There's also, you know, like integrated terminal and get just to like get that end-to-end workflow. The second part of raising the ceiling that we have the basics is visibility. We need to be able to quickly understand what each agent is doing. So, we have this nice side panel here that really shows us like high-level mission status summary and so on. What are they actually doing? But the cool thing about Agent Craft is that we don't just see a list of what they can do. We can actually see them working. So, if we look at the map, you would notice that it's actually a projection of my file system. Each part of my file system is actually on the map. So, I have these directories here. And each one of these directories has files. These files are represented as rooms, as you can see here. So, I can actually track and see visually what the agent is working on, which file. I can see the entire change list of what happened there. And because we're orchestrating it, I also know which agents did what and when. So, we can have full lineage of what's going on. And we can take this one step further. If I know all of these stuff, why not just create a heat map? I can actually try and see visualize collisions and I can even prevent them proactively.提升代理自主性与工作流自动化
现在，这里很酷的一点是，一旦我们有了这种可见性，我们还没有完全完成，因为我们仍然需要能够对正在发生的变化做出反应。所以，我们可以借鉴 RTS 游戏的另一个很酷的机制。我们可以简单地利用肌肉记忆来快速切换那些需要我们帮助的代理。它们需要我们批准计划，需要我们回答一些问题等等。所以，现在我们有了可见性，并且可以快速做出反应。所以，我们完成了，我们解决了编排问题。但并非完全如此，因为这真的只是第一步。我能够并行使用更多代理，但只能在很短的时间内。这有几个原因。第一个原因是，在任何给定时间，我头脑中能有的想法数量是有限的，否则会感到疲倦。所以，我所做的就是基本上告诉代理去做。我告诉它们，“好的，为我找到要做的任务。”所以，我现在有了任务，我可以点击一个按钮，它们就会去做任何事情。它们可以重构、测试所有我不想做的事情。第二个原因是，所有这些“照看”工作都花费了大量时间。我需要看到发生了什么，我能很快地做出反应，但我仍然需要切换。所以，我所做的就是说，“我如何尽可能地将自己排除在等式之外？”所以，如果代理如此强大，为什么不让它们去做呢？我可以给它们一些想法。我有一个“战役”功能。大致说明我想要发生什么，然后我就会启动一个容器。我会让代理在那里运行。它们可以分解任务，可以规划，可以向我展示计划。我不在乎它们在做什么，因为是在容器里，所以随便它们。这里的主要事情是，一旦它被分解，我就不必进行“照看”了。现在，我有“战役编排器”，那是他的问题。所以，我们实际上将更多的精力转移到了规划阶段或审查阶段。一旦我们有了那个，我们就达到了一个可以这样说的点：“为什么是我的想法？为什么我不能让它像一个 cron 作业一样运行，每天去 Twitter 扫描很酷的想法然后自己实现它们？”我只需要决定我想要什么。这实际上是我如何快速实现频道（channels）功能的方式。所以，我们有了那个，现在我只需要审查大量的不同 PR。所以，有一个很好的功能是审查捆绑包（review bundles）。现在我可以确切地看到每个 PR 中发生了什么变化。比如它们为什么要做这些事？任务是什么？我还有视觉证据。所以，我现在可以查看截图，查看视频，真正了解发生了什么，而无需投入太多时间。一旦我们有了那个，我们就可以将更多的工作从规划转移到审查。如果我能做 10 次计划，然后只选择最适合我的那个，我需要花多少时间在计划上？
在实现了代理自主性和工作流自动化之后，Agent Craft 进一步拓展了协作的边界，实现了更深层次的人机与人际协作。
Original English
Now, the cool thing here is that once we have this visibility, we're not exactly done yet because we still need to be able to react to the changes that are happening. So, we can lean into another cool mechanism from RTS games. We can simply use muscle memory to quickly cycle between the agents that need our help. They need us to approve the plan. They need us to answer some questions and so on. So, now we have visibility and we can react quickly. So, we're done. We solved orchestration. But not quite because that's really only the first step. I was able to use more agents in parallel, but only for a short amount of time. There are a few reasons for that. The first one is that there's only a limit to how many ideas I can have in my head at any given time without being tired. So, what I did is basically tell the agent to do it. I told them, "Okay, find missions for me to do." So, I have quests now and I can click a button and they just do whatever. They can refactor test all the stuff that I don't want to do. And the second one is that all of this babysitting takes a lot of time. Like I need I see what's going on. I can react to it very quickly, but I still need to cycle through it. So, what I did there is kind of say, "How do I take myself out of the equation as much as possible?" So, if agents are so amazing, why not just let them do it? I can just like give them some idea. I have this campaign feature. Broadly say what I want to happen and I would just spin up a container. I would let the agents run there. They can decompose the task. They can plan it. They can present the plan to me. I don't care what they're doing because it's container, so do whatever. And the main thing here is that once it's decomposed, I'm not the one doing the babysitting. Now, I have the campaign orchestrator and that's his problem. So, we're actually moving more of the effort only to the planning phase or the review phase. And once we have that, we reach a point where we can just say, "Why is it my ideas? Why can't I tell it to have like run in a cron job, go to Twitter every day, scan cool ideas and just implement them?" I just decide what I want. Which is actually how I implemented channels pretty quickly. So, we have that and now I just have a lot of different PRs to review. So, there's this nice capability of just review bundles. And now I can see exactly what changes happened in each one. Like why did they do stuff? What are the tasks? And I also have visual evidence. So, now I am able to just look at screenshots. I can look at videos and really see what's going on without investing too much time in doing it. And once we have that, we can actually shift more of the work from the planning to the review. How much time do I need to spend on the plan if I can just do it 10 times and I'll just pick the one that is most fitting for me.深度协作与未来展望
接下来的部分是，我们还没有完成。我的意思是，如果你仔细想想，这只是第一步，因为代理还没有那么聪明。所以，我们需要将其外包给别人——人类。现在，我可以做到的，这也是我最喜欢的功能，就是我们可以创建这些工作空间。所以，我可以与我团队中的产品设计师协作，他们可以做任何他们想做的事情，而我可以继续他们未完成的工作。所以，举个例子，假设这是一个来自产品设计师的代理，在他自己的电脑上。所以，他们可以看到我的代理，我可以看到他们的代理。我可以理解他们在做什么，我们可以一起协作。嗯，他们又开始工作了。所以我可以看到他们想设计这个新页面，这很酷。所以我可以等他们完成，或者我现在就可以继续，然后从他们那里交接给我的代理。嗯，我们的代理。插入共产主义，随便什么。所以，我们现在有了代理，我可以继续进行下去。很酷的是，这不仅仅是人与人的协作。我们也在与代理协作。所以，有更多直接的东西，比如我可以输入内容并提示我的代理，甚至是他们的代理。但也有一个更柔和的机制。实际上有一个聊天，它存在于人与人之间，也存在于人与代理之间。你可以在这里看到代理说，“我开始处理某事了。”然后我可以说，“我也在处理它。”所以，下次代理做某事时，它就知道有人也在处理。它们也可以进行软协作，这样它们就会知道每个人正在更改哪些文件。所以，我们实际上已经解决了很多限制我们充分发挥代理潜力的东西，并逐一解决它们。还有很多其他功能我没有时间介绍，但你可以自己尝试一下，看看是否真的能以这种方式更好地工作。所以，总而言之，这些并不是全新的技能。我的意思是，你可能担心，你可能无法适应这个未来，在这个未来里，我们不再实际编写代码，只是告诉别人为我们编写代码，或者告诉其他代理。但这些技能是存在的。只是直到现在我们还没有将它们用于工作。所以，以游戏为例，我们可以将这些技能提升到一个新的水平。我们需要以某种方式提高这个天花板。我们需要以某种方式改善我们与代理的协作。所以，Agent Craft 的目标是借鉴游戏的经验，并通过更好的可见性、更多的代理自主性以及人机协作，真正将它们提升到一个新的水平。所以，我邀请你去访问网站。这是二维码。它是免费的。你可以下载并试用它。它仍然是实验性的，仍然是新的。有很多东西需要改变，但这只有在收到大量反馈的情况下才会发生。还有一个 Discord。所以，请加入。给我们您的反馈，让我们一起提高天花板。谢谢。
Original English
And the next part is we're still not done. I mean, if you think about it, this is only the first step because agents aren't that smart yet. So, we need to offload it to someone else. Humans. Now, what I can do, and this is my favorite feature, is that we can actually create these workspaces. So, I can collaborate with the product designer from my team and they can do whatever they want and we can I can just continue from where they left off. So, for example, let's say this is an agent actually from the product designer on their computer. So, they can see my agents. I can see their agents. I can understand what they're doing and we can just collaborate. Um Yeah, they just started working again. So, I can see that they want to design this new page, which is pretty cool. So, I can wait for them to finish or I can just go ahead now and just hand off from them to my agents. Well, our agents. Insert communist, whatever. So, we have our agents now and I can just keep going from there. And the cool thing is that it's not just human-to-human collaboration. We are also collaborating with the agents. So, there's more direct stuff like this. I can just type stuff and prompt my agents or even their agents. But there's also a softer mechanism. There's actually a chat that is between humans and humans, but also between the humans and the agents. You can see here that the agent said, "I'm starting to work on something." And then I can say, "I'm also working on it." So, the next time the agent does something, it knows someone else is working. They can also have soft collaboration, so they would know what files each one is changing. So, we've actually taken a bunch of stuff that were limiting us from really reaching our full potential with agents and kind of solve them one by one. There are a bunch of other features that I just didn't have time to go over, but you can try them out and see for yourself if you can really work better that way. So, to sum up, uh these are not exactly new skills. I mean, you're probably worried perhaps that you won't be able to get adapted to this future where we're not actually coding, we're just telling other people to code for us or other agents. Uh but these skills are there. They're just not something we used for work until now. Uh so with games as one example, we can take these skills to the next level. We need to somehow raise that ceiling. We need to somehow improve our collaboration with agents. Uh and with Agent Craft, the goal is to take the learnings from games and really raise that to the next level with better visibility, uh more autonomy to the agents, and human-to-agent collaboration. So, I invite you to go to uh the website. Uh this is the QR code. You can It's free. You can just download it and play with it. Uh it's still experimental. It's still new. There's a bunch of stuff that need to change, uh but it will only happen with great feedback. There's also Discord. Uh so, please join. Give us uh your feedback, and let's raise the ceiling together. Thank you.📌 文中提及的人物和组织
产品/模型: Agent Craft