The article compares Kimi K2.6 with Claude Design, showing that Kimi not only generates complete front‑end websites and handles multi‑agent tasks but also does so at roughly one‑seventh the price, positioning it as a strong open‑source challenger in AI‑driven design.
This article introduces five open‑source AI‑powered tools—huashu‑design for high‑fidelity design generation, Kami for elegant static blogs, open‑codesign for multi‑model prototyping, agents‑md for professional AI coding assistance, and PostHog for self‑hosted product analytics—detailing their core features, usage steps, and ideal users.
The article compares Kimi K2.6 and Claude Design, showing that Kimi’s design and full‑stack generation capabilities, agent‑swarm parallelism, and roughly seven‑fold lower price give it a clear edge, while also providing a step‑by‑step tutorial for building a $10,000 website without code.
Claude Design’s preview launch on April 17 triggered a sharp drop in major design‑tool stocks, showcases a natural‑language driven workflow that generates interactive UI, PPT and code, reveals high token consumption and uniform styling limits, and has its full system prompts publicly leaked on GitHub, signaling a major shift in the AI‑design landscape.
Anthropic's Opus 4.7 upgrade brings a best‑practice Claude Code guide with a new default xhigh effort level and adaptive thinking, an open‑source desktop pet for BLE‑enabled hardware interaction, and Claude Design—a React‑powered AI design suite that streamlines UI prototyping, wireframing, and marketing asset creation.
The article verifies the authenticity of a 73 KB, 422‑line Claude Design system prompt leaked by the CL4R1T4S project, provides a faithful translation of its contents, and dissects the five‑layer design that enables high‑quality AI‑assisted design output.
Claude Design, Anthropic's new conversational design tool built on Claude Opus 4.7, reshapes AI‑assisted UI creation by moving design into a chat interface, integrating handoff to Claude Code, and challenging existing workflows from Figma to DIY design pipelines.
The article reveals Claude’s design system prompt, detailing its role as an expert designer, a six‑step workflow, context‑driven methodology, exploration modes, strict technical rules, built‑in collaboration tools, and ethical content guidelines that together enable the AI to produce high‑quality, user‑centric designs.
The author evaluates Lovart’s latest four updates—Brand Kit, Font Generator, Create Skill, and Export PSD—through three real‑world cases, showing how the AI agent ensures brand‑consistent visuals, streamlines design workflows, and enables reusable design assets for both personal and professional projects.
This guide explains why AI‑generated interfaces often look generic, introduces the open‑source Impeccable agent skill that supplies design references and anti‑pattern checks, and walks through its core components, slash commands, installation, CLI detection, and real‑world use cases for creating polished, production‑ready UI.
McKinsey’s “Building next‑horizon AI experiences” report reveals a “gen AI paradox” where high usage of generative and agentic AI yields few measurable business returns, and outlines four experience breakpoints and four design principles that can turn AI into a trusted, collaborative partner across organizations.
Google Labs’ March 18 update to Stitch introduces an AI‑native infinite canvas, a stronger design agent, voice‑driven collaboration, instant interactive prototyping, and the DESIGN.md system, dramatically lowering design barriers, speeding workflows, and sparking a debate on the future role of designers.
Adobe’s latest Firefly rollout adds custom style models, a Photoshop AI Assistant, and a seamless Image Editor, shifting focus from pure generation to giving creators control, refinement, and edit rights over AI‑produced visuals, a strategic move that could outweigh raw generative power.
The article analyzes why large‑language models like Claude, GPT‑4, and Gemini repeatedly generate nearly identical web designs, identifies four convergence dimensions (typography, color, motion, background), and presents a reusable "Skills" mechanism that injects expert design context to produce distinctive, high‑quality frontend outputs.
This guide introduces Pencil, an AI‑powered design tool that works like Figma's Make, explains how to install and configure it with large‑model agents, demonstrates prototype creation via natural language in Claude CLI, details the 14 MCP APIs, and shows how to install and use the find‑skills utility for rapid UI development.
In a 2026 Lenny's Podcast interview, Jenny Wen, Claude’s design lead at Anthropic, explains how AI has upended traditional design workflows, reshapes the role of designers, and reveals the tools, hiring priorities, and future UI‑chat hybrids that are shaping modern product creation.
A post‑holiday roundup of AI‑powered design tools reveals how Figma’s deep Claude integration, Google Flow’s full‑studio upgrade, Claude’s dedicated design plugin, Quiver AI’s vector generation, Paper Desktop’s code‑canvas sync, and Pencil’s swarm mode collectively accelerate design workflows and reshape the role of designers.
This article walks designers through an AI‑assisted workflow that converts a 2D floor plan into an immersive 3D walkthrough video, detailing each step from uploading the plan, crafting prompts, generating room‑level renders, to assembling a smooth camera‑driven video.
The author argues that traditional design hand‑off creates a persistent gap between mockups and final products, and proposes “direct design”—using AI code generators like Cursor or Claude Code to let product thinkers write and iterate code themselves, dramatically shortening feedback loops from weeks to minutes.
This article explains the concept of AI design "Skills", how they are structured, their origins, step‑by‑step creation process, practical usage examples, and the visual quality differences between AI generated with and without these Skills.
Uni-Layout introduces a unified framework that generates layouts across diverse tasks, simulates human evaluation with a novel feedback dataset, and aligns generation and assessment through dynamic margin preference optimization, achieving state‑of‑the‑art performance on multiple benchmarks.
The article reviews three open‑source AI tools—Claude Cowork for file‑based assistance, the LTX‑2 video generation model runnable on 8 GB GPUs via Pinokio, and SongGeneration Studio for end‑to‑end music creation—detailing their features, performance benchmarks, and usage steps for creators.
This article shows how AI can replace repetitive design tasks by breaking down requirements, generating multiple creative concepts, producing key visual elements and fonts, and offering detailed feedback, enabling designers to focus on strategy and creativity while cutting production time from days to hours.
The integration of ChatGPT with Adobe Photoshop and Express lets users describe design tasks in natural language, enabling AI-driven image generation, editing, and seamless export, which dramatically lowers the barrier to professional design and heralds a future where creativity is driven by conversation.
The article explores how AI tools have become permanent actors in the design workflow, extending creative cycles, and draws parallels to Wong Kar-wai’s iterative film‑making process, highlighting the director‑like role designers now play when selecting the perfect prompt‑generated image.
The article traces Microsoft’s experiments with virtual assistants—from the home‑metaphor of Microsoft Bob and the intrusive Clippy to modern AI‑driven Copilot—highlighting design lessons about timing, personalization, user control, and how advances in large language models finally make the long‑standing vision viable.
This guide walks through setting up the MCP protocol on macOS, configuring a server, installing Bun, linking Cursor 0.47+ with Figma, importing the plugin manifest, enabling MCP in Cursor, and using prompt templates to automatically generate high‑quality iOS fitness app designs, complete with screenshots and practical tips.
AI technologies are rapidly reshaping the design field by automating repetitive tasks, enabling data‑driven UX, powering generative tools like Figma’s AI features, Adobe Firefly, Midjourney, and AIGC platforms, while also raising new skill and ethical challenges for designers.
This article examines Baidu App’s newly launched “Pinch‑to‑Summarize” feature, detailing how AI‑powered content summarization combined with design thinking—through gesture triggers, refined guidance, immersive full‑page containers, dynamic feedback, and a smart visual language—enhances information retrieval efficiency and user experience across mobile scenarios.
As 2025 approaches, designers are exploring AI‑driven tools, immersive VR/AR experiences, dynamic graphics, lo‑fi aesthetics, and a resurgence of Chinese visual culture, all of which promise to redefine visual design by blending technology, cultural confidence, and innovative storytelling.
This article examines the three dominant AI integration forms on PC—immersive agents, accompanying co‑pilots, and embedded AI—detailing their capabilities, UI designs, real‑world examples, and design considerations to help creators choose the most effective approach for each scenario.
This article introduces the key AI design principles from Google’s People + AI Guidebook and Microsoft’s Human‑Centred AI guidelines, covering explainability, privacy, user‑focused value, scenario‑based services, easy activation, and clear communication to help create intelligent, humane user experiences.
This article explains how designers leveraged AI drawing tools like Midjourney to create a distinctive visual style for a housing‑mortgage loan landing page, detailing the prompt engineering, image generation, refinement, and final integration steps that boost efficiency while preserving creative control.
Leveraging AI image generation and LoRA model fine‑tuning, Baidu’s MEUX team reimagined the traditional 24 solar‑term cards in a fresh New‑Chinese aesthetic, blending cultural heritage, artistic composition, and modern visual effects to boost design efficiency and create a cohesive brand experience.
This article outlines ten practical principles for designing applications with large language models, emphasizing a model‑first mindset, precision through interactive disambiguation, clear division of code and model responsibilities, data quality, handling uncertainty, and recognizing the limits of LLMs to build robust, maintainable software.
This article walks you through using Midjourney AI to generate custom images, refine them in Photoshop, and publish personalized WeChat red‑envelope covers via the official Open Platform, highlighting practical tips, workflow details, and the benefits of AI‑assisted design.
Since 2021, NetEase Cloud Music’s Design Platform has evolved its design‑frontend workflow through three stages—engineering phase 1.0, phase 2.0, and the AI‑driven intelligent phase—by introducing the C2D2C (Code‑to‑Design‑to‑Code) methodology, unified design systems, LLM‑enhanced code, and generative AI tools, cutting communication overhead and boosting designer and developer productivity by up to 200 %.
In August, our team tackled two high‑traffic delivery campaigns, using AI‑assisted design to speed up visual creation, analyze user scenarios, and boost coupon redemption, ultimately demonstrating how Midjourney and Stable Diffusion can transform workflow efficiency while preserving brand identity.
This article details how 58.com’s design team leveraged AI tools such as Stable Diffusion, LoRA models, and prompt engineering to create a visually rich September recruitment landing page, outlining the project background, design strategy, technical exploration, and measurable results.
This article explores the rise of AI‑driven design, examines real‑world projects such as AI‑Soup, virtual jewelry, and e‑commerce checkpoints, explains diffusion model fundamentals, compares major tools, and discusses the opportunities and risks for creators and businesses adopting generative AI.
This article explores how AI-powered tools such as Midjourney and Photoshop enable designers to rapidly generate high‑quality 3D assets, streamline visual workflows, meet urgent client demands, and expand creative possibilities while emphasizing the need for solid aesthetic fundamentals.
This guide demonstrates how to leverage Midjourney AI to instantly generate e‑commerce website designs, mobile app interfaces, custom icons, and flat illustrations, offering practical prompts, color‑scheme tips, the knolling technique, and vector‑conversion methods for polished UI assets.
This article chronicles 58.com’s journey from a small brainstorming room to a full‑scale AI design platform, detailing the development of smart cutout, the BASNet segmentation model, custom loss functions, template editing, and the measurable business impact of the AI designer.
The article outlines Tongdun Technology's anti‑fraud challenges, presents their AI‑based detection solutions, and details design principles—including early warning, multi‑feature analysis, and human‑machine collaboration—to build a robust, multi‑layered fraud prevention framework.
This article examines the relationship between graphical user interfaces (GUI) and voice user interfaces (VUI), highlighting how VUI offers more natural, low‑learning‑cost interactions while GUI provides richer information, and outlines shared design principles—visibility, consistency, familiarity, and guidance—that can improve AI‑driven conversational products.
Alibaba unveiled its AI‑driven design platform Luban, which leverages massive data and machine‑learning algorithms to automatically generate high‑quality, personalized graphics at double‑digit scale, reshaping design workflows, boosting efficiency, and prompting a strategic shift for designers in the new commercial era.
