After the success of OpenAI’s video editing app Sora, now at the top of the U.S. App Store, Google may be looking to give its Gemini AI app a more visually focused revamp. The company is seemingly experimenting with a new user interface that would shift the app from having a chatbot-style look and feel to one offering a scrollable feed with suggested prompts accompanied by eye-catching photos.

The changes were spotted in a recent version of the Gemini Android app by the news site Android Authority but are not yet live to the public. Instead, by looking into the app’s code, a reverse engineer enabled the app’s new home screen. Here, shortcut buttons to do things like “Create Image” or access “Deep Research” were moved up on the screen and were then followed by the scrollable feed.

Reached for comment, a Google spokesperson said there’s no announcement to be made “just yet.”

In the examples shown, prompts suggested fun things to do with your photos, like “Teleport me to deep space,” “Give me a vintage or grunge look,” or “Turn my drawing into a storybook,” among other things. Other prompts featuring a colorful background offered different ideas of things to ask Gemini, or suggested use cases. For instance, one prompt idea said “Brainstorm out loud with Live,” and another said “Send me a daily news roundup.”

The idea is to inspire users with more specific suggestions of how to use Gemini’s AI, rather than leaving them to figure out the AI chatbot’s capabilities on their own. However, the revamp would also make Gemini’s app more visually appealing and engaging.

If pushed live to the public, it could also help Google better challenge rival OpenAI, whose ChatGPT app is still fairly minimalist as it launches to a largely blank screen. Plus, it could capitalize on consumer demand for Google’s newer AI image model, Nano Banana, which helped the Gemini app climb the App Store’s Top Charts in September; it became the No. 1 app as of September 12 and held that ranking until being booted by Sora.