Anthropic Adds Shareable Dashboard Feature to Claude Code

Anthropic has added a new feature called "Artifacts" to Claude Code for users of paid plans "Claude Team" and "Claude Enterprise." This feature outputs Claude Code's work results as an interactive webpage updated in real time, allowing multiple team members to monitor progress simultaneously by sharing a URL. A key characteristic is the ability to visualize in-house deliverables such as dashboards and app designs on the spot.

Traditionally, engineers needed to set up separate infrastructure or create screenshots and explanations to share development work status with non-technical team members. Artifacts eliminates this step by having AI directly read existing codebases or connected data sources to automatically generate webpages. The generated pages update their content in real time as the agent works, with the URL remaining unchanged while reflecting the latest state.

Security and management considerations are also in place. Each time a page is updated, a new version history is recorded, enabling rollback to previous states and change tracking from both desktop and mobile. The system allows engineers to continue work in a terminal on their device while team members in distant locations view the same page and understand the situation in real time. Note that Anthropic first introduced Artifacts to a consumer-facing chatbot in the summer of 2024, and this update integrates that functionality into the CLI (command-line interface) and desktop application.

A similar feature is also provided by OpenAI as an update to its "Codex" platform. OpenAI's "Sites," released approximately two weeks ago, is an enterprise-focused web hosting feature designed as a full-fledged platform that can continuously deploy applications on Cloudflare's infrastructure. In contrast, Anthropic's Artifacts adopts a "stateless" design that lacks persistent backend infrastructure and dynamically generates pages from session context, representing a philosophically different approach.

These developments by both companies indicate that competition over AI-powered enterprise work environments is expanding beyond the developer realm. Major AI companies are currently presenting different solutions to the challenge of streamlining information sharing between engineering teams and management or planning departments. Which approach better suits an enterprise's needs depends on whether persistent infrastructure is required or whether priority is placed on real-time sharing during development.