当文档的主要读者变成 AI 智能体：Hahnbee Lee 与 Lincoln Murr 的产品思考

简要说明Brief Description

一场围绕 AI 智能体文档、API 访问、智能体支付，以及团队所面临的维护选择展开的炉边对谈。A fireside conversation about documentation for AI agents, API access, agent payments, and the maintenance choices teams face.

目录Table of Contents

• 简介
  Intro
• 当智能体是主要用户时
  When agents are the main users
• 能够支付的智能体
  Agents that can pay
• 为什么智能体支付要使用加密货币
  Why crypto for agent payments
• 1亿笔代理交易
  100 million agent transactions
• API、MCP 与 CLI 的比较
  API vs. MCP vs. CLI
• 代理式支付的发展方向
  Where agentic payments are headed
• 相比前端，更注重 API
  APIs over front ends
• 智能体流量：10% 至 80%
  Agent traffic: 10% to 80%
• 人类写作与 AI 写作
  Human vs. AI writing
• 最大的陷阱：自建还是购买
  The biggest pitfall: build vs. buy

简介Intro

主持人：大家好，很高兴见到各位。感谢大家前来，希望大家今天都开了个好头。很高兴认识大家。我是 Hamby，Mintlify 的联合创始人兼 CTO。Mintlify 是一家总部位于旧金山的 B 轮公司，为 Coinbase 等公司提供开发者文档服务。你愿意介绍一下自己吗？Host: Hi. Nice to meet you all. appreciate you guys all coming. hope everyone is having a good start to their day. nice to meet you. I'm Hamby. I'm a co-founder and CTO at Mintlify. Mintlify is a series B company based in San Francisco and we power developer documentation for companies like Coinbase. would you like to give an intro?

嘉宾：没错，当然可以。大家好，我叫 Lincoln，是 Coinbase 的 AI 产品负责人。你们可能知道 Coinbase 是一家加密货币公司，不过它也在广泛拓展各类资产和支付业务。此外，它还有智能体相关的发展方向，我们很快就会聊到这一点。Guest: Yeah, sure. Everyone, my name is Lincoln. I'm the head of AI product at Coinbase, which you might know as a crypto company, but is widely expanding into all sorts of assets and payments as well and there's also an agentic angle, which we'll be talking about here shortly.

主持人：好。你想先去问第一个问题吗？Host: Yeah. do you want to go and ask the first question?

嘉宾：当然。形式就是轻松的炉边谈话，我们轮流聊一聊对当今世界的看法，各自的公司如何为这个智能体时代构建产品，以及我们认为未来会走向何方。那么，Hamby，你能先提个问题吗？Guest: Yeah, sure. So, the format was just kind of fireside chat back and forth, talk a little bit about how we view the world today, how our respective companies are building for this agentic future and where we kind of think things will go. So, Hamby, can you kick us off with a question here?

当智能体是主要用户时When agents are the main users

抱歉，我只是……哦，对，对，对，就是这个。那么，我们该如何看待智能体成为互联网上的主要行动者，以及成为人们互联网体验中主要使用的东西？我可以告诉一个智能体去为智能体配置 Coinbase。它会找到我们的文档，然后完全替我把一切都办好。这会如何改变我们在思考如何编写文档时所看重的东西？Sorry, I'm just Oh, yeah, yeah, yeah. This one. So, yeah, how do we think about agents becoming the primary actor on the internet and the primary thing that people are using as part of the their internet experience? I can go tell an agent to go set up Coinbase for agents. It's going to find our docs and do it all entirely for me. How does this change what's important when you're thinking about how you're building docs?

主持人：是的，当然。Mintlify 是 2022 年创立的，所以我想说，那是在 ChatGPT 出现之前，具体来说是在 GPT-3 之前。我觉得以前人们会更重视设计和前端，而我个人很喜欢设计，我们现在也绝对仍然是一家以设计为主导的公司。所以，这多少还是让我有点难过。说实话，智能体看不到你的网站，也不在乎它看起来怎么样，或者它的品牌形象是什么。结果就是，像页面大小这样的东西反而变得重要得多。Host: Yeah, of course. so, Mintlify was founded in 2022, so pre-chat chat GPT, GPT-3 specifically, I would say. and I would say that previously there was like much more of an emphasis on design and front end, which I personally love design and we are definitely like a design-led company still. So, it's kind of still it kind of makes me sad. I'm not going to lie, the fact that like the agents do not see your website and they do not care what it looks like or what the branding of it. And so, what ends up mattering a lot more is like things like page size.

就是说，它会占用很多上下文窗口吗？比如说内容是否准确，因为智能体可以读取你的文档并设置好，然后如果遇到一点小阻碍，它就会停下来。Like, is it taking up a bunch of like the context window? like the content being accurate because like an agent can like set like read your docs and set it up, and then if it runs into like a little friction point, it's just going to stop.

它就是不会去调试它。它可能会反复尝试，想用蛮力解决问题，但也可能轻而易举地转而使用另一款产品。所以我确实觉得，编程智能体让整个世界的节奏快了很多。工程团队，或者说尤其是 EPD，正在获得这么多生产力提升，这很重要，而组织里的其他部分也得赶上来，对吧？我觉得，要让我们所有人都能跟上工程团队所获得的生产力提升带来的速度，唯一的办法就是借助 AI 跟上。It's just like it's not going to like debug it. It's It might just like It might try and try to like brute force it, but then it can also just as easily churn to another product. And so, I do think like, you know, like coding agents have made the world like move so much faster, and it's important that like I like engineering or EPD specifically is like seeing so many like like productivity gains, and like the rest of the org kind of needs to catch up, you know? And I think the only way in order for us to all move at the speed that like the productivity gains that engineering is seeing is to kind of use AI to kind of keep up.

所以这就意味着，当然，文档写得好不好会更主观一些；或者说，你知道，关于 AI 写作，我个人喜欢什么，我还在摸索。And that means like, of course, it's a lot more subjective like whether the docs are good or like, you know, writing AI writing I like I personally like I'm still figuring that out.

不过我确实觉得，设置自动化来确保诸如此类的东西不会过时，是非常非常重要的。but I do think like setting up automations in order to ensure that like like things like do not go stale is like a very very important.

具备支付能力的智能体Agents that can pay

我也想听听你自己的看法。那么，现在代理开始在互联网上进行交易，这会如何改变 Coinbase 对交易本身的整体看法？and I'm curious for yourself. So, now that like agents are making transactions on the internet, how does that change how Coinbase thinks about like just transactions in general?

嘉宾：是的，AI 智能体与作为支付通道的稳定币，差不多是在同一时期兴起的。回顾以往的技术时代，我们也常看到两个技术拐点同时出现，比如移动电话和 4G LTE 的发展。这带来了许多新的机遇，但也意味着我们可能会被一家新兴初创公司或企业绕过，或受到其冲击。所以，我们主要从两个角度来看待这件事。Guest: Yeah, the intersection of AI agents and stablecoins as a payment rail have sort of happened at the same time. And traditionally, you see two inflection points come together in previous eras of technology, like for example, mobile phones at the same time that you have 4G LTE. And this opens up a lot of new opportunities, but it also opens up an opportunity for us to be disintermediated or disrupted by a new nascent startup or company. So, there's there's really two ways that we think about it.

一个问题是，我们可以构建、使用并专门面向智能体推广哪些创新产品，又可以为智能体打造什么产品，让它们获得一种在互联网的前一个时代完全不可能实现的体验。另一个问题是，Coinbase 业务的哪些核心部分需要向智能体开放，才能让人们继续使用 Coinbase，满足我们最基本的需求场景，比如交易、资金管理等等。One is what are these innovative products that we can build and use and and market specifically toward agents and build for agents so that they have this experience that is otherwise completely not possible in the previous era of the internet. But then also too, what are the core parts of Coinbase's business that we need to make accessible to agents such that people continue using Coinbase as for our bread and butter use case of trading and money management and whatnot.

我对这两件事的看法是，关键在于如何通过 API 让我们的整个业务都能够被访问。也就是说，我们如何把所有供人使用的功能转化为智能体能够与之交互的形式。虽然通过浏览器也能做到这一点，但这并非最理想的方式。这里涉及很多身份验证和安全方面的顾虑，尤其是在处理财务事务时。And the way that I view those two things is around how we make our entire business accessible via APIs. So, how can we take all of the functionality that's available to humans and translate that into a world where agents can interact with it. And though that's possible with browser use, it's not exactly the most ideal situation. There's a lot of authentication and and security concerns, especially when you're dealing with finances.

你不希望给你的智能体某种不受限制的账户访问权限。你需要设置适当的防护措施、限制等等。因此，为了给公司构筑这道防御屏障，让我们能够在 AI 时代生存下去，我们正在做的事情有点类似于从 Web 转向移动端；而现在，则是从移动端转向智能体，并让十年前人们使用手机时能够访问的一切都能通过智能体实现——那时人们还会说：“我绝不会用手机办理银行业务。”You don't want to give your agent sort of unfettered access to your account. You want the right guardrails, limitations, all of that in place. So, to build this defensive hedge for our company and allow us to survive in the AI era, we are taking this it's sort of an analog to web shifting to mobile, but now mobile shifting to agents and making everything that was accessible for mobile users inside their their phone back a decade ago when people were saying, "I would never bank on my phone.

“这听起来太疯狂了。”如今，每个人使用它的频率甚至超过使用网页浏览器。我们要做的也是同一件事，只不过现在把它开放给智能体使用，并加入所需的各种安全机制。这样一来，你今天可能还会说：“我为什么要让 AI 访问我的账户来管理资金？”但十年后，你甚至都不会再查看自己的账户，一切都会通过你的智能体来完成。That sounds crazy." Now everyone does it more than they do even on their web browser. Doing that same thing, but now making it available to agents adding in all of the safety nuances that you would need such that today you may say, "Why would I ever give an AI access to my account to manage money?" And 10 years from now, you won't even be looking at your account at all, just be happening through your agent.

为什么代理支付要使用加密货币Why crypto for agent payments

主持人：我很好奇，加密货币作为解决方案有什么特别的优势吗？Host: I'm curious, is there like specific advantages of crypto being the solution for this?

嘉宾：我认为支付方面绝对是这样。我们看到 X402 早期取得了不少进展。X402 是我们的互联网原生支付标准，现在我们已将其独立出来，成立了一个单独的基金会。该基金会由 Cloudflare、Stripe、Amex、Mastercard、Visa 等共同运营和治理。我认为，加密货币的优势主要在于，数字美元能够以低成本、快速且无需许可的方式发送到世界各地。Guest: I think on the payment side, absolutely. So, a lot of what we've seen with early traction around X402, which is our internet native payment standard that we have now externalized into its own separate foundation. That's that's co-run and governed by Cloudflare, Stripe, Amex, Mastercard, Visa, and so on. The the crypto angle, I think is primarily around the ability for digital dollars to be sent cheap, fast, permissionlessly anywhere in the world.

所以，任何经营业务并希望自己的 AI 智能体能够接受交易的人，都可以做到这一点。虽然我们已经在现有的、类似银行卡支付或 Stripe 链接的解决方案中经常看到这种情况，但我认为加密货币特别能发挥作用的领域之一，是微支付：智能体可以花费百分之一美分的千分之一，甚至百分之一美分的百万分之一，来访问 API、服务，甚至是付费墙后的网站，而且整个过程非常顺畅、轻而易举。So, anyone who's running a business and wants their AI agent to accept a transaction can do so. And though we've seen this a lot with existing sort of card-based or stripe link style solutions, one of the areas where I think crypto has a particular role to play is around micro transactions and the ability for an agent to spend 1/1000 of a cent, even 1/1000000 of a cent, to access an API or a service or even a paywalled website very, very seamlessly and and trivially.

1 亿笔智能体交易100 million agent transactions

主持人：我很好奇，那样的未来已经到来了吗？比如，我们已经看到智能体通过加密货币进行交易了吗？比如……Host: And I'm curious, is that future already here? Like are we already seeing agents making transactions via crypto? Like

嘉宾：是的，绝对如此。我们看到交易量正在快速增长，几乎呈指数级上升。过去一年里，实际上已经发生了约一亿笔智能体交易，这些交易全部都在链上进行，任何人都可以公开审计。这些交易主要用于与 API 交互。在过去的模式下，你得先访问想要使用的服务的网站，为账户充值，获取 API 密钥，然后把密钥交给你的智能体。Guest: Yeah, absolutely. We're we're seeing a pretty pretty exponential increase in the amount of transactions that are being made. In the past year, we've seen around 100 million agentic transactions actually, all happening on chain, all publicly available for anyone to audit. all of those are primarily for this use case of interacting with APIs. So in this previous version of the world, you would have to go to whatever website you wanted to interact with the service, you'd have to fund that account, you'd have to get an API key, and then hand that to your agent.

只有这样，你才能真正开始与各种事物互动。但现在我们看到的是这样一个世界：只要给智能体一个钱包或某种金融账户，它就能自行按次付费，调用不同的 API。这对智能体支付的早期采用者这一核心受众群体来说，是一个非常有吸引力的用例。Only then you can really start to interact with things. But now we're seeing a world where if you just give an agent a wallet or some sort of financial account, it can go off and pay in a one-off basis for different APIs. And that's been a really resonant use case with this core audience of of early adopters of agentic payments.

主持人：所以你的意思基本上是，人们通过 API 连接到你的钱包，或者是代理购买 API，还是……Host: So you're talking about like basically people connecting to your wallet via API or like the agent purchasing APIs or

嘉宾：是的，这就像代理购买 API。所以Guest: Yeah, it's like the agent purchasing APIs. So

主持人：哦，好吧。Host: Oh, okay.

嘉宾：我喜欢用这样的比喻：现在互联网的运作方式，就像每次去杂货店，你都得先进去，买一张那家杂货店专属的礼品卡，再注册他们的会员账户，然后才能开始买东西。每次访问一个网站，感觉也是如此：你得获取 API 密钥，专门给那个账户充值，然后你的智能体才能开始交互。但随着我们赋予这些智能体更多的财务独立性和自主权，它们就能做事，而不必经过这个繁琐、受人为阻碍的流程。就像我如果无法使用资金，在互联网上能做的事情也很有限一样，智能体也是如此。Guest: The the analogy I like to use is it'd be like if every the the current way the internet works is every time you it'd be like if every time you went to a grocery store, you had to walk in, you had to buy a gift card for that specific grocery store, you had to sign up for their loyalty account, and only then you can start paying for stuff. And that's how it feels whenever you go to a website, you have to get API keys, you have to fund that account specifically, and only then your agent can start interacting. But as we give these agents more financial independence and autonomy, they're able to do things without having to go through this arduous human blocking process. And in the same way that I can only do so much on the internet without having access to money, agents are very much the same way.

让它们能够使用资金，是提升其自主性并最终让它们能够自行处理事情的方式。比如，你只要告诉云端代理“我想生成一张图片”，即使它目前还没有接入相关服务，它也应该能够做到。它只需为这项服务付费，比如支付 25 美分或其他相应费用。Giving them access to money is how you increase their autonomy and ultimately get to the point where they can go do things if you just tell your cloud agent, I want to go generate an image, it should be able to do that even if it doesn't have a connection to that today. It should just pay for that service, pay the 25 cents or whatever it might be.

主持人：所以，你会说 Coinbase 总体上是在进一步加码 API，以便更好地适配智能体吗？Host: So, Coinbase is like doubling down on APIs in general, would you say, to make it more agent friendly?

嘉宾：是的，当然。我认为 API 才是关键所在。你可以把它封装进 MCP 里；如果未来某个时候情况有所变化，那也没什么。我们拭目以待。不过，真正重要的还是 API，以及以一种安全、友好、直观的方式提供对你服务的底层访问，让更多人更容易使用它。Guest: Yeah, absolutely. I think APIs are the name of the game. You can wrap that in an MCP and that's all fine and dandy if that changes at some point in the future. We'll see, but it's it's really the the the APIs and that underlying access to your service in a way that gives makes it so much more accessible to people in like a safe, friendly, intuitive manner.

API 与 MCP 与 CLIAPI vs. MCP vs. CLI

主持人：我本来想问问你对 MCP、CLI 和 API 之间的区别有什么看法。Host: I was going to ask if you have any takes on like MCP versus CLI versus API.

嘉宾：是的，我只是觉得，API 始终会是这一切底层最基础的那一层，而 MCP 则很适合用来补充额外的上下文和细微差别，这些是在类似自然语言的场景中所需要的。CLI 大体上也一样，只是还需要关联一个终端。但我觉得，这几者都得有，而这也体现了 AI 辅助开发已经变得多么容易。感觉你只是在以代理能使用的任何方式、形式，把它们封装起来。除此之外，它们各自都有优缺点，但我觉得这些工具还远没有发展到最终形态，未来会如何演进、又会走向何方，仍有很长的路要走。Guest: Yeah, I just I think API's always going to be that fundamental layer underneath it all and then the MCP is nice for adding additional context and nuance that's required within like a natural language style setting and and CLI is is broadly the same with the additional requirement of having like a terminal associated with it, but between all of them, I think it's kind of like a you have to have all of them and it's how easy AI assisted development has gotten. It kind of feels like you're just fundamentally wrapping them in whatever way, shape, or form that the agent can use. And beyond that, there's, you know, pros and cons to each of them individually, but I think we're far from the end game of how these tools evolve and and where they start going.

代理式支付的发展方向Where agentic payments are headed

主持人：是啊，这就引出了我的下一个问题。你觉得世界会走向何方？Host: Yeah, that leads to my next question. Like, where do you think the world is going to be headed towards?

嘉宾：嗯。嗯。Guest: Mhm. Mhm.

嘉宾：我尤其是在智能体支付这方面，核心的基本信念是：让智能体获得资金并授权它们进行消费，赋予它们更大的财务自主权，这样才能逐步提升它们的自主程度，让它们持续运行，最终带来更好的结果。如果我能让我的智能体有能力在需要付费才能访问的网站上购买信息，而这些信息此前它无法获取，那么它就可以整夜运行，进行更深入的研究；而如果我只是让它访问公开的开放互联网，它就做不到这一点。同样，如果未来有一天我让智能体替我设立一家公司、成立一家 LLC，也许它无法完全独立完成这件事，但或许它可以去 Fiverr 之类的平台雇一位律师，或者雇个真人，或使用这类服务中的任何一种，再找一位会计师来处理这项工作。Guest: I On the agentic payment side particularly, my sort of core fundamental belief is that granting agents more financial independence by giving them access to money and and authorizing them to spend that is how we create increasing levels of autonomy and long-running agents that just lead ultimately to better outcomes. If I can get my agent the ability to go pay for information on paywalled sites that otherwise wouldn't previously be available, that would allow it to run overnight and do even deeper research settings that I could do if I just gave it access to the public open internet. Similarly, if I allow my agent to in a future version of the world, say I want my agent to go set up a company for me and form an LLC. Maybe it can't do that entirely on its own, but maybe it can go hire a lawyer off of a you know a Fiverr equivalent or or rent a human or any one of these services and and an accountant to handle this work.

加密领域有一个非常有意思的概念，叫作 DAO。DAO 就是去中心化自治组织。这个概念已经存在好几年了，但它最终基本上只是变成了另一种形式的官僚体制：一小撮人试图做决定，而这种组织总是会以某种方式瓦解。It there's a really interesting concept from the crypto space. It's called a DAO like a DAO. It's a decentralized autonomous organization. And this has been around for for several years now, but it's really manifested itself as basically just another form of bureaucracy where there's a handful of people trying to make decisions and it just it just always kind of crumbled.

它从未真正实现那个完整的愿景。最初的愿景是以自动化为核心、让人类处于边缘，并以这种方式运营组织。我认为，能够动用资金的智能体，就是一个非常明显的例子，能让我们看到这一愿景最终将如何实现。It never really achieved that whole vision. And the original vision was automation at the core and humans at the edges and you run an organization that way. And I think agents with access to money are a very clear example of how we're going to see that vision finally come to life.

主持人：我问这些问题真的是出于好奇，因为我个人对加密货币不太了解。我觉得很有意思的是，之前提出的很多观点，好像正在随着 AI 的加入逐渐成为现实。Host: I genuinely ask these questions with curiosity cuz I personally do not know crypto very well and it's very interesting to see how like I guess like a lot of these theses that were like kind of built previously are kind of coming into fruition with AI in play.

嘉宾：是的，看到这一切真的很有意思。从很多方面来说，这都验证了这一点：你显然不能直接让 AI 访问银行账户。加密钱包是一个很好的方式，可以用可验证的方式让它获得资金的使用权和所有权。不过，我很想听听你对世界将如何演变的看法和愿景，也想了解随着智能体成为文档的主要使用者和摄取者，这会如何改变你们在 Menthafy 的战略。Guest: Yeah, it's been really fun to see. It's very validated in a lot of senses where it's like you simply can't just give an AI access to a bank account. A crypto wallet is a nice way to provably give it access and and ownership over over money, but I would love to hear your your perspective and vision on how the world evolves as well as as agents becoming the primary adopters and ingesters of of documentation and how that changes your strategy at Menthafy.

API 优先于前端界面APIs over front ends

主持人：是啊，我很喜欢你如此强调 API，因为我的看法也一样。感觉很多软件公司都在变得更加以开发者为中心。你知道，我们确实设想过这样一个世界：每个人都在使用这类技术。但眼下，最早采用它们的是开发者，而且这些智能体实际上也会说开发者的语言，因为一切都是代码，对吧？而且它们特别擅长用 bash。Host: Yeah, I love how much of an emphasis you had on APIs cuz that's also my take. Like it's it feels like a lot of software companies are kind of becoming more developer-centric. And you know, we do envision a world where everybody is using like this technology, but right now like the earliest adopters are developers and also the agents actually speak like the language of developers because like it's all in code, right? And like they they're really good at bash.

他们非常擅长使用 CLI 命令。所以我确实认为，至少目前，软件公司都应该大力投资 API 以及这些说实话看起来有点传统的东西。我也觉得，你刚才说的话进一步说明，前端也没那么重要了。They're really good at CLI commands. And so definitely think at least like for now like doing that and all like software companies should be really investing in APIs and these things that like seem a little bit traditional honestly. and also I I think like what you said also reinforces the fact that the like front end is not mattering as much either.

比如说，基本上就是通过创建 API，让代理能够访问一切。Like make make everything avail- accessible to agents by like by creating APIs essentially.

智能体流量：10% 至 80%Agent traffic: 10% to 80%

我想分享一个有意思的数据：年初时，在 Netlify 的所有站点中，大约只有 10% 的访问量来自智能体；而现在，这个比例已经接近 80% 了。挺有意思的是，我们公司内部有个追踪器，会记录这个比例，我们还会私下打赌，猜它会涨到多少。结果它增长得比我们预想的还快。 这并不是说人类访问量在下降，而是智能体访问量增长得实在太快了。我总觉得挺奇妙：智能体在某些方面和人类很像，在很多方面又很不一样。不过，我有时会把描述智能体的说法用在人类身上。比如，与智能体相比，我们人类的上下文窗口很小；而智能体有更多时间去吸收大量内容，也能更好地理解这些内容。我认为，这正是我们现在看到智能体对企业和工作方式产生巨大影响、并迅速崛起的关键所在。one interesting statistic that I want to share is that at the beginning of the year across all Netlify sites, we had around like 10% of like the viewership was agents and now we're closer to like 80%. and it's kind of funny we have like this internal tracker at our company where we we just track like how what what the percentage is and we're like we internally like take bets on like where we think it's going to go and it's been growing faster than we even think. And it's not like human viewership is going down, but I think that like the agent viewership is just going so much higher. I always like to like it's it's weird because like agents act kind of similarly to humans and and different in in many different ways, but like I like kind of using like the agent terms on humans in the sense that like we as humans have very small context windows in comparison to the agents like and they have much more like you know, time to just like like ingest so much more content and be able to grok that well and I think that's like really the the crux of like the big surge that we're all just like seeing right now with like how agents are impacting businesses and like how we work.

这简直太疯狂了，过去几年的增长实在惊人。比如 OpenClaw，明明就是今年才出现的，可感觉也像是很久以前的事了。it's it's it's insane like the like the the growth like over the past years is insane. like open claw like was literally like this year and that's that also kind of feels like forever ago.

人类写作与 AI 写作Human vs. AI writing

嘉宾：这真是太有意思了。我想深入聊聊你提到的一点：公司会投资于传统的东西，以及你之前谈到的由人类而不是 AI 来编写文档。我很想进一步了解你对此的看法：我们是否始终需要这种人为参与来编写文档，或者提供一些细微之处，供智能体读取和吸收？还是说，未来团队可以通过更自动化的流程来完成这件事？如今各个团队又是如何采用这种模式的？Guest: That that's fascinating. I want to drill in on something you said about companies investing in like the traditional things and also what you made previously around humans writing documentation as opposed to AI. I'm really curious to learn a little bit more about your perspective on that and if we'll always sort of need this human touch to to write documentation or or or provide a nuance that then an agent can go ingest or if there's a world where this starts to become a a more automated process for teams and how teams are interacting with this this pattern today.

主持人：是啊，我花很多时间思考人类写作和 AI 生成写作之间的区别，以及我的观点在其中处于什么位置。我确实认为，对于创意散文或叙事写作来说，人类的温度非常重要。我不知道在座各位上网上到有多深，但我自己已经深度沉迷网络了。关于软件工程师用编程工具写所有代码，却坚持亲手写散文的讨论，真的特别多。Host: Yeah, I spend a lot of time thinking about like human writing versus like AI-generated writing and where my takes fall in that. And I do think that for creative prose or narrative writing, it's very important to have that human touch. And I don't know how terminally online this room is, but I am quite terminally online. And there is so much conversation about you know, like software engineers like using coding for writing all their code, but then religiously like writing like prose by hand.

比如说，你知道，当你要把一份文档交给团队里的其他人时，你会选择用 AI 生成，还是自己写？现在似乎开始出现一类文档，也出现了某种分化。所以，我确实觉得自己总是在传统和一种新范式之间摇摆不定：一切都在变化，我们也需要改变思维方式。Like, you know, when you're like giving a document to somebody else within the team, like do you decide to AI-generate it or do you decide to write it yourself? There's starting to become like a class of documents and like division happening now. And so, I definitely think like it's I like I always kind of like teeter around like, you know, going towards tradition versus like going towards like a new paradigm of like everything is changing and we need to change the way that we think.

我觉得我们都是边走边摸索。说实话，我确实有过那么一段时间，感觉自己有点「AI 精神病」，心想：哦，我不需要跟任何人说话，跟我的 MCP 聊聊就能获得所有洞见和一切。我确实觉得，尤其是作为一个产品人，我也很好奇你对此有什么看法。And I think that it's we're all figuring it out as we go. I I I'm not going to lie, I do think I had a point in time where I was like feeling a little AI psychosis, where I'm like, oh, like, I don't need to talk to anyone. Like, I'll just talk to my MCPs and I'll be able to get all the insights and everything. I definitely think, especially as a product person, I'm also curious to hear your thoughts on that.

就是说，尽管各种创新都在不断变化，但和人们交流，弄清楚当下真正的痛点和使用场景，仍然很重要。不过，回到你的问题，我认为尤其是技术写作，它有一个收集见解并将其整理成文的过程，而我确实认为，其中技术写作这部分可以自动化。Like, it's still important to talk to people and figure out like what what what the real pain points and use cases are today in spite of all the innovations that are changing. but yeah, to to kind of go back to your question, like I think for technical writing particularly, like there is like a process of gathering the insights and then like putting it in, in which I do think like the technical writing like portion of it can be automated.

我觉得，找出所有相关的 PR、相关背景信息，以及 Slack 里发生的所有事情和做出的所有决定，然后把这些内容精简地整理出来，再弄清楚该把它注入到你的内容库中的什么位置——这一整套事情都可以自动化。Like, I think it's very tedious to find all the related PRs, find all the related context, all everything that's happening within Slack, all the decisions being made, and then like put that into something succinct, and then figure out like where and like amidst your corpus of like content like you need to like inject it in. I think like all of that can be automated.

嘉宾：有意思。是的，我我我从产品角度也注意到了，正如你说的，仅仅通过和智能体交互，很难找到任何洞察或可借鉴之处。而且说到底，它只会产生幻觉，让你把优先级排到错误的事情上。Guest: Interesting. Yeah, I I I've noticed from the product perspective to your point that it's it's very difficult to find any sort of insights or takeaways from just interacting with an agent. And if anything it just hallucinates and make you prioritize the wrong wrong things.

最大的陷阱：自建还是购买The biggest pitfall: build vs. buy

如果我对时间的估算没错，我们应该还有时间再回答一个问题。我很想听听，在你看来，致力于构建 AI 并为 AI 编写文档的团队最常掉进的陷阱是什么？这会如何影响他们试图引导 AI 完成的任务？你又有什么建议，能让整个流程更加顺畅？if my reckoning of time is right we probably have time for one more question. So I'd be very curious to hear from you what is the most common fit fitfall you see teams who are building for AI and building documentation for AI fall into and how that sort of impacts what they're attempting to drive the AI to do and what you would recommend to to make this whole process much more seamless.

主持人：嗯，是的。好吧，这听起来可能像是在给自己打广告，但我确实觉得，这本质上就是“自建还是购买”的问题。我觉得这是大家在开发软件产品时一直会问的问题。做决定时，无论你考虑的是文档，还是公司里用来提升生产力、但并非核心业务的其他 SaaS，我确实觉得，你要么决定自己维护，要么把这件事交给另一个团队，而那个团队每个醒着的小时都在琢磨这件事。所以我确实觉得，随着 AI 的发展，竞争越来越激烈，节奏也越来越快。我认为每家公司都应该专注于自己的头号价值主张，而人们很容易忘记维护这些东西的成本，你懂吧？Host: Mm yeah. Okay, this is going to sound like my own plug, but I do think that like it's the whole like build versus buy. I think is like the question that everyone is constantly asking for software products. And I do think that you know, when you're deciding what to do whether it's documentation or any other SAS that you have within your company to like improve your productivity or like not your main thing, I do think that there is like it's you're either deciding to maintain something yourself or like offload that to another team that's literally spending like every waking hour thinking about it. and so I do think like things are getting more competitive with AI, things are moving faster with AI and I think like every company should be focused on whatever their number one value proposition is and it's so easy to kind of forget about the maintenance costs of things, you know?

我觉得这就像我们在企业销售中经常看到的情况：“嘿，大家，我们在黑客马拉松期间做了这个，但没人愿意维护它。”就像，如果我们也在做你们现在做的事，我们就会去打造你们的业务，你懂吧？所以我觉得，真的要记住这一点——而且我觉得一直以来都是这样。只是 AI 把这一点凸显得更明显了。就像：“嘿，我们可以把它做出来，但我们想维护它吗？”我觉得这也是我们在开发产品时会问自己的问题。因为我们什么都可以做。I think that's like what we're kind of seeing a lot in enterprise sales as well where it's like "Hey guys, we built this during a hackathon and nobody wants to maintain it." Like what like like if we were in the business of doing what you guys are doing, we would be building your business, you know? and so I think that like really remembering and I think this has always been the case. I think just AI like accentuates this a lot more. It's like "Hey, we could build it, but like do we want to maintain it?" and I think that this is a question that we also ask ourselves when building products. Cuz we could be building everything.

嘉宾：是的，这确实很有道理。尤其是智能体领域发展得这么快，而且它们抓取网站之类的方式也各不相同，感觉各种标准多得数不清。所以，能持续了解最前沿的情况，并且不用自己费心维护，就很有价值。我在黑客松项目之类的事情上亲身见识过这一点。所以，没错，我完全同意。Guest: Yeah, that that makes a lot of sense. And especially with how fast-moving the agent space is and the way and manner in which they crawl sites and whatnot. It feels like there's a million different standards and whatnot. So, having just like a constant view on what the state of the art is and having that handled without having to do the maintenance. I've seen that firsthand with hackathon projects and whatnot. So, yeah, couldn't agree more.

主持人：太好了。非常感谢你抽出时间，林肯。Host: Awesome. Thanks so much for your time, Lincoln.

嘉宾：是的，当然。感谢大家耐心听完。谢谢。Guest: Yeah, absolutely. Appreciate everyone sitting through this. Thank you.