Anthropic brings Artifacts to Claude Code, letting teams share live pages from coding sessions
Quick Answer
Anthropic's Claude Code now features 'artifacts', interactive web pages that capture and share live coding session results.
Quick Take
These pages automatically update with session context and maintain a version history, enhancing collaboration among teams.
Key Points
- Claude Code introduces interactive web pages called 'artifacts' for coding sessions.
- Artifacts automatically update with changes and maintain a version history.
- Teams can share live results, enhancing collaboration and communication.
- The feature pulls from the full session context for better clarity.
- This update aims to streamline coding workflows and improve team productivity.
📖 Reader Mode
~1 min readClaude Code now supports artifacts, a feature already familiar from the Claude chat. It lets you turn the results of a Claude Code session into interactive web pages and share them with your team. The pages are generated from the full session context: code, connected tools, and chat history. When something changes, the page updates automatically at the same URL, complete with version history.
To create an artifact, just ask for it—or for anything visual—during your session. Claude Code then gives you a link you can open in a browser or the desktop app and share directly via the header.
Anthropic says use cases range from PR walkthroughs and incident timelines to license audits and architecture overviews. Artifacts are private by default and only visible to authenticated members of your organization. Admins control access through roles and retention policies. The feature is available as a beta for Claude Team and Enterprise customers and works with both the Claude Code CLI and the desktop app.
— Originally published at the-decoder.com
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from The Decoder
See more →
An AI model programmed nonstop for 19 days on a single MirrorCode task that cost $2,600 to run
Epoch AI's MirrorCode benchmark reveals Claude Opus 4.7 as the leader with a 56% solve rate, reconstructing a 16,000-line toolkit in 14 hours. Despite this, all models tested struggle with the most complex tasks, highlighting limitations in current AI capabilities. The single task consumed $2,600 over 19 days, raising questions about cost-effectiveness in AI development.
