Claude‘s run of new and expanded features continued this week with a new beta feature that lets you create interactive visuals, including charts and diagrams, right inside a chat. These tiny interactive tools let you tweak controls and see the graphics shift to reflect the change.

The feature builds on the company’s earlier “Imagine with Claude” concept, which experimented with letting the AI construct visual outputs without requiring code. The latest version brings those visuals directly into the conversation itself. Instead of living in a side panel like Claude’s artifacts, the diagrams appear inline as part of the response and evolve as the discussion continues.

Article continues below

1. Coffee calculations

The first prompt was grounded in something practical. I asked Claude:

“Make an interactive coffee-to-water ratio calculator. Pick your brew method and cup count and get exact coffee and water measurements.”

Within seconds, a small interactive tool appeared inside the chat. At the top was a selector for brew method, offering familiar choices such as pour-over and French press. Beneath that sat a simple control that let me choose how many cups I wanted to brew.

The clever part was how the display responded. When I switched from one cup to three, the measurements below changed instantly. The visual showed the precise amount of coffee grounds and water required for that brew style. It was the sort of calculation that coffee enthusiasts often memorize or look up online. Seeing it rendered as a little dynamic graphic made the process feel almost obvious.

Instead of explaining brewing ratios with text, the chatbot had quietly built a tiny barista tool inside the conversation.

2. Volcano fun

For the second test, I wanted to see how Claude handled an educational task. I asked it to:

“Show an interactive cross-section of a volcano with labeled parts. Animate the parts when I toggle an eruption.”

Claude responded with something that looked like a digital page torn from a science textbook. The volcano appeared sliced open from the side, revealing its inner structure.

When I toggled the eruption control, the magma chamber lit up and animated upward through the conduit like glowing lava rising toward the surface. Switching the eruption off returned the mountain to its dormant state.

The whole thing felt like a miniature geology lesson assembled in real time.

3. Vibe dresser

The third experiment leaned fully into absurdity. I asked Claude to:

“Build a vibe-based outfit generator. Pick a temperature and a vibe and generate a very specific outfit suggestion with a stick figure model.”

Claude responded with the kind of interface that might appear in a very strange fashion app. At the top sat a temperature slider ranging from chilly to sweltering. Beneath it were several vibe buttons. Selecting a combination generated an outfit for a tiny stick-figure model.

When I chose a cooler temperature and the cozy vibe, the stick figure appeared bundled in what looked like an oversized sweater and thick socks. When I shifted the vibe to chaotic, the outfit became dramatically less sensible. The stick figure wore clashing colors and sunglasses, suggesting someone who had made bold decisions before leaving the house.

The text description next to the figure explained what to wear and the vibe it might project. The little figure updated every time the controls changed, making it oddly tempting to keep experimenting with different combinations.

None of these examples is likely to change the world on its own, but how Claude created them is pretty impressive and quite fun.

The approach hints at how chatbots might communicate small visual demonstrations on the fly. The visuals are deliberately temporary, but the fleeting quality makes them feel less like sketches drawn during a conversation, and it could really draw in more potential users. At least that’s the vision Claude is hoping to sketch out.

Follow TechRadar on Google News and add us as a preferred source to get our expert news, reviews, and opinion in your feeds. Make sure to click the Follow button!

And of course you can also follow TechRadar on TikTok for news, reviews, unboxings in video form, and get regular updates from us on WhatsApp too.

Eric Hal Schwartz is a freelance writer for TechRadar with more than 15 years of experience covering the intersection of the world and technology. For the last five years, he served as head writer for Voicebot.ai and was on the leading edge of reporting on generative AI and large language models. He’s since become an expert on the products of generative AI models, such as OpenAI’s ChatGPT, Anthropic’s Claude, Google Gemini, and every other synthetic media tool. His experience runs the gamut of media, including print, digital, broadcast, and live events. Now, he’s continuing to tell the stories people want and need to hear about the rapidly evolving AI space and its impact on their lives. Eric is based in New York City.