Roman Ugarte：一个月打造 Grok Bot，如何让智能体成为可信赖的知识工作同事

简要描述Brief Description

Lenny Rachitsky 与 SpaceXAI Grok Bot 的产品负责人 Roman Ugarte 进行了交流，探讨如何将代理产品推广到开发者以外的用户群体，并将其打造为一个类似同事的知识工作系统。他们谈到了支撑产品发布的小型团队和快速内部孵化过程，团队为何选择具有明确立场的产品界面而非通用聊天界面，入门流程和紧密反馈循环如何塑造产品，委派与信任的运作机制，以及由多个 AI 代理组成的团队这一更长期的愿景。Lenny Rachitsky speaks with Roman Ugarte, product lead for Grok Bot at SpaceXAI, about taking an agent product beyond developers and turning it into a colleague-like system for knowledge work. They cover the small team and fast internal incubation behind the launch, why the team chose an opinionated product surface over a generic chat interface, how onboarding and close feedback loops shaped the product, the mechanics of delegation and trust, and the longer-term vision of teams of AI agents.

目录Table of Contents

• 在一个月内构建知识工作代理
  Building a knowledge-work agent in a month
• 产品界面：同事，而非聊天窗口
  The product surface: colleagues rather than chat
• 用户入门、采用情况及近距离用户反馈
  Onboarding, adoption, and close user feedback
• 委派、上下文与可靠执行
  Delegation, context, and reliable execution
• 设计机器人、权限和协作
  Designing bots, permissions, and collaboration
• 产品迭代速度与反演示软件门槛
  Product velocity and the anti-demoware bar
• 智能体知识工作的未来
  The future of agentic knowledge work
• 总结性建议与原则
  Closing recommendations and principles

在一个月内构建知识工作代理Building a knowledge-work agent in a month

主持人：Lenny 开场时形容 Grok Bot 格外引人入胜：在入门体验期间试用它后，他只是简单要求推广自己最新一期的播客节目，Grok Bot 就给出了有用的结果，并准确找到了相关节目。他说，这款产品很快融入了自己的日常工作，而最近的一次社区聚会也展现出了同样高涨的热情。他询问 Roman，这个想法源自何处，以及是什么让这款产品在拥挤的 AI 市场中脱颖而出。Host: Lenny opens by describing Grok Bot as unusually compelling: after trying it during onboarding, a simple request to promote his latest podcast episode produced a useful result and correctly found the relevant episode. He says the product rapidly became part of his own daily work and that a recent community meetup showed similarly strong enthusiasm. He asks Roman where the idea came from and what made the product break through a crowded AI market.

Roman：这项工作起初是一项从一张白纸开始的尝试。公司已经学会了如何为开发者和工程师构建实用的智能体，但希望了解，这种能力对于知识工作而言可以发展成什么样。少数几个人被调离常规组织，获得了独立的办公空间和私密的沟通渠道，并被要求在大约一个月内打造出一款出色的知识工作产品。Roman: The work began as a blank-page effort. The company had learned how to build useful agents for developers and engineers, but wanted to understand what that capability could become for knowledge work. A handful of people were taken out of the normal organization, given a separate space and private communication channels, and asked to build an excellent knowledge-work product in roughly a month.

这一狭窄的范围至关重要。团队每天都必须做出许多细小且不显眼的决策，而一个围绕六到十二个月计划运作的更大团队，会让项目变得更慢、更趋于传统。从写下第一行代码到做出一个可供内部使用的原型，大约花了一个月。随后，团队将其推广到整个公司，并把大家的反应当作压力测试：人们是否真的会从其他内部和外部工具转向这个代理界面？That narrow scope mattered. The team had to make many small, non-obvious decisions every day, and a larger group oriented around a six- to twelve-month plan would have made the project slower and more conventional. From the first line of code to an internally usable prototype took about a month. The team then rolled it out across the company and used the reaction as a pressure test: would people actually move from other internal and external tools to this agent surface?

内部响应比预期强烈得多。不符合典型早期采用者特征的团队成员开始将日常的智能体工作转移到 Grok Bot 中。当团队看到这种需求拉动后，便从内部试验转向筹备更广泛的发布，以及支持数百万用户所需的运营工作。The internal response was much stronger than expected. People from teams that did not fit the stereotypical early-adopter profile began moving everyday agentic work into Grok Bot. Once the team saw that pull, it switched from internal experimentation to preparing for a broader launch and the operational work required to support millions of users.

产品界面：同事，而非聊天工具The product surface: colleagues rather than chat

主持人：Lenny 将这种方法与那些从编码代理起步、再在现有产品中加入知识工作能力的公司进行了对比。他问道，团队为什么不干脆把 Grok Bot 做成 Cursor 类工具中的另一项功能。Host: Lenny contrasts this approach with companies that started from coding agents and added knowledge-work capabilities within an existing product. He asks why the team did not simply make Grok Bot another feature inside Cursor-like tooling.

Roman：团队希望从用户的工作任务出发，而不是从一个既有的产品界面出发。一个带有一系列连接的通用聊天界面可能很有用，但它会限制人们认为自己可以交给 AI 的任务上限。关键的思维转变，是从“AI 聊天”转向“一个拥有电脑的同事”。一旦用户以这种方式看待系统，他们就愿意分配更大块的工作，并期望系统能够在他们实际使用的工具和信息之间开展工作。Roman: The team wanted to start from the user’s job, not from a pre-existing product surface. A generic chat interface with a collection of connections can be useful, but it sets a low ceiling for what people think they can hand to AI. The important mental shift is from “AI chat” to “a colleague with a computer.” Once users see the system that way, they are willing to assign larger pieces of work and expect it to operate across their real tools and information.

因此，该产品需要一个比全能型聊天窗口更聚焦的界面。团队不断移除功能、撤回尚未发布的想法，而不是不断堆叠控制项和装饰性功能。目标并不是展示模型能够完成的所有事情，而是让少数几个工作流程变得足够可靠，从而让用户愿意再次使用它们。The product therefore needed a more focused surface than an all-purpose chat window. The team repeatedly removed features and unshipped ideas rather than accumulating controls and decorative capability. The objective was not to display everything the model could do; it was to make a small number of workflows feel dependable enough that users would return to them.

Roman 表示，这些早期决策在当时并不显而易见，但事后看来却成为了核心。该产品围绕可委派的工作来设计，而不是围绕某个令人印象深刻的单一响应来设计。两者存在本质区别：能够完成一项工作的系统，可以以一种仅仅完成大部分工作的系统无法做到的方式改变工作流程。Roman says the early decisions were not obvious at the time, but became central in hindsight. The product is designed around work that can be delegated rather than around an impressive single response. The difference is categorical: a system that completes a job can change a workflow in a way that one which gets most of the way there cannot.

新用户引导、采用情况以及密切的用户反馈Onboarding, adoption, and close user feedback

主持人：Lenny 回忆说，Roman 亲自带着他体验了产品。引导流程并没有从冗长的讲解开始，而是鼓励他完成一项实际任务，让产品的能力立刻变得具体可感。Lenny 说，这是整个体验中很重要的一部分，并询问团队从早期用户那里学到了什么。Host: Lenny recalls that Roman personally guided him through the product. The onboarding did not begin with a long explanation; it encouraged a real task, which made the capability immediately concrete. Lenny says this was an important part of the experience and asks what the team learned from early users.

Roman：早期的用户引导高度依赖人工。团队观察人们如何使用产品，了解他们的假设在哪些地方与现实不符，并利用这些反馈来改进产品以及产品的介绍方式。仅仅让构建者了解系统能做什么是不够的。系统还必须让那些没有亲身参与其开发的人也能理解。Roman: Early onboarding was highly manual. The team watched people use the product, learned where their assumptions did not match reality, and used that feedback to refine both the product and the way it was introduced. It was not enough for the builders to understand what the system could do. The system had to make sense to people who had not lived inside its development.

团队将采用视为一项改变行为的实验。人们通常带着围绕聊天产品、代码助手或某种狭窄的内部工具养成的习惯而来。目标是帮助他们确定一项可以交由他人处理的具体任务，然后回到一个已经完成的结果。成功案例在团队中传播开来，让其他人更好地直觉判断哪些类型的工作适合委派。The team treated adoption as an experiment in changing behavior. People often arrived with habits formed around a chat product, a coding assistant, or a narrow internal tool. The goal was to help them identify a concrete task they could hand off and then return to a finished result. Successful examples spread through teams, giving others better intuitions about what kinds of work were appropriate to delegate.

Roman 强调，反馈并不仅仅是功能需求的来源。它帮助团队区分用户真正要完成的任务与用户最初提出的解决方案。公司关注各种需求、直接对话、社交媒体上的示例、支持信号，以及内部团队实际将机器人融入工作流程的方式。由此形成的循环被刻意缩短：观察真实的工作流程，决定要改进或移除什么，发布，然后再次观察。Roman emphasizes that feedback is not merely a source of feature requests. It helps the team distinguish the underlying job from a user’s first proposed solution. The company paid attention to requests, direct conversations, examples on social media, support signals, and the ways internal teams actually incorporated bots into their work. The resulting loop was deliberately short: observe a real workflow, decide what to improve or remove, ship, and observe again.

委派、上下文与可靠执行Delegation, context, and reliable execution

主持人：Lenny 询问，为什么这种体验与其他 AI 产品不同，尤其是在非编码工作方面。他提到，把任务交给 Grok Bot 后就不再过问，回来时任务已经完成，这种感觉令人印象深刻。Host: Lenny asks why the experience feels different from other AI products, especially for non-coding work. He cites the feeling of giving a task to Grok Bot, leaving it alone, and returning to something completed.

Roman：委派所需的不只是一个有能力的模型。人类受托者会获得上下文，能够检查可用的工具，采取行动，从歧义中恢复，并且有动力让工作产生价值。智能体需要一个等效的运行环境：访问恰当的上下文、完成任务的路径，以及一种能让其进展和结果清晰可见的产品体验。Roman: Delegation requires more than a capable model. A human delegate receives context, can inspect the tools available to them, can take actions, can recover from ambiguity, and has an incentive to make the work useful. An agent needs an equivalent operating environment: access to the right context, a path through the task, and a product experience that makes its progress and results legible.

团队专注于构建一种能够跨用户实际使用的系统开展工作的智能体，而不是要求用户手动将所有相关材料整理到提示词中。连接之所以重要，是因为它们能让智能体的工作立足于用户所处的真实环境。但更深层次的产品问题在于，如何利用这些连接来完成一项工作，而不仅仅是检索信息。The team focused on building an agent that could work across a user’s actual systems rather than asking the user to manually collect all relevant material into a prompt. Connections matter because they make the agent’s work grounded in the user’s world. But the deeper product question is how to use those connections to complete a job rather than merely retrieve information.

Roman 将理想的交互描述为更接近与队友协作。用户应该能够提出以结果为导向的请求，并在需要时进行引导或澄清，而不必管理每一个中间步骤。这要求产品清楚地说明当前任务，并帮助用户在恰当的时机进行干预。这同样需要可靠性：如果用户必须经常亲自重做最后的 10%，他们就不会反复将重要工作委托出去。Roman describes the desired interaction as closer to working with a teammate. Users should be able to give an outcome-oriented request, then steer or clarify when needed, without managing every intermediate step. That requires the product to be clear about its current task and to help the user intervene at the right moments. It also requires reliability: users will not delegate important work repeatedly if they must routinely redo the last ten percent themselves.

信任是逐步建立的。早期的工作流通常范围有限且易于检查；随着用户看到成功的结果，他们会扩大分配给代理的任务范围。产品应支持这一渐进过程，而不是要求新用户立即赋予代理广泛的权限。Trust is built gradually. Early workflows tend to be bounded and easy to inspect; as users see successful results, they expand the scope of what they assign. The product should support that progression rather than demand that a new user immediately give an agent broad authority.

设计机器人、权限与协作Designing bots, permissions, and collaboration

主持人：对话转向了单个机器人所扮演的角色。Lenny 在自己的工作区中开启了许多机器人，并询问这种模式如何与通用助手的愿景相契合。Host: The conversation turns to the role of individual bots. Lenny has many bots open in his own workspace and asks how this model fits with the vision of a general assistant.

Roman：更长期的愿景是打造一组能够协助人们处理工作和生活的 AI 机器人。机器人并不仅仅是保存下来的提示词。它可以拥有明确的角色、相关的上下文、对特定系统的访问权限，以及与其负责的任务之间的持续关联。这样一来，用户就可以按职能组织工作，而不必在每次对话中重新创建相同的配置。Roman: The longer-term vision is a team of AI bots that help with a person’s job and life. A bot is not simply a saved prompt. It can have a defined role, relevant context, access to particular systems, and an ongoing relationship with the tasks for which it is responsible. That makes it possible for users to organize work by function rather than recreating the same setup in every conversation.

不同的机器人可以体现不同类型的专业能力或访问权限。产品必须让用户理解这些边界，尤其是在涉及工具、信息、权限或外部操作时。Roman 将其视为一个产品设计问题，而不仅仅是技术问题：人们需要知道机器人能做什么、知道什么，以及当它朝着错误的方向发展时如何引导它。Different bots can embody different kinds of expertise or access. The product must make those boundaries understandable, especially where tools, information, permissions, or external actions are involved. Roman frames this as a product-design problem as much as a technical one: people need to know what a bot can do, what it knows, and how to steer it when it is heading in the wrong direction.

团队还认为，协作方式可以更加丰富。用户不必将每次互动都视为彼此孤立的事件，而是可以构建一组协作代理，让它们保留恰当的上下文，并在适当的时候参与任务。这里的类比并不是说机器人应该在方方面面模仿人类，而是说，一个有用的团队成员应通过其角色、所处上下文以及对结果承担责任的能力来理解。The team also sees room for richer collaboration. Instead of treating each interaction as isolated, users can build a working set of agents that retain the right context and can be brought into a task at the appropriate time. The analogy is not that bots should imitate people in every way; it is that a useful team member is understood through their role, context, and ability to take responsibility for a result.

产品迭代速度与反演示软件门槛Product velocity and the anti-demoware bar

主持人：Lenny 注意到产品和公司发展的速度之快。他询问团队如何保持这样的节奏，并避免打造出在演示中看起来令人印象深刻、但在日常使用中却表现不佳的产品。Host: Lenny notes how quickly the product and the company have moved. He asks how the team sustains that pace and avoids making a product that looks impressive in a demonstration but fails in ordinary use.

Roman：速度源于雄心、小团队以及愿意做出取舍。公司具有竞争力，但相关的竞争并不只是其他人工智能公司，而是用户现有的工作方式。新产品必须足够出色，才能取代人们已经熟悉的某些事物，包括熟悉的聊天工具和手动流程。Roman: Speed comes from a combination of ambition, small teams, and a willingness to make tradeoffs. The company is competitive, but the relevant competition is not just other AI companies. It is the user’s existing way of doing work. A new product has to be good enough to displace something people already know, including familiar chat tools and manual processes.

团队通过坚持反复使用来避免沦为演示软件。一次性、华而不实的成果并不是衡量标准。标准在于，用户能否为了某项重要工作流程再次使用产品，获得有用的结果，并随着时间的推移建立信心。正因如此，团队会投入时间打磨那些可能显得不那么光鲜的产品细节：让工作更容易启动，为代理提供恰当的上下文，帮助用户理解其行为，并改进围绕失败与反馈建立的闭环。The team tries to avoid demoware by holding itself to repeated use. A flashy one-off result is not the standard. The standard is whether a user can return to the product for an important workflow, receive a useful result, and build confidence over time. This is why the team spends time on product details that might appear unglamorous: making work easier to start, giving the agent the right context, helping users understand its behavior, and improving the loops around failure and feedback.

Roman 表示，该产品是通过“爬山法”开发出来的，而不是假定最终设计一开始就已知。许多微小的改进会逐渐累积并产生复合效应。团队不断决定哪些内容要删减、哪些要保留，以及哪些不完善之处最为重要。团队从未将发布视为工作已经完成的宣告。Roman says the product is developed through hill-climbing rather than by assuming the final design is known in advance. There are many small improvements that compound. The team constantly decides what to cut, what to keep, and which rough edges matter most. It has never treated a release as a declaration that the work is finished.

智能体知识工作的未来The future of agentic knowledge work

主持人：Lenny 询问产品的发展方向，以及 Roman 如何看待更广泛的 AI 时代。他再次谈到这样一个观点：能够完成全部工作的 AI，与仅仅提供帮助的 AI，在本质上是不同的。Host: Lenny asks where the product is going and how Roman thinks about the broader AI moment. He returns to the idea that AI which does all of a job feels fundamentally different from AI that is merely helpful.

Roman：随着智能体能够处理更多端到端的工作，天花板也会不断提高。人们将越来越多地使用它们来完成那些目前需要打开多个工具、查阅分散的文档、协调各种细节并做出一系列小决策的工作。这一机遇并不局限于替代某个单一应用，而是为用户提供一个界面，使他们能够在整个环境中指挥并完成有意义的工作。Roman: The ceiling rises as agents become able to handle more of an end-to-end job. People will increasingly use them for work that currently requires opening many tools, searching through scattered documents, coordinating details, and making a series of small decisions. The opportunity is not limited to replacing a single application. It is to give users an interface through which they can direct meaningful work across their environment.

Roman 很谨慎，不会把这描述成对人类判断力的即时替代。该产品仍需要更强的能力、更高的可靠性，以及让用户能够保持掌控的更好方式。最有价值的发展方向，是在保留引导、审查和设定适当边界能力的同时，让人们能够放心委托更多事务。Roman is careful not to present this as an instant replacement for human judgment. The product still needs better capabilities, better reliability, and better ways for users to stay in control. The most valuable direction is to increase what people can confidently delegate while preserving the ability to steer, review, and set appropriate boundaries.

一组机器人的愿景意味着人与软件之间将形成不同的关系。人们不必为每项任务打开一个单独的应用程序，而是可以请具有相关职责的智能体代表自己执行操作。产品必须通过在实际工作中的实用性赢得这一角色，而不是靠对遥远未来的承诺。The vision of a team of bots implies a different relationship to software. Rather than opening a separate application for every task, a person can ask agents with relevant roles to act on their behalf. The product must earn that role through usefulness in real work, not through a promise about a distant future.

总结性建议与原则Closing recommendations and principles

主持人：在快速的收尾环节中，Lenny 询问 Roman 喜欢的产品、他反复思考的想法，以及听众接下来应该做什么。Host: In a rapid-fire closing, Lenny asks about products Roman enjoys, ideas he returns to, and what listeners should do next.

Roman：他说自己一直很喜欢语义搜索产品，尤其是将语义检索应用于独特数据集的非同寻常的场景。他提到 Metaphor（后来更名为 Exa），并表示，与其只将语义搜索用于传统的网页搜索，不如用它来搜索奇怪或专业化的查询，这很有趣。Roman: He says he has long enjoyed semantic search products, especially unusual applications of semantic retrieval over distinctive datasets. He mentions Metaphor, which became Exa, and describes finding it fun to use semantic search for strange or specialized queries rather than only for conventional web search.

作为人生准则，Roman 提到了诗歌《心愿》。他从十几岁起就一直把它带在身边，并发现每次重读时，它都能带来新的启示。他认为这首诗能让人脚踏实地，而不是一句简短的口号。For a life principle, Roman mentions the poem “Desiderata.” He has kept it with him since he was a teenager and finds that it continues to offer something new on rereading. He describes it as grounding rather than as a short slogan.

Roman 最后邀请用户试用 Grok Bot 并提供反馈。该产品仅在几周前推出了测试版，早期用户的意见正直接影响着团队要构建的内容以及构建方式。Lenny 感谢 Roman 和整个团队，并指出这次对话记录了 Grok Bot 以及更广泛的 AI 领域尤为活跃的一个时期。Roman closes by asking users to try Grok Bot and send feedback. The product had launched its beta only weeks earlier, and the early user input was directly shaping what the team built and how it built it. Lenny thanks Roman and the wider team, noting that the conversation captures a particularly active moment for Grok Bot and AI more broadly.