Artifacts in Claude Code, and the open question of sharing outside your org.

What artifacts in Claude Code are

Artifacts in Claude Code let the agent turn what just happened in a session into a live, interactive web page. Anthropic's examples are dashboards, incident timelines, PR walkthroughs, and checklists, the kinds of things you would otherwise paste into a doc or a channel. The page is built, in Anthropic's words, using the full context of your session, including your codebase, your connectors, and the conversation itself. So it is not a generic export; it is shaped by what the agent already knows about your work.

Two details make it feel alive rather than static. First, updates land in place: when Claude Code updates an artifact, the open page refreshes, so a teammate watching a long-running task sees it change without reloading. Second, each artifact keeps version history you can restore from, and all of them sit in a gallery. The result is closer to a living view of an agent's work than a one-shot file.

It runs from the Claude Code CLI and the desktop app, and the pages themselves are viewable in any browser, subject to the access rules below.

One boundary worth stating, because it sets expectations: an artifact is a page, not an app. Per Anthropic's docs it cannot call external APIs at view time, accept or store form submissions, load scripts or styles from outside the page, or serve multiple routes. In other words it is a self-contained static page, which is exactly the shape that travels well if you ever need to host it somewhere else.

How sharing and access work

This is the part worth reading carefully, because it defines what the feature is for. Anthropic is explicit on three points:

• Private by default. Every artifact is private to its author by default.
• Org-only viewing. Artifacts are viewable only by authenticated members of your org, and, in Anthropic's words, cannot be made public.
• Admin-governed. Admins manage access with an org-level toggle and role-based scoping.

So "share it with your teammates and your organization directly from the page" is the sharing model in full. There is no public link, no link-only mode, and no external-viewer mode. A viewer has to be an authenticated member of your Claude organization. That is a deliberate design for internal work, and it is consistent with how the feature is positioned.

On availability, it is in beta for Claude Team and Enterprise orgs. On Team plans it is on by default; on Enterprise an admin must enable it in the organization's admin settings. It is not described as available to Pro or individual accounts at launch.

What it is great at

Taken on its own terms, this is a strong answer to a real problem: the output of an agent session is usually trapped in a terminal or a transcript, and getting it in front of teammates means copying, pasting, and reformatting. Artifacts skip that.

• Session-aware, not generic. Because the page is built from your codebase, connectors, and the conversation, it reflects the actual work rather than a blank template.
• Live, not a snapshot. The refresh-in-place behaviour means a long task can be watched as it unfolds, which is exactly what an incident timeline or a build dashboard wants.
• Versioned. History and a gallery mean an artifact is durable and recoverable, not a throwaway.
• Org-scoped access that matches the use case. For internal dashboards and walkthroughs, "only people in our org can see this" is the right default, and admin role-scoping fits how companies actually gate internal tools.

For a Team or Enterprise org that lives in Claude Code and wants to surface an agent's work to colleagues, this is a clean fit, and an open primitive like ours does not replace it.

The open questions: external sharing, domains, export

The questions people ask cluster at the edges of that internal model. Here is what the announcement says, and where it is silent.

Can you share an artifact with someone outside your org? No, not as announced. Anthropic states plainly that artifacts cannot be made public and are viewable only by authenticated members of your org. If you need a client, a contractor, a candidate, or anyone without a Claude seat in your org to see the page, the access model does not cover that case, and you would have to reach for a different channel.

Can you put it on your own domain? Custom domains are not mentioned. Artifacts are hosted by Anthropic and viewed at their URL. This may arrive later, and it is reasonable to expect demand for it, but the launch does not describe attaching your own domain. The honest reading is "not documented," not a flat no.

Can you export it or self-host it? Export, code download, and self-hosting are not mentioned. The page is hosted by Anthropic, and the announcement does not lay out a path to move it elsewhere. That could change; for now there is no documented exit.

None of this is a criticism of the feature for its stated purpose. Internal artifacts generally do not need a public URL, a vanity domain, or portability. Those become real considerations only when the page has to leave the org, reach someone without a seat, or move. If that is your situation, it is worth knowing the announcement does not cover it.

Three "Claude artifacts" features, untangled

It is easy to conflate three different things Anthropic now ships under the word "artifacts." They are not the same:

• Claude.ai artifacts are created in a chat on claude.ai and can be shared publicly. If you have been sharing Claude artifacts, this is usually the one you mean.
• Live Artifacts live in Cowork and are persistent dashboards that re-query your connected apps and refresh when you open them. We cover those in what are Claude Live Artifacts.
• Artifacts in Claude Code, this post, are built from a coding session and are org-only; they cannot be made public.

The sharing rules differ across the three, so the one that matters for "can I send this to someone outside the company?" is which surface you made it on.

Where this leaves open tools like Stacktree

Full disclosure: we build Stacktree, so treat this as us describing where we sit, not neutral advice. Stacktree solves a narrower, more open problem than Artifacts in Claude Code, and the two address different needs.

Stacktree is a publish primitive for agent-made HTML, exposed over MCP, so it works across Claude Code, Cursor, Codex, and Claude.ai rather than inside one product. Its sharing model is the inverse of org-scoping: a page is private by default, and the unguessable URL is itself the credential, so a viewer needs no account and does not have to belong to any organization. You can add a password, an email-domain gate with magic-link verification, or end-to-end encryption; map a custom domain on the Pro plan; replace a page in place with update_site; and self-host the whole stack on your own Cloudflare account, since it is source-available. The trade is scope: Stacktree hosts static HTML only, with no server logic or session-aware live data layer. So if you want a live, session-aware internal page for your Claude org, Artifacts in Claude Code is built for that; if you need to send an agent-made page to someone outside the org, put it on your own domain, or keep the ability to take it with you, an open primitive is the closer fit. They are not substitutes.

What to watch

This reflects Anthropic's announcement as of June 2026, and a beta feature is exactly the kind that moves. A few things would be worth rechecking:

1. An external or public sharing mode. Anthropic is currently explicit that artifacts cannot be made public; if that changes, the most-asked question here is answered.
2. Custom domain support. A common next step for hosted-page products, and it would change how durable an artifact URL feels.
3. Export or portability. A documented way to download or move an artifact would address the lock-in question directly.
4. Wider plan availability. It is Team and Enterprise beta today; Pro or individual access would broaden who this reaches.
5. Use beyond Claude Code. Today it is built from a Claude Code session; if the surface widens, the picture changes again.

If any of these land, the answers above will need updating. For now, this is the announced state of the feature.