← Claude 官方博客
产品Claude 官方博客· 06-22 · 10:38

Claude Code 现已支持 artifacts

Claude Code now supports artifacts

打开原文约 27 分钟读

Preview your in-progress work as a live, interactive web page—built from your full session context and shareable with your team.

Starting today, Claude Code can capture work progress as an artifact, which turn Claude Code's work into live, shareable visual pages— including PR walkthroughs, system explainers, dashboards, and release checklists—that update themselves as your session works.

A Claude Code session can range from investigating an incident to refactoring a service to analyzing months of data. Artifacts translate the work into a web page anyone can open and explore, like a pull request walkthrough, a dashboard you can filter and sort, or even a release checklist that fills itself out as work gets done. Artifacts make it easier to collaborate on shared work, so teams can spend more time building and less time communicating status updates.

Built on the context from your session

Claude Code builds an artifact using the full context of your session, including your codebase, your connectors, and the conversation itself. A single incident page can bring together the failing test and the function behind it from your code, the error spike from a connected monitoring tool, and the root-cause reasoning from the session you just ran. With artifacts, you don't need to wire up data sources or stand up infrastructure. You ask for a page, and Claude Code builds it from what already exists.

Live pages that update in place

When Claude Code updates an artifact, the open page refreshes in place and teammates see the updates the moment they’re published. Every publish is a new version at the same link, with version history so you can restore at any time, and a gallery lets you browse and manage all artifacts you've made.

From our internal testing, one of our most common use cases has been debugging. These typically look something like: An engineer kicks off an incident investigation before standup. Claude Code works through the logs and publishes an artifact: a timeline, the suspect commits, and an error-rate chart. She shares the link with her team from the page header. By the time standup begins, Claude has republished it twice as the investigation progressed, incorporating the latest information. With artifacts, team members and stakeholders don’t have to "walk us through what the agent found" because they're all looking at the same view, with the same context.

Private to your organization

Every artifact is private to its author by default. When you're ready, share it with your teammates and your organization directly from the page. Artifacts are viewable only by authenticated members of your org and cannot be made public. Admins manage access with an org-level toggle and role-based scoping, set retention policies, and get org-wide visibility through the compliance API.

Getting started

Ask your session for an artifact — or just ask for something visual, here are some ideas by role:

Claude Code builds the page and gives you a link. Open it in your browser or the desktop app, share it from the header—updates publish to the same URL automatically.

Availability

Artifacts is available in beta to Claude Team and Enterprise orgs, from the Claude Code CLI and desktop app, with pages viewable in any browser.

Claude Code 现已支持 artifacts

原文:Claude Code now supports artifacts

*把进行中的工作预览成一个实时、可交互的网页——它由你完整的会话上下文构建,并可分享给团队。*

从今天起,Claude Code 可以把工作进展沉淀成一个 artifact,从而把 Claude Code 的工作变成实时、可分享的可视化网页——包括 PR(pull request,拉取请求)走查、系统说明、仪表盘、发布检查清单——而且这些页面会随着会话工作的推进自动更新。

一次 Claude Code 会话,可以从排查一起事故,到重构一个服务,再到分析好几个月的数据。artifacts 把这些工作转化成一个任何人都能打开、随意探索的网页,比如一份 pull request 的逐步走查、一个可以筛选和排序的仪表盘,甚至一份随工作完成而自动勾选的发布检查清单。artifacts 让大家在共享的工作上协作更轻松,团队因此能把更多时间花在动手做事上,少花在沟通进度更新上。

基于你的会话上下文构建

Claude Code 会用你会话的完整上下文来构建一个 artifact,这包括你的代码库、你的 connectors(连接器)以及对话本身。一个事故页面,就能把以下信息汇到一处:来自你代码的失败测试和它背后的函数、来自所连监控工具的错误激增、以及你刚跑完的那次会话里的根因推理。有了 artifacts,你不需要去打通数据源、也不需要搭建基础设施。你只要开口要一个页面,Claude Code 就会用已经存在的东西把它构建出来。

原地更新的实时页面

当 Claude Code 更新一个 artifact 时,已经打开的页面会原地刷新,队友在更新发布的那一刻就能看到。每一次发布都是同一个链接下的一个新版本,并带有版本历史,你随时可以恢复到任意版本;还有一个图库(gallery),让你浏览和管理自己做过的所有 artifacts。

在我们的内部测试中,最常见的用例之一就是调试。它们通常是这样的:一位工程师在 standup(站会)前启动了一次事故排查。Claude Code 梳理完日志,发布了一个 artifact:一条时间线、几个可疑的提交,还有一张错误率图表。她从页面顶栏把链接分享给团队。等到站会开始时,随着排查推进,Claude 已经把它重新发布了两次,每次都纳入了最新信息。有了 artifacts,团队成员和相关方不必再让人「向我们复述一遍 agent 查到了什么」,因为大家看的是同一个视图、同一份上下文。

仅对你的组织私有

每个 artifact 默认仅对它的作者私有。等你准备好了,可以直接从页面把它分享给队友和你的组织。artifacts 只有你组织里通过认证的成员才能查看,无法被设为公开。管理员通过组织级开关和基于角色的权限范围来管理访问、设置留存策略,并通过 compliance API(合规 API)获得组织范围内的可见性。

上手指南

向你的会话要一个 artifact——或者干脆要点可视化的东西。下面是一些按角色划分的点子:

  • 法务 / 开源:直接从仓库出发,对每一个依赖做一次许可证审计,标记出 copyleft。*「构建一个 artifact,列出每一个第三方依赖及其许可证,并标记出任何 copyleft 的。」*
  • 隐私:一张数据流图,标出代码中个人数据在哪里被采集、存储和记录日志。*「把我们在整个代码库里触及个人数据的地方追踪出来,做成一个 artifact,供隐私评审使用。」*
  • 安全:每条发现都链接到确切的那一行代码,让修复毫不含糊。*「把这次评审里的认证问题发现做成一个 artifact,每一条都链接到代码。」*
  • FinOps(云成本运营) / 平台财务:从你的 infrastructure-as-code(基础设施即代码)中梳理出云资源和成本驱动因素。*「把我们的云资源从 Terraform 里梳理成一个 artifact,按服务分组,标出主要的成本驱动项。」*
  • 软件工程师:一份审阅者真正跟得上的 PR 或 bug 走查,从 diff 以及它周围的代码里提取出来。*「做一个 artifact,带我走一遍这个 PR——diff、推理过程,以及我测了些什么。」*
  • 设计师与前端工程师:为某个界面给出几个 UX 方向,每个都基于你真实的组件构建,这样你选中的那个就是能直接上线的。*「给我一个 artifact,包含这个注册表单的 5 种 UX 变体,都用我们的组件库构建。」*
  • 资深工程师与架构师:一张图,画出一个服务实际是怎么拼到一起的——它取自真实的导入关系图,而不是白板上画的。*「把支付服务实际是怎么拼起来的画成一个 artifact,从代码出发。」*
  • SRE(站点可靠性工程师)与 on-call(值班):一个随你排查而不断生长的事故页面,最终变成 postmortem(事故复盘)。*「把这起事故变成一个 artifact——时间线、可疑提交、来自我们监控的错误激增——并在我一步步排查时重新发布它。」*
  • 工程经理:一个页面,呈现真正交付了什么,由已合并的 PR 构建而来。*「构建一个 artifact,呈现我团队这周合并了什么,从 PR 里取,按项目分组。」*

Claude Code 把页面构建好,给你一个链接。在浏览器或桌面端 app 里打开它,从顶栏把它分享出去——更新会自动发布到同一个 URL。

可用范围

artifacts 以 beta 形式向 Claude Team 和 Enterprise 组织开放,可从 Claude Code CLI 和桌面端 app 使用,页面在任意浏览器中均可查看。

*立即开始* *使用 Claude Code。*