What is a Claude Artifact? Types, editing, and publishing

What is a Claude Artifact

A Claude Artifact is a substantial, self-contained output that opens in its own panel beside the conversation: a document, code file, diagram or interactive tool you inspect and revise while the chat continues. It starts private to you; Share opens it to people with a Claude account, and a public link anyone opens without one is left only for artifacts made in a chat before September 16, 2026. One thing decides most questions about artifacts: Anthropic uses the word for four experiences with different creation, sharing and plan rules.

Four things called an artifact

What counts as an artifact

Anthropic's artifact guide describes content that is substantial, self-contained, useful outside the immediate answer and likely to be edited or reused, typically over 15 lines: Markdown and text documents, code, single-page HTML, SVG, diagrams, interactive React components.

Interactive is not the same as AI-powered. A calculator whose JavaScript runs in the browser is interactive; it becomes AI-powered only when it calls Claude for its user.

Artifacts require Code execution and file creation in Claude's capability settings. If Claude keeps answering in the chat instead of opening the panel, check that first, then ask directly and name the deliverable:

Create this as a Claude Artifact. Keep the result self-contained so I can
revise, inspect, and share it separately from our conversation.

Create, edit, and keep the right version

1. Step 1CreateAsk for a self-contained artifact in a conversation, or start one from the Artifacts area.
2. Step 2ReviseDescribe the change in chat; for Markdown, select the exact text and use Edit with Claude.
3. Step 3InspectEdit an earlier message to branch the chat with its own artifacts; view, copy or download the code.
4. Step 4Export or distributeCopy, download or export it, then Share it with the people who need it.

Two things the steps do not show:

• Changing the artifact does not rewrite Claude's memory of the earlier content, so say when a revised fact should guide the rest of the conversation.
• Everything you make is saved to the Artifacts tab in the sidebar and stays private until you share it. Keep the source conversation anyway: it holds the context that produced the artifact.

Can you edit a Claude artifact?

Yes, in your own chat. Ask Claude for the change in the conversation that made it. In a doc or Markdown artifact, highlight the passage, click Edit with Claude and type the request. Artifacts started from a template (Docs, Slides, Design) also take direct typing.

Someone else edits your artifact only if you share it with Can edit access; Can view and Commenter cannot change it. A published legacy artifact, made in a chat before September 16, 2026, is not editable by its viewers. They copy its code into a new chat and get a separate artifact; your original stays as it was. The old Remix button is gone.

Either way the artifact stays inside Claude. Publish it to Birta and it becomes a page at its own address that no single conversation owns: Birta's agent edits it right in the app, or any agent you connect (Claude, ChatGPT, Codex). People comment on the page, and each edit is a new version at the same address.

Where the four meanings diverge

AI-powered artifact

Claude writes the tool, Anthropic runs it, and each user authenticates with their own account: no API key to paste, no shared limits. Artifacts can also use storage (a legacy artifact only after it is published) and outside connections: Anthropic documents 20 MB per artifact, text only, separate personal and shared stores (a shared store shows a confirmation on first use), and connections over the Model Context Protocol that every user authorizes for themselves. Why the connection belongs to the user rather than being a password inside the artifact.

Claude Code artifact

Anthropic's artifact documentation for Claude Code describes a self-contained .html, .htm or .md file published from a session to a URL like claude.ai/code/artifact/5fbea6f3-…, served from a sandboxed *.claudeusercontent.com origin, updated at the same address as the session continues, each publication a version. Good for annotated pull-request walkthroughs, investigation timelines and dashboards from session data. Documented limits: one page, no backend, no stored form submissions, no routes, strict external-request limits, 16 MiB rendered. A later session needs the URL to update the page; without it, it creates another artifact.

Cowork live artifact

An interactive HTML view around ongoing work that can refresh from connected services. Anthropic's live-artifact guide says it is a paid Claude Desktop feature that lives on the computer that created it: Pro and Max cannot share it, Team and Enterprise share inside the organization, and a recipient opens it in Claude Desktop with their own access to the connected services. Live means a working view that refreshes, not a public website.

What it means to publish an artifact

Anthropic's sharing guide now separates two actions, and which one you get depends on when the artifact was made.

• Share is the action for current artifacts, on every plan. You pick a level, Can view, Commenter or Can edit, and an audience: anyone with the link, people invited by email (beta on paid plans, up to 50 outside people per artifact), or, on Team and Enterprise, the whole organization. Every viewer needs a Claude account: "People without one can't open a shared artifact, even with the link."
• Publish is left for legacy artifacts, made in a chat before September 16, 2026, on Free, Pro and Max. It creates the one kind of link anyone uses without a Claude account, and only a published artifact can be embedded on a site whose domain the publisher lists. New legacy artifacts cannot be made.

So for anything made today, a link for people outside Claude does not exist on Anthropic's side. Before sharing, check the source material the link exposes and whether the artifact uses personal or shared storage.

Artifact, Project, Canvas

An Artifact is the output. A Project is the context workspace: chats, knowledge, instructions; it can contain chats that create artifacts. ChatGPT Canvas is the editing surface of another product. Choose a Project when several chats should share background; an Artifact when one result deserves its own revision surface.

When a Birta page is the better artifact

The artifact is the finished deliverable while the work is between you and Claude: a reviewable document, a prototype, a session walkthrough, a small tool whose Claude access model suits everyone using it. The moment a third person enters, the same conversation can publish it as a page on Birta, and the difference is what happens after you share the link.

Why an artifact link is not a website owns the ownership argument; the same-chat hosting guide has the transfer steps for a static artifact. For a single-page HTML artifact one person has to open today, paste the copied code into Publish HTML for a 24-hour link, no account.

Frequently asked questions