Build and share AI-powered apps with Claude
Today, we’re introducing the ability to build, host, and share interactive AI-powered apps directly in the Claude app. Now developers can iterate faster on their AI apps without worrying about the complexity and cost of scaling for a growing audience.
Build and host Claude-powered apps
Here’s what we built: Claude can now create artifacts that interact with Claude through an API— turning these artifacts into AI-powered apps, where the economics actually work for sharing.
When someone uses your Claude-powered app:
- They authenticate with their existing Claude account
- Their API usage counts against their subscription, not yours
- You pay nothing for their usage
- No one needs to manage API keys
Claude writes real code that orchestrates complex AI functionality. You can see it, modify it, and share it freely.
Community ideas
Early users have already used interactive artifacts to build:
- AI-powered games with NPCs that remember conversations and adapt to player choices
- Learning tools that adjust to individual skill levels and provide personalized tutoring
- Data analysis apps where users upload CSVs and ask follow-up questions in natural language
- Writing assistants that help with everything from scripts to technical documentation
- Agent workflows that orchestrate multiple Claude calls for complex tasks
Getting started
Start building in the Claude app by enabling this new interactive capability. Simply describe what you want to create, and Claude will write the code for you.
As you work together, Claude can debug and improve its own code based on your feedback. Once your app is ready, you can share it instantly through a link—no deployment process needed. Claude takes care of the technical details like prompt engineering, error handling, and orchestration logic, allowing you to focus entirely on bringing your idea to life.
What you can do:
- Use a Claude API within your artifacts
- Process files and create rich UIs with React
- See, fork, and customize any artifact
Current limitations:
- No external API calls (yet)
- No persistent storage
- Limited to a text-based completion API
This capability is available in beta to Free, Pro, and Max plan users.