5 Trends That Defined AI Engineering at World’s Fair 2026定义 2026 年 AI 工程领域的 5 大趋势
At this year's AIE World’s Fair, AI engineering entered a new phase: building systems around agents, rather than just building with agents.在今年的 AI 工程师世界博览会（AIE World’s Fair）上，AI 工程进入了一个新阶段：重点不再仅仅是使用智能体（Agent）进行构建，而是围绕智能体构建系统。
swyx’s note: thanks to Richard for covering AIE while I was working on the conference itself! Make sure you have opted into the AINews feed to get our weekday updates. AIE next returns to NYC, Oct 12-14, with a heavy focus on AI in Finance this year.swyx 的笔记：感谢 Richard 在我忙于会议筹备期间报道 AIE！请确保您已订阅 AINews 动态，以获取我们的工作日更新。AIE 下一站将于 10 月 12 日至 14 日在纽约举行，今年的重点将是 AI 在金融领域的应用。
AI engineering has come a long way in three years. When swyx coined the term “AI engineer” in June 2023, he was giving a name to a new kind of developer emerging from the big bang of large language models. It seems like ancient history now, but remember when we called the intersection of AI and software development “prompt engineering”? That was just months before swyx’s reframing.AI 工程在过去三年中取得了长足进步。2023 年 6 月，当 swyx 首次提出“AI 工程师”这一术语时，他是在为大语言模型爆发后涌现出的一种新型开发者命名。现在回想起来，这似乎已是遥远的往事，但您还记得我们曾将 AI 与软件开发的交叉领域称为“提示词工程”（Prompt Engineering）吗？那距离 swyx 重新定义该领域仅过去数月。
The latest AI Engineer World’s Fair showed just how much the field has matured. Whether or not “AI engineer” has become a formal job title everywhere is almost beside the point. The engineering practices that have developed around AI over the past three years — building coding agents, designing harnesses, managing context, evaluating model outputs, and orchestrating increasingly autonomous systems — are becoming part of mainstream software development.最新的 AI 工程师世界博览会展示了该领域已变得多么成熟。“AI 工程师”是否已在各地成为正式的职位名称，其实并不重要。过去三年围绕 AI 发展起来的工程实践——构建编码智能体、设计工具包（harness）、管理上下文、评估模型输出以及编排日益自主的系统——正逐渐成为主流软件开发的一部分。
Rather than focusing on individual announcements at AIEWF, this post will pick out five larger trends that show where AI engineering stands in 2026.本文将不再关注 AIEWF 上的个别发布，而是挑选出五个更大的趋势，以展示 2026 年 AI 工程的发展现状。
1: The focus shifts from agents to the systems around them1：重心从智能体转向其周围的系统
One of the clearest ways to see how AI engineering has evolved is to compare two essays by former OpenAI researcher, and now co-founder of Thinking Machines Lab, Lilian Weng. Her influential 2023 article, LLM Powered Autonomous Agents, described the anatomy of an LLM agent in terms of planning, memory and tool use. AutoGPT, BabyAGI and GPT-Engineer were among her examples — proof-of-concept systems that suggested autonomous agents might soon become practical.观察 AI 工程演变最直观的方式，是对比前 OpenAI 研究员、现 Thinking Machines Lab 联合创始人 Lilian Weng 的两篇文章。她在 2023 年那篇极具影响力的《LLM 驱动的自主智能体》（LLM Powered Autonomous Agents）中，从规划、记忆和工具使用三个维度描述了 LLM 智能体的结构。AutoGPT、BabyAGI 和 GPT-Engineer 都是她列举的案例——这些概念验证系统表明自主智能体可能很快就会变得实用。
Her new 2026 essay, Harness Engineering for Self-Improvement, takes a very different perspective. Rather than focusing on the agent itself, Weng argues that the system surrounding the model has become just as important: the harness that manages workflows, context, permissions, evaluation, persistent state and continuous improvement. In other words, AI engineering has moved beyond prompting models toward engineering reliable systems around them.她在 2026 年发表的新文章《用于自我完善的工具包工程》（Harness Engineering for Self-Improvement）则采用了截然不同的视角。Weng 认为，围绕模型的系统已变得与模型本身同等重要，重点不再仅仅是智能体本身，而是管理工作流、上下文、权限、评估、持久状态和持续改进的“工具包”（harness）。换句话说，AI 工程已经超越了模型提示词阶段，转向围绕模型构建可靠的系统。
This shift was very much top of mind at AIEWF. I don’t think AutoGPT — the buzzy autonomous agent project everyone was talking about in 2023 — was even mentioned this year. Instead, the conversation revolved around Claude Code, Codex, Gemini CLI, Cursor, Warp and all the infrastructure needed to make coding agents dependable in production.这种转变在 AIEWF 上体现得淋漓尽致。我不认为 AutoGPT（2023 年人人都在谈论的那个热门自主智能体项目）今年还有被提及。相反，讨论的焦点围绕着 Claude Code、Codex、Gemini CLI、Cursor、Warp 以及使编码智能体在生产环境中可靠运行所需的所有基础设施。
I remember being turned off by the AutoGPT buzz at the 2023 event, mainly because all the discussions seemed to focus on removing humans from the equation. But over the past few years we’ve learned that complete agent autonomy is not only unreliable, it isn’t even desirable — especially at scale. So it was a relief that at AIEWF, agents were largely positioned as augmenting the AI engineer, rather than replacing them.我记得 2023 年大会上 AutoGPT 的热潮曾让我感到反感，主要因为当时的讨论似乎都集中在如何将人类排除在流程之外。但过去几年我们意识到，完全的智能体自主性不仅不可靠，甚至是不受欢迎的——尤其是在大规模应用中。因此，在 AIEWF 上，智能体被定位为辅助 AI 工程师而非取代他们，这让我感到欣慰。
During the OpenAI keynote on day 2 at AIEWF, Romain Huet emphasized this point. Using tools like OpenAI’s Codex, Huet argued, engineers can more easily collaborate with agents. As he put it, “software ate the world, and then AI ate software, but now what we’re here to say is that the AI engineers are eating the world.”在 AIEWF 第二天的 OpenAI 主题演讲中，Romain Huet 强调了这一点。Huet 认为，通过使用 OpenAI 的 Codex 等工具，工程师可以更轻松地与智能体协作。正如他所言：“软件吞噬了世界，随后 AI 吞噬了软件，但我们今天想说的是，AI 工程师正在吞噬世界。”
Despite the growing power of AI engineers, there’s also a sense that even the frontier companies don’t fully understand how their models are evolving — and so how much control can engineers truly have over them? In a separate keynote, Anthropic’s Thariq Shihipar talked about how their latest model, Claude Fable, is like an organic system — “models are grown, not designed.” There’s a “capability overhead,” he said, where “Claude gets smarter in a spiky way.”尽管 AI 工程师的力量日益增强，但人们也感觉到，即使是前沿公司也并不完全了解其模型是如何演变的——那么工程师又能对它们有多少真正的控制权呢？在另一场主题演讲中，Anthropic 的 Thariq Shihipar 谈到他们的最新模型 Claude Fable 就像一个有机系统——“模型是生长出来的，而非设计出来的。”他说，存在一种“能力开销”，“Claude 的智能化过程是突发式的”。
[AINews] The Field Guide to Fable
[AINews] Fable 实战指南![[AINews] The Field Guide to Fable](https://substackcdn.com/image/youtube/w_728,c_limit/9fubhllmsBU)
While we congratulate (friend of the show!) General Intuition on their new model and (friend of the show!) Shunyu Yao on their new model, and the world awaits the release of GPT-5.6 Sol Ultra, people are racing to find the limits of Fable 5 before the虽然我们祝贺 General Intuition（我们的节目好友！）推出了新模型，也祝贺 Shunyu Yao（我们的节目好友！）推出了新模型，且全世界都在等待 GPT-5.6 Sol Ultra 的发布，但人们正竞相在 Fable 5 发布之前寻找它的极限。
All the more reason to build systems for agentic development, so that we can evaluate and monitor the outputs.这更充分地证明了我们需要为智能体开发构建系统，以便对输出结果进行评估和监控。
2: Loop engineering is the new control layer2：循环工程（Loop Engineering）是新的控制层
By the end of the first morning of keynotes at AIEWF, it was clear that “loops” was the buzzword du jour of the event. Overuse of the term aside, it did highlight a key point of tension around AI engineering: how much control should agents have, and where should humans remain in the loop?在 AIEWF 第一天上午的主题演讲结束时，很明显“循环”（loops）已成为本次大会的流行语。抛开该术语的过度使用不谈，它确实突显了 AI 工程中一个关键的矛盾点：智能体应该拥有多少控制权？人类又应该在什么环节保持参与？
One approach a lot of leading engineers are now taking is putting themselves in an “outer loop” — to oversee the largely autonomous work being done by agents in an inner loop.许多领先的工程师现在采取的一种方法是将自己置于“外循环”（outer loop）中，以监督智能体在“内循环”（inner loop）中进行的大部分自主工作。
Roland Gavrilescu is co-founder and CEO of Introspection, a new company building infrastructure for deploying self-improving systems. In an interview with Latent Space, he explained how the concept of “autoresearch” provides the necessary feedback structure for agent loops:Roland Gavrilescu 是 Introspection 的联合创始人兼 CEO，该公司致力于构建部署自我完善系统的基础设施。在接受 Latent Space 采访时，他解释了“自动研究”（autoresearch）的概念如何为智能体循环提供必要的反馈结构：
“You can think of the system as having an inner loop and an outer loop. The inner loop is the primary system interacting with users and performing the work. Autoresearch is more concerned with the outer loop: another system that studies and maintains the primary system.““你可以将系统视为拥有内循环和外循环。内循环是与用户交互并执行工作的主要系统。自动研究则更多关注外循环：即另一个研究并维护主系统的系统。”
The outer loop can include feedback signals, evals and human input. So it might still be largely autonomous, but the point is it is a method of oversight for the primary agent loop. Former Google engineering leader Addy Osmani had a nice line relating to this, saying that “agents can run much more of the inner execution loop, but that outer loop is still engineering.”外循环可以包含反馈信号、评估和人类输入。因此，它可能在很大程度上仍然是自主的，但其核心在于它是主智能体循环的一种监督方法。前谷歌工程领导者 Addy Osmani 曾有一句精辟的总结：“智能体可以运行更多的内执行循环，但外循环仍然属于工程范畴。”
The term “loop engineering” came up multiple times during AIEWF, suggesting that it’s the human AI engineer’s responsibility to build these loop systems. Even the “ClawFather” Peter Steinberger, creator of OpenClaw, makes a point of putting himself in the outer loop. In the OpenAI keynote, he explained that “the agent runs the inner execution loop; I set the direction and I make decisions in the outer loop.”“循环工程”这一术语在 AIEWF 期间多次出现，这表明构建这些循环系统是人类 AI 工程师的责任。即使是 OpenClaw 的创建者、被称为“ClawFather”的 Peter Steinberger，也特意将自己置于外循环中。在 OpenAI 的主题演讲中，他解释说：“智能体运行内执行循环；我负责设定方向并在外循环中做出决策。”
On the final day, an on-stage debate was held to determine whether fully autonomous agents were capable of managing loops in reality. Dex Horthy from HumanLayer claimed that “the hype is outrunning the discipline.” He wasn’t against loops, per se, noting that Kubernetes is built on control loops — “but they’re deterministic loops.” Geoffrey Huntley, creator of the Ralph Loop, admitted that loops were “frontier thinking,” but he had a wonderful analogy for the audience to ponder:在最后一天，大会举办了一场现场辩论，旨在确定完全自主的智能体是否真的有能力管理循环。来自 HumanLayer 的 Dex Horthy 声称“炒作超过了严谨性”。他本身并不反对循环，并指出 Kubernetes 就是建立在控制循环之上的——“但它们是确定性的循环。”Ralph Loop 的创建者 Geoffrey Huntley 承认循环是“前沿思想”，但他给观众留下了一个值得深思的精彩类比：
“[We’re] kind of like locomotive engineers now. That’s our job: to keep the locomotive on the rails.”“我们现在有点像火车司机。这就是我们的工作：让火车保持在轨道上。”
3: AI engineering enters the enterprise3：AI 工程进入企业
This way of working with AI tools is starting to make its way into enterprises, typically via a new role called a “forward deployed engineer” (FDE) — where engineers work directly with organizations to implement AI capabilities.这种 AI 工具的使用方式正开始进入企业，通常通过一种名为“前沿部署工程师”（Forward Deployed Engineer，简称 FDE）的新角色实现——工程师直接与组织合作实施 AI 能力。
Natalie Meurer, who leads FDE at Sierra, told Latent Space that implementing AI into organizations typically requires a lot of orchestration. “Every enterprise we work with wants to know how it can maintain everything its agentic ecosystem is capable of doing,” she said. “It needs to manage all the integrations and all the teams that contribute to the agent.”在 Sierra 负责 FDE 团队的 Natalie Meurer 告诉 Latent Space，将 AI 引入组织通常需要大量的编排工作。“我们合作的每一家企业都想知道如何维护其智能体生态系统所能做的一切，”她说，“它需要管理所有的集成以及为智能体做出贡献的所有团队。”
In her session at AIEWF, Cursor’s Pauline Brunet spoke about what their FDEs look to achieve in each engagement:在 AIEWF 的会议上，Cursor 的 Pauline Brunet 谈到了他们的 FDE 在每次合作中力求实现的目标：
“When [we] walk away at the end of the engagements — and we, in our case, have deployed cloud agents, long-running agents, automations, [and] we’ve built applications on top of our Cursor SDK — that when we walk away, it is a strict ROI for them. That means they’re not gonna turn things off when we leave.”“当我们在合作结束时离开——就我们而言，我们已经部署了云智能体、长效智能体、自动化流程，并且在我们的 Cursor SDK 之上构建了应用程序——我们要确保这能为他们带来明确的投资回报（ROI）。这意味着我们离开后，他们不会关掉这些系统。”
Another term used regularly at the conference was “software factory.” At Cursor, “a software factory means long-running agents helping people throughout that entire process,” said Brunet. This is basically what her team of FDEs is responsible for implementing, sitting alongside their customers’ engineers.大会上经常使用的另一个术语是“软件工厂”。Brunet 说，在 Cursor，“软件工厂意味着长效智能体在整个过程中为人们提供帮助”。这基本上就是她的 FDE 团队负责实施的内容，他们与客户的工程师并肩工作。
Where human engineers fit into a software factory is a key issue for enterprises. Warp CEO Zach Lloyd explained that organizations need to choose which parts of the lifecycle to automate, and where humans should be brought into the loop.人类工程师在软件工厂中的定位是企业的关键问题。Warp CEO Zach Lloyd 解释说，组织需要选择生命周期中的哪些部分进行自动化，以及在何处引入人类参与循环。
“You choose your repositories, the parts of the software lifecycle you want to automate, and the points where humans should be brought into the loop,” Lloyd told us, regarding his company’s new software factory platform, Oz. “Different organizations and codebases will have different preferences. Do you fully automate code review? Do you have humans review certain high-risk changes?”“你需要选择你的代码库、想要自动化的软件生命周期部分，以及人类应该介入循环的节点，”Lloyd 在谈到他公司的新软件工厂平台 Oz 时说道，“不同的组织和代码库会有不同的偏好。你是要完全自动化代码审查？还是让人类审查某些高风险变更？”
Another concern for enterprises is managing their unique organizational data in AI systems. Prukalpa Sankar from Atlan spoke at the conference about “context engineering,” explaining in a tweet that it’s important to consider “how context flows from your business systems into a shared company brain, then out to agents, copilots, and apps through MCP, APIs, and retrieval.”企业关心的另一个问题是管理 AI 系统中独特的组织数据。Atlan 的 Prukalpa Sankar 在会上谈到了“上下文工程”（context engineering），她在推文中解释说，考虑“上下文如何从业务系统流入共享的公司大脑，然后通过 MCP、API 和检索流向智能体、副驾驶和应用程序”非常重要。
Finally, lest we think enterprises are all-in on agents, Cursor’s Brunet pointed out that enterprise adoption of AI “is still concentrated among early adopters.” So finding “the right champions inside an organization” is a challenge for FDEs at this stage.最后，为了防止我们认为企业已经全面拥抱智能体，Cursor 的 Brunet 指出，企业对 AI 的采用“仍然集中在早期采用者中”。因此，在这个阶段，为 FDE 寻找“组织内部的合适拥护者”是一个挑战。
4: Coding agents replace IDEs as the developer interface4：编码智能体取代 IDE 成为开发者界面
Perhaps the biggest practical change since the first AI Engineer Summit is how developers interact with AI on a daily basis.自第一届 AI 工程师峰会以来，最大的实际变化或许是开发者日常与 AI 交互的方式。
In 2023, AI-assisted programming largely meant GitHub Copilot completing the next few lines of code. Most developers were still writing almost everything themselves, using AI as an intelligent autocomplete. But now we have tools such as Claude Code, Codex, Gemini CLI, Cursor and Warp. These “coding agents” can typically understand a broader objective, explore a codebase, modify multiple files, run tests, debug failures and iterate on their own work before presenting it back to the developer.2023 年，AI 辅助编程在很大程度上意味着 GitHub Copilot 补全接下来的几行代码。大多数开发者仍然几乎自己编写所有内容，仅将 AI 作为智能自动补全工具。但现在我们有了 Claude Code、Codex、Gemini CLI、Cursor 和 Warp 等工具。这些“编码智能体”通常能够理解更广泛的目标、探索代码库、修改多个文件、运行测试、调试故障，并在将结果呈现给开发者之前自行迭代工作。
The trend of coding agents now extends to web development too — with the recent release of Vercel’s eve, which the company calls an “agent framework,” comparable to its popular open source React framework, Next.js.编码智能体的趋势现在也扩展到了 Web 开发领域——随着 Vercel 最近发布了 eve，该公司将其称为“智能体框架”，可与他们流行的开源 React 框架 Next.js 相媲美。
Vercel’s Chief of Software, Andrew Qu, told Latent Space at AIEWF that agents are effectively a new type of software. “They [agents] are not as predictable as web applications,” he explained. “The infrastructure can look similar, but the interaction, interface and outputs are much more dynamic.”Vercel 的软件主管 Andrew Qu 在 AIEWF 上告诉 Latent Space，智能体实际上是一种新型软件。“它们（智能体）不像 Web 应用程序那样可预测，”他解释道，“基础设施看起来可能相似，但交互、界面和输出要动态得多。”
Qu added that the job of building a framework for agent development is far from over. “A year ago, we did not know sandboxes would become so important, or how much demand there would be for secure code execution and long-running jobs,” he said. “As we learn more from production, there will be much more to build.”Qu 补充说，构建智能体开发框架的工作远未结束。“一年前，我们不知道沙箱会变得如此重要，也不知道对安全代码执行和长效作业的需求会有多大，”他说，“随着我们从生产环境中学习到更多，还有很多东西需要构建。”
This brings us back to the software factory trend, when developers are managing multiple agents. Charlie Holtz, CEO of Conductor, reminded the AIEWF audience that regardless of the coding harness, human engineers should always remain in control.这又回到了软件工厂的趋势，即开发者需要管理多个智能体。Conductor 的 CEO Charlie Holtz 提醒 AIEWF 的观众，无论编码工具包如何，人类工程师始终应该保持控制权。
“I don’t want the future to be built around factories,” Holtz said. “I want to feel like a human, I want to be in the flow, I want to be in front of an orchestra, waving my baton.”“我不希望未来建立在工厂之上，”Holtz 说，“我希望感觉自己是人类，我希望处于心流状态，我希望站在管弦乐队前，挥舞我的指挥棒。”
There was a sense during the conference that AI engineers aren’t yet aligned on which term is more appropriate: software factories or orchestras? Even Geoffrey Huntley, a loopmaxxing advocate, cautions about getting ahead of ourselves when it comes to automation:在会议期间，人们感觉到 AI 工程师对于哪个术语更合适尚未达成共识：是软件工厂还是管弦乐队？即使是“循环狂热”倡导者 Geoffrey Huntley，在谈到自动化时也告诫不要操之过急：
“My biggest concern is that this time next year at the conference, we’re going to see a whole bunch of folks saying, our factories failed, our loops failed. These are things that we are still yet to figure out.”“我最大的担忧是，明年此时在大会上，我们会看到一大群人说，我们的工厂失败了，我们的循环失败了。这些都是我们仍需解决的问题。”
5: Every agent platform is building around skills5：每个智能体平台都在围绕“技能”构建
One of the talking points of the conference was “skills,” a concept Anthropic popularized when it introduced “agent skills” to Claude last October. To borrow Addy Osmani’s definition, skills “encode the workflows, quality gates, and best practices that senior engineers use when building software.”大会的话题之一是“技能”（skills），这是 Anthropic 去年 10 月将“智能体技能”引入 Claude 时推广的一个概念。借用 Addy Osmani 的定义，技能“编码了资深工程师在构建软件时使用的工作流、质量门禁和最佳实践”。
At AIEWF, Vercel’s Andrew Qu said that skills were “useful as portable, on-demand knowledge.” Introspection co-founder Roland Gavrilescu declared that AI engineering has shifted “from agent tools to agent skills.”在 AIEWF 上，Vercel 的 Andrew Qu 表示，技能作为“可移植的、按需获取的知识非常有用”。Introspection 联合创始人 Roland Gavrilescu 宣称，AI 工程已经“从智能体工具转向了智能体技能”。
In a session on the main stage, Philipp Schmid from Google DeepMind showed how using skills (and other declarative Markdown files) allows developers to use “agents without code.” His main point was that skills reduce the need for orchestration code, which up till recently was typically done using Python. His conclusion:在主舞台的一次会议上，来自 Google DeepMind 的 Philipp Schmid 展示了使用技能（以及其他声明式 Markdown 文件）如何让开发者实现“无代码智能体”。他的主要观点是，技能减少了对编排代码的需求，而这在不久前通常是使用 Python 完成的。他的结论是：
“Agents are just files. We write markdown files to extend capabilities. Agents can learn from those, can create their own files.”“智能体就是文件。我们编写 markdown 文件来扩展能力。智能体可以从中学习，也可以创建自己的文件。”
Paul Bakaus, who used to work for Google but now runs a company called Renaissance Geek, has created an entire project around agent skills. Impeccable is an open source design skills system that gives coding agents a vocabulary for improving interfaces. He even advocates for “skill engineering” as a discipline in its own right.曾在谷歌工作、现经营一家名为 Renaissance Geek 公司的 Paul Bakaus，围绕智能体技能创建了一个完整的项目。Impeccable 是一个开源设计技能系统，为编码智能体提供改进界面的词汇表。他甚至主张将“技能工程”作为一门独立的学科。
In an interview with Latent Space, Bakaus argued that most skills — and indeed most models — are not very creative. “They converge in one direction, and if everybody uses the same skill to do frontend design work or something like that, everything ends up looking the same,” he said.在接受 Latent Space 采访时，Bakaus 认为大多数技能——实际上大多数模型——并不是很有创造力。“它们向一个方向收敛，如果每个人都使用相同的技能来做前端设计工作，最终一切看起来都会是一样的，”他说。
Apparently there’s also such a thing as “skills hell,” which Matt Pocock said is comparable to previous developer frustrations — like frameworks hell. In a virtual presentation, Pocock provided a detailed checklist for writing skills, which you can see in the video below. In a nutshell, he advises writing fewer and smaller skills, and putting more thought into structure.显然还有一种东西叫“技能地狱”（skills hell），Matt Pocock 说这与之前的开发者挫折——比如框架地狱——相当。在一次虚拟演示中，Pocock 提供了一份编写技能的详细清单，您可以在下面的视频中看到。简而言之，他建议编写更少、更小的技能，并在结构上投入更多思考。
In a closing keynote, Y Combinator president Garry Tan implored the audience to use skills and other “AI native” approaches at their own startups or employers. Talking about business functions like sales, support and finance, Tan said that “the AI native companies that I see inside YC encode all of that as skills, written procedures that their agents execute, and they hire engineers whose job it is to maintain those skills, to do the work the skills can’t do yet.”在闭幕主题演讲中，Y Combinator 总裁 Garry Tan 恳请观众在他们自己的初创公司或雇主那里使用技能和其他“AI 原生”方法。在谈到销售、支持和财务等业务职能时，Tan 说：“我在 YC 内部看到的 AI 原生公司将所有这些都编码为技能，即由其智能体执行的书面程序，他们雇佣工程师，其工作就是维护这些技能，去完成技能尚无法完成的工作。”
But again, there’s a danger in relying too much on what agents autonomously do. As AIEWF attendee Tyler Brown noted on X, “autonomy without structure creates as much slop as leverage.” One of his learnings from the conference was to “re-visit and re-implement your skills”:但同样，过度依赖智能体自主行为存在风险。正如 AIEWF 与会者 Tyler Brown 在 X 上指出的那样，“没有结构的自主性会产生与杠杆效应同样多的混乱。”他从会议中学到的一点是“重新审视并重新实施你的技能”：
“Each time there’s a new model release, it’s as if you have a kid that grows from middle school to high school. You have to change the curriculum for them to get the benefits of the new model.”“每次有新模型发布，就好像你有一个孩子从初中升入高中。你必须改变课程，他们才能从新模型中获益。”
Agent engineering at scale大规模智能体工程
It’s been three full years since The Rise of the AI Engineer and the first AI Engineer Summit. Looking back, it really is striking how much the conversation has evolved. Three years ago, the focus was on proving that LLMs could act as autonomous agents at all (and the answer at that time was usually no). AutoGPT, prompt engineering, and early orchestration frameworks like Langchain dominated the discussion back then.距离《AI 工程师的崛起》和第一届 AI 工程师峰会已经整整三年了。回首往事，对话的演变程度确实令人震惊。三年前，重点是证明 LLM 能够作为自主智能体运行（当时答案通常是否定的）。那时，AutoGPT、提示词工程和早期的 Langchain 等编排框架主导了讨论。
Now that agents not only work, but have proven they can scale, this year’s AI Engineer World’s Fair was able to concentrate on the bigger problems: building reliable systems, orchestrating teams of agents, managing context, evaluating outputs and integrating AI into production software.现在，智能体不仅能工作，而且已证明可以规模化，今年的 AI 工程师世界博览会得以专注于更大的问题：构建可靠的系统、编排智能体团队、管理上下文、评估输出以及将 AI 集成到生产软件中。
The term “AI engineer” may have started life as a new job title, but at AIEWF 2026 it felt more like a description of where software engineering itself is heading. Whether developers call themselves AI engineers, software engineers or Forward Deployed Engineers, they’re increasingly working with the same set of ideas: coding agents, harness engineering, designing loops, and orchestration.“AI 工程师”这个术语可能最初是一个新职位名称，但在 AIEWF 2026 上，它更像是对软件工程本身发展方向的描述。无论开发者称自己为 AI 工程师、软件工程师还是前沿部署工程师，他们越来越多地使用同一套理念：编码智能体、工具包工程、设计循环和编排。
