Design work through conversation with Claude, editing the result directly on the canvas.
Claude Design is design work done through conversation: describe the change and the result appears on a canvas you can edit directly. Because the underlying artifact is code, the same session produces something functional rather than a picture of it. It suits designers who prefer to direct and critique rather than draw every state by hand.
- Design through conversation
- Edit results on the canvas
- Output is working code
- Functional prototypes, not mockups
- Direct rather than draw
- Iterate without starting over
Recent X Posts
Claude Fable 5.1 is available everywhere today. Claude Mythos 5.1, our model for cyberdefenders and life scientists, is available through trusted access programs. Read more: anthropic.com/claude-fable-a…
Finally, we’ve improved our safeguards. Our cybersecurity safeguards now flag benign requests about 60% less often. On basic biology and medical questions, we’ve recently reduced the fallback rate by around 85%.
We’re also introducing Enterprise Frontier Safeguards (EFS), which give enterprise customers complete privacy (the same as zero data retention), while still being state-of-the-art at preventing adversarial use. EFS rolls out in phases, starting this fall. anthropic.com/news/enterpris…
Cache reads with Fable 5.1 cost 75% less than Fable 5’s. This reduces the cost of the model in practice by around 25% for typical workloads, and up to 45% for highly agentic ones.