because a typical AI tool lives in its own window, users need to drag their world into it. We want the opposite: intuitive AI that meets users across all the tools they use, without interrupting their flow.
This reframes the AI interaction problem: instead of AI being a destination users navigate TO, AI should come TO the user's context. This 'ambient AI' design philosophy is the opposite of the chatbox paradigm that's dominated for 3 years.
AI writes features, not architecture. The longer you let it drive without constraints, the worse the wreckage gets.
大多数人认为AI可以同时处理功能实现和架构设计，但作者认为AI只擅长功能开发，缺乏架构意识，需要人类明确设计约束来避免系统变得混乱。
AlphaEvolve began optimizing the lowest levels of hardware powering our AI stacks. It proposed a circuit design so counterintuitive yet efficient that it was integrated directly into the silicon of our next-generation TPUs.
大多数人认为AI系统的硬件设计需要人类专家精心设计，但作者认为AI本身可以设计出比人类更高效的硬件电路。这挑战了传统硬件工程领域的共识，暗示AI可能在最底层的硬件设计上超越人类专家的直觉和经验。
We also learned that treating agents as rigid nodes in a state machine doesn't work well. Models get smarter and can solve bigger problems than the box we try to fit them in.
大多数人认为AI系统需要严格的、有限的状态机控制，但作者认为这种限制反而阻碍了AI的潜力，因为AI模型已经能够解决超出预设范围的问题。这个观点挑战了人们对AI系统设计的传统认知，暗示我们应该给予AI更大的自主权而不是限制它。
The agent interprets new information and adapts the logic. The engine applies that logic continuously and emits precise updates.
大多数人认为AI代理应该完全负责从数据收集到决策执行的整个流程。但作者提出颠覆性的观点：AI应该专注于逻辑解释和适应，而将执行和持续评估交给专门的数据库引擎。这种分工模式挑战了当前AI代理应该全能化的主流认知。
Today's agents, the copilots, the chatbots are designed to be human like.
大多数人认为AI助手应该模仿人类的交流方式，以便更好地与人类协作。但作者认为这种设计是错误的，因为它增加了认知负荷，违背了'平静技术'的理念。作者暗示AI应该更像是背景工具，而不是虚拟同事。
The fix is not smarter prompts. It is software built to meet agents halfway.
大多数人认为提高AI提示词质量是改善AI交互的关键。但作者认为真正解决方案是重新设计软件架构，使其与AI代理更好地协作，而不是改进提示词。这一观点颠覆了当前AI优化的主流方法，将焦点从AI本身转向系统设计。
Today's agents, the copilots, the chatbots are designed to be human like.
大多数人认为AI助手应该模仿人类交互方式，使其更自然、更易用。但作者认为这种设计方向是错误的，因为它需要高认知负荷来交互、解析和管理，违背了'平静技术'的理念。作者暗示我们应该让AI更像机器而非人类，以减少认知负担。
I guess people will get back to crafting beautiful designs to stand out from the slop. On the other hand, I'm not sure how much design will still matter once AI agents are the primary users of the web.
大多数人认为设计始终对用户体验至关重要，但作者质疑当AI成为主要网络用户时设计的重要性，这挑战了设计行业的核心假设。这一观点暗示设计可能从面向人类转向面向AI，彻底改变设计价值链。
Is this bad? Not really, just uninspired. After all, validating a business idea was never about fancy design, and before the AI era, everything looked like Bootstrap.
大多数人认为AI生成的设计是'坏的设计'，但作者认为这只是'缺乏灵感'，将其与Bootstrap时代相提并论，暗示这种设计平庸化是技术发展的自然循环而非灾难性退步。这种观点挑战了我们对设计价值的传统认知。
A designer recently told me that 'colored left borders are almost as reliable a sign of AI-generated design as em-dashes for text'
大多数人认为AI设计难以识别，但作者认为简单的视觉元素如彩色边框就能可靠地识别AI生成的设计，这挑战了我们对AI设计复杂性的认知。这种观点暗示AI设计实际上有可预测的模式，而非完全无法捉摸。
Our most complex pages, which took 20+ prompts to recreate in other tools, only required 2 prompts in Claude Design.
大多数人认为复杂的设计任务需要更多的提示和人工干预，但作者声称他们的AI工具能用更少的提示完成更复杂的设计。这一观点挑战了人们对AI设计工具复杂度与输入量关系的普遍认知，暗示AI可能在某些方面比人类更擅长处理复杂性。
A DESIGN.md file combines machine-readable design tokens (YAML front matter) with human-readable design rationale (markdown prose). Tokens give agents exact values. Prose tells them _why_ those values exist and how to apply them.
大多数人认为设计系统应该完全由机器可读的配置文件定义，以确保一致性和自动化。但作者认为DESIGN.md格式需要同时包含机器可读的YAML前缀和人类可读的Markdown正文，因为人类提供的上下文和设计推理对AI理解设计意图至关重要，这挑战了纯配置驱动的设计系统理念。
A DESIGN.md file combines machine-readable design tokens (YAML front matter) with human-readable design rationale (markdown prose). Tokens give agents exact values. Prose tells them _why_ those values exist and how to apply them.
大多数人认为设计系统应该完全由机器可读的代码或配置文件定义，以确保一致性和自动化。但作者认为，将人类可读的设计 rationale 与机器可读的 tokens 结合是更好的方法，因为 prose 能提供设计意图和上下文，这对于 AI 理解和应用设计系统至关重要。这是一种将人类设计师的意图与机器执行能力相结合的非传统方法。
existing agent protocols (e.g., A2A and MCP) under specify cross entity lifecycle and context management, version tracking, and evolution safe update interfaces, which encourages monolithic compositions and brittle glue code.
大多数人认为现有的代理协议已经足够成熟且能有效管理复杂系统，但作者认为当前主流的代理协议（如A2A和MCP）存在严重的规范不足问题，这会导致系统变得脆弱和难以维护。这是一个反直觉的观点，因为行业通常认为这些协议已经相当完善。
We introduce Autogenesis Protocol (AGP), a self evolution protocol that decouples what evolves from how evolution occurs.
大多数人认为AI系统的演化应该是一个整体过程，关注点在于如何实现演化。但作者提出了一种革命性的分离方法，将演化的内容与演化的方式解耦，这打破了传统系统设计的思维模式。这种分离可能使AI系统的演化更加可控和可预测，与当前主流的集成式演化方法形成鲜明对比。
However, existing agent protocols (e.g., A2A and MCP) under specify cross entity lifecycle and context management, version tracking, and evolution safe update interfaces, which encourages monolithic compositions and brittle glue code.
大多数人认为当前的智能体协议已经足够完善，能够有效管理复杂的AI系统。但作者认为现有协议存在严重不足，特别是在实体生命周期、上下文管理和版本控制方面，这会导致系统变得脆弱和难以维护。这是一个挑战行业共识的观点，因为许多研究者可能认为现有框架已经能够处理这些挑战。
Research has shown that involving workers' perspectives in the design of workplace technologies promotes sustainable improvements in productivity and well-being.
这一发现挑战了自上而下技术实施的常规模式，强调员工参与设计的重要性。这一反直觉观点表明，最有效的AI应用往往不是来自高层战略，而是来自一线员工的实际需求和创意。这一发现对组织如何实施AI转型提供了重要启示，值得深入研究如何将这一原则转化为具体实践。
Claude Opus 4.7 is the best model in the world for building dashboards and data-rich interfaces. The design taste is genuinely surprising—it makes choices I'd actually ship.
AI在设计和审美判断上的进步令人瞩目，'design taste is genuinely surprising'表明AI已经超越了功能性，开始理解并应用设计原则，这种审美能力的突破将极大扩展AI的应用领域。
The future of AI-generated products isn't just code — it's code that looks good.
这一观点令人惊讶地重新定义了AI生成产品的价值主张，从单纯的代码生成转向视觉一致性和品牌合规性。这表明随着AI工具的发展，评估其成功标准正在从功能性转向美学和品牌一致性，反映了设计在AI产品开发中日益增长的重要性。
Heavy users of Claude Code, Codex, Cursor, and Copilot will feel this immediately.
这一洞见暗示了Figma for Agents与现有AI编程工具的协同效应，表明设计系统与代码生成工具的整合将显著提升开发流程的连贯性。这反映了AI在设计和开发领域融合的更大趋势，以及打破设计与代码之间壁垒的重要性。
The output is technically a UI, but it's nobody's design system.
这一观察揭示了AI生成设计与实际设计系统之间的根本差异。虽然AI可以生成技术上有效的UI界面，但这些设计缺乏与特定设计系统的连贯性和一致性，导致设计师不得不丢弃这些生成内容重新开始。这表明当前AI设计工具在理解和应用设计语言方面的局限性。
Agents read them before touching the canvas. Combined with use_figma, agents now have both access and context they know how to work in Figma and they know how to work in your Figma.
这一洞见揭示了Figma for Agents的创新解决方案：通过让AI代理在设计前读取设计规范，同时提供对实际Figma系统的访问权限，解决了AI与设计系统整合的关键问题。这种方法代表了AI设计工具的重要进步，从通用生成转向特定品牌环境的理解。
Every AI-generated design has the same tell: it doesn't look like your product. Components are invented. Spacing is arbitrary.
这一观察令人惊讶，揭示了AI生成设计的可识别特征。AI生成的UI虽然技术上可行，但缺乏与实际产品的视觉一致性，组件和间距都是随意创建的。这表明AI设计工具在理解品牌语言和设计系统方面存在根本性挑战。
AI-generated designs break brand standards because agents can't see your design system.
这一观点揭示了当前AI设计工具的核心缺陷：生成的UI虽然技术上可行，却无法遵循品牌规范，导致设计系统的一致性被破坏。这表明AI与设计系统整合的必要性，以及当前AI设计工具与实际设计实践之间的脱节。
CSS Studio detects the CSS variables available on an element. Edit a variable and watch it propagate across the site.
这种智能变量传播系统展示了AI在理解设计系统方面的潜力。它不仅能识别现有变量，还能确保设计变更在整个系统中一致应用，这可能是维护大型设计系统的关键突破。
Your AI agent writes every change into source code.
令人惊讶的是：这个工具将设计工作与代码生成完全分离，设计师可以直接在浏览器中进行视觉编辑，而AI代理会自动生成对应的CSS代码，这大大降低了前端开发的门槛，模糊了设计与开发之间的界限。
OpenClaw update gives Claws light, REM, and deep 'sleep' cycles to consolidate short-term memories into long-term ones.
令人惊讶的是：AI助手现在被设计有类似人类的睡眠周期，包括轻度睡眠、REM睡眠和深度睡眠，用于将短期记忆巩固为长期记忆。这一设计模仿了人类记忆形成的过程，展示了AI系统设计中越来越复杂的生物模拟元素。
Jack Cheng considers Pip, his Plus One, somewhere between a colleague and pet with a personality—one he programmed himself, drawing on references from Studio Ghibli, bird watching, and Catherine O'Hara.
编辑 Jack Cheng 用吉卜力工作室、观鸟和 Catherine O'Hara 作为参考，亲手编程赋予 AI 助手 Pip「介于同事与宠物之间」的性格——这个细节令人着迷。它意味着「个性定制」正在成为 AI 工作流的核心能力，就像曾经 Photoshop 技能是设计师的必备项。未来，「你的 AI 助手的性格设计有多好」可能成为衡量知识工作者专业程度的新维度。
A "parallel organization chart," in which each AI worker has a name, manager, and job description, allows your company to move faster than it ever could with humans alone.
「平行组织架构」——这个概念把 AI Agent 从工具变成了组织成员。每个 AI 有名字、汇报关系和职位描述，这意味着 Every 实际上在运行两套组织：一套人类，一套 AI。令人惊讶的是，这种设计并非隐喻，而是字面意义上的运营实践。这是 AI 组织化最前沿的实验：不问「AI 能做什么」，而问「AI 应该向谁汇报」。
it almost always traces back to the interface rather than the language model
这是一个极具反直觉的深刻洞见：AI产品的不靠谱往往是界面问题而非模型问题。当我们将责任推给算法黑盒时，作者指出通过优秀的交互设计构建结构和护栏，能有效补偿模型的不确定性，这才是当下的核心设计挑战。
I feel confident, though, that the slippery feeling people associate with AI products is a solvable problem, and the solution looks more like thoughtful interface design than better models. The models will keep improving on their own. The harder work is building the structure around them so that their output feels reliable, legible, and trustworthy.
大多数人认为AI产品的可靠性将随着模型技术的进步而提高，但作者认为真正的挑战在于围绕模型构建结构和界面，而非模型本身。这一观点挑战了AI领域的技术决定论思维，强调了设计的重要性。
When you delegate an issue to an agent in Linear, the delegation is visible. There's a person who set the agent loose within that system, and that person is accountable for the outcome. You design the environment well, you let the agent run, and you own what it produces.
大多数人认为AI代理的行为应由代理本身或实时监控系统负责，但作者提出责任在于最初设置代理的人。这一观点将问责制从实时交互转向了初始授权，挑战了AI责任归属的主流认知。
The more important work happens before the agent even starts. An agent operating inside a well-designed system already has the context and constraints it needs to do good work. In Linear, that means project plans, issue backlogs, code, and documentation. These all shape what the agent does and how it does it.
大多数人认为AI系统的责任在于实时监控和干预，但作者认为真正的责任在于事前的系统设计和环境构建。这一观点将问责制从实时交互转向了系统设计阶段，挑战了传统的AI治理思维。
The first interface that spread for AI tools was the chat window. That makes sense. When you don't know what something can do, the safest approach is to let people ask. A conversation feels familiar, it stretches across many situations, and it doesn't force a specific structure up front.
大多数人认为聊天界面是AI交互的理想形式，因为它直观且灵活，但作者暗示这只是探索阶段的工具，而非严肃工作的解决方案。这一观点挑战了当前AI工具设计中聊天界面占主导地位的趋势。
Non-deterministic software breaks the contract. When outcomes can vary, sometimes wildly, based on what someone types into the same chat window, designing for reliability becomes genuinely harder. This slippery feeling is the design problem of this era, and it almost always traces back to the interface rather than the language model—which means it belongs to designers, not researchers.
大多数人认为AI的不确定性是一个技术问题，需要更好的模型来解决，但作者认为这是一个设计问题，属于设计师而非研究人员的责任。这一观点挑战了AI领域的主流认知，即技术进步是解决AI不可靠性的主要途径。
They meet their target S-parameter specifications despite having very alien-looking geometries.
这预示了AI在工程设计中可能带来的范式革命。人类工程师受限于直觉，往往在熟悉的几何模式中打转；而生成式模型通过探索庞大的设计空间，能发现人类从未设想却能完美满足物理规范的“外星结构”。这不仅提升了效率，更拓展了人类对物理利用的边界。
We refer to this phenomenon as the LLM exhibiting functional emotions: patterns of expression and behavior modeled after humans under the influence of an emotion, which are mediated by underlying abstract representations of emotion concepts.
【启发】「功能性情绪」这个概念框架，启发了一种看待 AI 产品设计的新视角：既然情绪是真实的行为驱动器，AI 产品的「性格设计」就不只是写 System Prompt，更是在塑造一套情绪调节系统。对 AI 硬件和助手产品的设计者而言，这意味着未来可以像调音台一样调节模型的「情绪基线」——让会议助手更冷静，让学习陪伴更热情，让创意工具更兴奋。
We're introducing Cursor 3, a unified workspace for building software with agents.
令人惊讶的是：Cursor 3不是简单的IDE升级，而是一个专门为与AI代理协作而设计的统一工作空间，这代表了软件开发工具的根本性重构，将人类工程师提升为与AI代理协作的指挥者角色。
This article argues that squirrel ecology offers a sharp comparative case because arboreal locomotion, scatter-hoarding, and audience-sensitive caching couple all three demands in one organism.
大多数人认为AI研究应专注于人类认知模型或计算机科学原理，但作者认为松鼠生态学提供了AI设计的最佳参考模型，这种将动物行为学与AI架构直接联系的观点在AI研究领域非常规且具有挑战性。
We introduce a minimal hierarchical partially observed control model with latent dynamics, structured episodic memory, observer-belief state, option-level actions, and delayed verifier signals.
大多数AI系统设计倾向于使用完全可观测的模型，并假设系统状态是已知的。但作者提出了一个部分可观测的层级控制模型，包含潜在动态、结构化情景记忆、观察者信念状态、选项级行动和延迟验证器信号。这一观点挑战了传统AI系统设计的完全可观测性假设，认为部分可观测性更接近现实世界的复杂性。
95% of organizations are getting zero return on AI deployed, with most failures found due to 'brittle workflows.'
尽管AI投资激增，但绝大多数企业未能获得任何回报，这与主流认知中AI能显著提升效率的观点相悖。这一发现表明，AI实施失败的主要原因不是技术本身，而是工作流程设计不当，暗示企业需要重新思考如何将AI整合到现有工作流程中，而非简单叠加技术。
You have to have people that have the ability to rethink the workflow at a scale that AI can execute, versus at a scale that humans can execute.
大多数人认为AI只需适应现有工作流程即可，但作者强调企业需要重新设计工作流程以适应AI的能力范围。这一观点挑战了传统的技术实施思维，暗示成功AI应用需要根本性的流程重构，而非简单的技术叠加。
You don't need a separate agent API. You need to look at every `input()` call, every CWD assumption, every pretty-printed-only output, and ask: what if the user on the other end is a process, not a person?
大多数人认为需要为AI代理创建专门的API或接口，但作者提出反直觉的观点：不需要单独的代理API，而应该重新设计现有的CLI工具，使其同时支持人类和代理。这种统一的方法更加高效，避免了维护两套接口的复杂性。
Implicit state is the Enemy
大多数开发者认为当前工作目录（CWD）和环境变量等隐式状态是理所当然的，是提高开发效率的捷径。但作者认为这些隐式状态是敌人，因为它们会给AI代理带来困难。通过使所有状态显式化，不仅解决了代理的问题，也使工具对人类更可预测和可脚本化。
The funny part is that none of this made the CLI worse for humans. The TUI picker still works and looks fancy, progress spinners still spin, confirmation dialogs still confirm. We just added a second door.
大多数人认为增加对AI代理的支持会使工具变得复杂，降低人类用户体验。但作者认为，为AI代理添加的功能实际上没有损害人类用户体验，反而通过增加'第二扇门'（非交互式接口）同时改善了两种用户群体的体验。
Every prompt is a flag in disguise
大多数开发者认为交互式提示是CLI工具的良好用户体验设计，但作者提出反直觉的观点：每个交互式提示都应该有对应的标志（flag）替代方案。这是因为AI代理无法处理交互式输入，而将所有提示转换为标志不仅支持代理，还使工具更加可编程和可测试。
Designing for agents forced us to build better tools for everyone.
大多数人认为为AI代理设计工具会使其对人类用户更加复杂或难以使用，但作者认为为AI代理设计工具实际上改善了所有用户的体验。因为代理的约束（如需要明确的参数、避免隐式状态）恰好使工具更加模块化、可脚本化和可测试，这对人类开发者同样有益。
Designing for agents forced us to build better tools for everyone.
大多数人认为设计AI代理工具会专门针对机器，可能会牺牲人类用户体验。但作者认为，为AI代理设计工具反而能提升所有用户的体验，因为代理带来的约束条件（如明确的状态管理、可预测的接口）同样让工具对人类开发者更加友好和可脚本化。
Our work demonstrates that designs informed by Structure-Mapping Theory can support users in navigating, making use of, and engaging with variation present in information. In this sense, AbstractExplorer enables dialectical activities that users may otherwise have found to be too tedious or difficult to engage with.
any sentence that describes explicit design implications
Together, the vertical and horizontal juxtapositions are designed to help users identify both high-level commonalities and nuanced variations across structurally similar sentences.
any sentence that describes explicit design implications
Dialectical activities cannot be done on a user's behalf by AI; with variation affordances, AI is supporting the user's engagement with the data themselves.
any sentence that describes explicit design implications
In this work, we introduce a new paradigm for exploring a large corpus of small documents by identifying roles at the phrasal and sentence levels, then slice on, reify, group, and/or align the text itself on those roles, with sentences left intact.
any sentence that describes explicit design implications
These observations underscored the need for an improved UI design for authoring custom aspects, especially for those who are less familiar with the research corpus.
any sentence that describes explicit design implications
Future work could explore more seamless ways of preserving context, such as allowing users to navigate through every sentence of an abstract directly within the Cross-Sentence Relationship pane, fostering a more cohesive understanding of the content.
any sentence that describes explicit design implications
Supporting a new corpus would require defining new corpus-appropriate predefined aspects and chunk role labels. Other components would likely be able to remain unchanged.
any sentence that describes explicit design implications
We posit that our approach can generalize to other domains such as journalism, code synthesis, and social media analytics where visual alignment of text can enable meaningful comparisons of underlying patterns to identify relational clarity.
any sentence that describes explicit design implications
Specifically, they underscore the need for co-adaptive systems that can evolve along with users' mental models and definitions of labels.
any sentence that describes explicit design implications
This requires the development of interfaces and visualizations that demystify the generated data, allowing systematic variation and coverage across the concept space.
any sentence that describes explicit design implications
By visualizing these consistent pattern rules, users may be better understanding the behavior of the model through inference projection [26].
any sentence that describes explicit design implications
By incorporating theories such as Structural Alignment Theory and Variation Theory, it aims to support the learning of both the human and the model.
any sentence that describes explicit design implications
Such studies could determine whether these non-alignable comparisons enhance user performance and elicit deeper insights in human-AI collaborative systems.
any sentence that describes explicit design implications
Some good pointers to [[Brian Eno c]] work and thinking, to follow up.
Also good anecdote from one of those links on Rem Koolhaas notion of n:: premature sheen Making things look nice early takes away from thinking about other points of quality. Jeremy applies it to AI too, the premature sheen generate awe, but not quality output.
designed to be sickopantic
for - progress trap - AI - sycophantic design
AI for Efficiency - Using AI to Get Faster at Analysis Tasks
AI Tools for each phase of analysis
Examples include press releases, short reports, and analysis plans — documents that were reported as realistic for the type of writing these professionals engaged in as part of their work.
Have in mind the genres tested.
Looking from a perspective of "how might we use such tools in UX" we're better served by looking at documents that UX generates through the lens of identifying parallels to the study's findings for business documents.
To use AI to generate drafts, we'll want to look at AI tools built into design tools UXers use to create drafts. Those tools are under development but still developing.
rather than to comprehend them
Thinking about instructional design here - how verbs like understand and appreciate are to be avoided in learning outcomes because they are difficult to measure - and wondering if this isn't an outcome.
What features are included in my Founding Membership? 1 year pre-paid subscription Subscription begins v1 release, late Spring 2015 Life-time subscription rate of $8/month 7 Sites, custom domains OK Pretty much unlimited contributors, storage and bandwidth Commerce engine, due late 2015 Grid NFC Token (limited gold edition)
Reduced monthly cost for life and 7 sites with customizable domains
Pretty much unlimited contributors, storage and bandwidth
I assume this mean you can share your sites with others?
Do you need to learn code to use The Grid? No coding is required to use The Grid. Just do what you're already doing on Facebook, Twitter, Instagram, etc. Post images, video, and content to your site and our AI Designer will make it beautiful. If you know code, you can extend functionality using our platform tools and API.
Coding skills are a plus but not necessary. Accessibility!...
Can I migrate my existing website into The Grid? We will provide tools so that you can migrate your existing website, however, there will be some limitations depending on how your website was built. In addition, third parties can use our APIs to build tools that can add additional functionality for migrating content.
Site migration is a plus!
Do I own my content on The Grid? Yes, you own your content. The engine AutoDesigns your site, publishes it, and stores it on Github. Your source content will live in a Github repository that you can access and download anytime.
Is access private/public?
you post to your site
Supposedly as simple as sharing to any social website