Claude Blog 采集 (2026-08-04)¶
共采集 2 篇文章
📋 文章索引¶
- How the product designer who built Claude Design uses it to explore ideas before building them - Jul 24, 2026 (评分: 9.5)
- Bringing MCP 2026-07-28 to Claude - Jul 28, 2026 (评分: 9.0)
How the product designer who built Claude Design uses it to explore ideas before building them¶
来源: Claude Blog 发布日期: Jul 24, 2026 采集时间: 2026-08-04 价值评分: 9.5/10 正文字数: ~5395 字符
摘要¶
Nate Parrott, a product designer at Anthropic, shares how he uses Claude Design (in beta) to explore, iterate on, and share visual ideas early, from product prototypes to slide decks and animations.
正文内容¶
Nate Parrott, a product designer at Anthropic, shares how he uses Claude Design (in beta) to explore, iterate on, and share visual ideas early, from product prototypes to slide decks and animations.
In the fall of 2025, I was the only product designer on Claude Code for VS Code , working with two engineers to reimagine everything Claude Code does for a friendly interface outside the terminal. We shipped the beta at the end of September, Opus 4.5 arrived in November, and the Claude Code team started shipping fast and aggressively. The engineers were shipping far more than before, while I was still delivering at the pace I always had. I needed to find a way to catch up. Claude Code runs in the terminal, where everything is text-based, and my first attempt treated it that way: I copied output into Claude, added screenshots, and asked, "Here's a feature we want to add. Why don't you design it?" The results weren't good. For a month or so, as a side project, I kept looking for ways to improve Claude’s design output. Giving Claude an HTML playground Eventually I stumbled onto the answer: Claude is really good with HTML. We think of HTML as the format for websites, but it's also a rich, interactive visual medium: anything you can make in a slide deck, a video file, or a PDF, you can make in a web page. So I prompted Claude to make HTML, and gave it a split-view interface where you could chat on the left and see the output on the right. That was useful, but product design is driven by applying knowledge of the product and brand you work on, so as a next step I spent a while distilling the essence of Anthropic's brand (the fonts, colors, assets, and principles our products use) into prompts. This way, when I type my prompt into the tool, the output is compliant with the Anthropic brand guide. I put all that into a small internal prototype and shared it with the team. Product designers picked it up immediately for interactive prototypes. Making a click-through prototype in traditional design tools means mocking up every state of every screen and wiring them together by hand. Here, you hand Claude your assets and say: make it work. Every artifact it delivers has a link you can share the way you'd share a doc. How Claude Design became a medium for visual work I first realized how compelling Claude Design was at an idea pitch session during an Anthropic Labs team offsite: every person there threw together slides using it, often in the middle of the meeting before their turn to present. That session convinced the Labs team to staff it, and Claude Design went from a side project to a real project. We stopped describing it as a tool for product mockups. Claude Design became a tool for producing any kind of visual communication: slide decks, landing pages, one-pagers you print as a PDF, emails, animations, visuals to share on social media. I think of it as one click above product design: you collaborate with Claude on visuals whose main job is communication and ideation. As models get better at vision, so does the range and quality of work Claude Design can do. Our latest Opus-class model, Claude Opus 5 , is better than previous Opus models at reading the charts, diagrams, and screenshots, making it powerful when paired with Claude Design for creating presentation-worthy decks and memos. What Claude Design is not meant to do Claude Design doesn't have an image model and isn’t built for image generation, so it's a poor fit for logo design—though that hasn’t stopped people from trying. The better approach here is to bring in the logo and assets you already have. The rest of the product works the same way: Claude creates options and starting points so you don’t have to stare at a blank canvas, and you choose what's good on its own, or as a combination of multiple versions. And if you're shipping production software, stick with Claude Code. Claude Code is for coding; Claude Design is for the other parts of the design work: early ideation, collaboration, or getting buy-in on a direction before anyone commits to building it. The two work together round-trip, so you can sync a prototype you started in Claude Code to Claude Design for iteration and editing on the canvas, or hand off a prototype you’re ready to build from Claude Design to Claude Code. As models get better at building production software, the work that matters most moves earlier in the process: having good ideas, getting everyone aligned, and collecting feedback while an idea is still early. How I use Claude Design in my daily work I use Claude Design every day for what you’d call bread-and-butter design work: wireframing early ideas, or generating 15 versions of a flow to collect feedback from colleagues. Some recent examples from my own work: The Claude Design intro animation. The animation that plays when you sign up for Claude Design was made in the tool itself, but not directly: I'm not an animator, so I first had Claude Design build me a bespoke video editor, then used that editor to make the animation.
Explore more product news and best practices for teams building with Claude.
Transform how your organization operates with Claude
Product updates, how-tos, community spotlights, and more. Delivered monthly to your inbox.
Please provide your email address if you'd like to receive our monthly developer newsletter. You can unsubscribe at any time.
采集自 Claude Blog，由 collect_claude_blog.py 自动采集
Bringing MCP 2026-07-28 to Claude¶
来源: Claude Blog 发布日期: Jul 28, 2026 采集时间: 2026-08-04 价值评分: 9.0/10 正文字数: ~3515 字符
摘要¶
The MCP 2026-07-28 spec is live, moving the Model Context Protocol to a stateless core with standardized extensions and hardened auth. Support is rolling out across Claude products soon. See what's new and how MCP is advancing in Claude.
正文内容¶
The fifth spec release of the Model Context Protocol, MCP 2026-07-28 , is live today. The latest spec moves MCP to a stateless core, while hardening authorization and graduating official extensions. Support is being rolled out across Claude products. What's new in MCP MCP recently surpassed 400M monthly SDK downloads, a 4x increase this year, and has become the industry standard for connecting AI agents to applications. MCP 2026-07-28 is one of the most significant spec releases to date: Stateless core. MCP moves from a bidirectional stateful protocol to a request/response model. Servers can now deploy on serverless and edge infrastructure. This simplifies the experience of building MCP servers for Claude and scaling their usage as they grow in adoption. Standardized extensions. MCP Apps and Tasks now ship under a versioned extensions framework, giving developers a formal path to add capabilities like interactive UIs and long-running work without changing the core protocol. Auth hardening. Authorization now aligns with production OAuth 2.0 and OIDC deployments, so MCP servers connect to enterprise identity systems like Entra or Okta without workarounds. Companies across the ecosystem have been building on the new spec alongside the MCP community since beta:
See the MCP 2026-07-28 release announcement for full details on the new spec. Advancing MCP in Claude Claude now lists over 950 MCP servers in the connectors directory , used by millions of people every day. This year we shipped support for new protocol extensions alongside features that make MCP easier to build on and deploy: MCP Apps let servers render interactive UI directly in the conversation. Users can see what a connector is doing and work with it inline, without switching tabs. Enterprise-managed auth lets admins provision MCP connectors for their whole organization through their identity provider. Admins authorize a connector once, users inherit access through their existing IdP groups, and it's connected on first login: zero-touch setup for the end user. Observability for developers building connectors gives published connectors in our directory a dashboard showing how they perform across Claude product surfaces. Developers can use it to track adoption, diagnose errors and latency, and break down usage by product. MCP tunnels (research preview) connect Claude to MCP servers inside a private network without exposing them to the public internet. Teams can bring internal tools to Claude with no inbound firewall rules, no public endpoints, and no IP allowlisting on the origin. The stateless core, standardized extensions, and hardened auth in 2026-07-28 will help developers bring more applications to Claude, with a lower-friction, more consistent end-user experience. We'll continue investing in MCP as an open standard alongside the community, and in the Claude features that make MCP more accessible and effective in production. Getting started Explore the spec and SDKs to get started. Support is rolling out across Claude products soon. If you’re planning to submit your MCP server to Claude’s connectors directory , you can learn more here .
Explore more product news and best practices for teams building with Claude.
Transform how your organization operates with Claude
Product updates, how-tos, community spotlights, and more. Delivered monthly to your inbox.
Please provide your email address if you'd like to receive our monthly developer newsletter. You can unsubscribe at any time.
采集自 Claude Blog，由 collect_claude_blog.py 自动采集