Anthropic’s Claude has always been great at coding and working with text, but where Google and OpenAI invested heavily in audio, image, and video models, Anthropic mostly ignored this space. On Thursday, however, Anthropic updated Claude to now also draw interactive charts, diagrams, and visualizations on demand.

The idea here is to have Claude build something graphical “to aid users’ understanding as it’s discussing the topic at hand,” the company says in its announcement. This is now rolling out as a beta to all Claude users on all plan types.

These graphical artifacts are part of the chat, appear inline, and are meant to be ephemeral, changing over the course of a conversation. They are not, Anthropic stresses, permanent artifacts like the documents Claude can create, and hence won’t appear in the Artifacts drawer in the Claude app.

To have Claude create a visualization, for example, the easiest way is to simply ask for one, but at times, the model may also decide that creating a graphic may be the best way to handle a question.

Anthropic’s canonical example for this is asking Claude to explain how compound interest works. It’ll create an interactive chart that’s pretty much what you would find if you searched for a compound interest calculator on Google — just without the ads, auto-playing videos, and cookie banners.

In experimenting with this feature, Claude mostly got things right, but like all models, it would also make mistakes. I had it draw a diagram of how airplanes under visual flight rules can approach a non-towered airport for landing, for example. There are hundreds of similar diagrams on the internet.

Claude mostly got this right and created a nice interactive chart. But while it labeled most things right, for the “midfield crosswind entry,” it aligned that arrow with the wrong part of the airport pattern (it’s called a midfield entry because you cross over the middle of the field). Claude isn’t getting its pilot’s license anytime soon.