Claude Code Adds Artifacts: Live, Shareable Pages for PR Walkthroughs and Dashboards
Anthropic introduced Artifacts in Claude Code, letting Team and Enterprise orgs turn an in-progress Claude Code session into a live web page that updates as the session progresses and can be shared privately within the organization.
Claude Code now supports Artifacts: live web pages generated from a Claude Code session that you can share with teammates inside your organization. Anthropic frames the feature as a way to turn a session's work into something other people can understand at a glance, without needing a meeting to narrate what the agent found.
Key Takeaways
- Artifacts turn an in-progress Claude Code session into a live, shareable visual page such as PR walkthroughs, dashboards, and release checklists.
- Pages refresh as Claude Code republishes updates, so teammates see changes at the same link.
- Artifacts are private by default and viewable only by authenticated members of your organization.
- Availability: beta for Claude Team and Enterprise organizations, from the Claude Code CLI and desktop app, with pages viewable in any browser.
What Anthropic Means by "Artifacts" in Claude Code
Anthropic says Claude Code can "capture work progress as an artifact," turning Claude Code's work into "live, shareable visual pages" that update as the session works. The examples they call out include PR walkthroughs, system explainers, dashboards, and release checklists.
In other words: instead of shipping a wall of terminal output or a long markdown summary, Claude Code can publish an interactive page someone else can open and explore.
How Sharing Works
Anthropic describes artifacts as private to their author by default. When you're ready, you can share an artifact with teammates and your organization directly from the page.
Artifacts are not meant to become public posts. Anthropic explicitly says artifacts are viewable only by authenticated members of your organization and cannot be made public.
Versioning and Ongoing Updates
A key part of the pitch is that artifacts change as the agent keeps working. Anthropic says that when Claude Code updates an artifact, "the open page refreshes in place and teammates see the updates the moment they're published."
They also describe versioning: each publish creates a new version at the same link, with version history available to restore prior versions.
Why This Matters for Day-to-Day Dev Work
Claude Code is already good at doing a bunch of work while you wait: debugging, incident investigation, PR review prep, summarizing complex code paths. The bottleneck is often the handoff. If one engineer runs the session, everyone else needs a synchronous walkthrough to trust what happened.
Artifacts target that gap by giving the session a shareable output surface. Anthropic's incident example is straightforward: a single page can combine connected tool signals (like monitoring charts) with repo context (tests, functions, commits) and the agent's reasoning, then get republished as the investigation evolves.
Sources
- Claude (X): https://x.com/claudeai/status/2067671912038240487
- Anthropic blog: https://claude.com/blog/artifacts-in-claude-code
- Video: https://www.youtube.com/watch?v=m7TJqx8CYG8
Frequently Asked Questions
Who gets access to Artifacts in Claude Code?
Anthropic says Artifacts is available in beta to Claude Team and Enterprise organizations from the Claude Code CLI and desktop app, with pages viewable in any browser.
Are Claude Code artifacts public links?
No. Anthropic says artifacts are private to their author by default and viewable only by authenticated members of your organization, and they cannot be made public.
What types of outputs work well as artifacts?
Anthropic's examples include PR walkthroughs, system explainers, dashboards, and release checklists that update as the session does work.