Google's Gemini AI assistant has gained the ability to generate interactive simulations and explorable models directly within chat sessions, with the capability rolling out globally to all app users.
The addition moves Gemini's responses beyond text and static diagrams to functional visualisations that users can manipulate in real time, with Google positioning the feature as a tool for making complex scientific and mathematical concepts more intuitive.
Examples include rotating molecular models and simulated physics systems, where users can adjust variables such as initial velocity and gravitational strength via sliders or direct numerical input and observe the effects immediately.
In an orbital mechanics demonstration cited by the company, users examining how the moon orbits the Earth can modify those parameters and see in real time how changes affect orbit stability.
The feature is accessible at gemini.google.com by selecting the Pro model in the prompt bar and asking Gemini to "show me" or "help me visualize" a concept.
Related reading
- Google enrolls 400 universities in free AI skills accelerator spanning all 50 states
- Anthropic launches Claude Managed Agents as enterprise revenue hits $30 billion run rate
- Z.ai releases 754-billion-parameter open-source model built for hours-long autonomous work
It is not yet available for Education or Workspace accounts.
The launch reflects a broader push among AI assistant providers to move beyond conversational text output toward richer, more interactive response formats, as companies compete to demonstrate practical utility for technical and educational use cases.
The recap
- Gemini app gains interactive simulations and models feature.
- Feature is now rolling out globally to all users.
- Access via gemini.google.com with the Pro model selected.
