Skip to main content
A hand holds a Gemini 3 Pro phone showing a sleek, magazine-style Google UI with images and text in a bright office.

Google Tests Magazine‑Style UI for Gemini 3 Pro Users

Updated: 3 min read

Google is testing a visual layout for Gemini 3 Pro, packaging responses in a clickable, customizable format. Dubbed a "generative UI," this new interface turns a simple request—like a three-day Rome itinerary—into a dynamic webpage. Subscribers to the higher-tier Ultra plan, meanwhile, get access to Gemini Agent. That separate feature can perform tasks like organizing a Gmail inbox.

Gemini 3 isn't just built for prototyping and modeling; Google is testing a new "generative UI" feature for Pro subscribers that packages its responses inside a "visual" magazine-style interface, or in the form of a "dynamic" interactive webpage. I only got access to Gemini 3's visual layout, which Google showed off as a way to envision your travel plans, like a three-day trip to Rome. When I tried out the Rome trip prompt, Gemini 3 presented me with what looked like a personalized webpage featuring an itinerary, along with options to customize it further, such as whether I'd prefer a relaxed or fast-paced vacation or if I prioritize certain dining styles.

Once you submit your preferences, Gemini 3 will redesign the layout to match your selections. I found that this feature can provide interactive guides on other topics, too, like how to build a computer or set up an aquarium. Next up, I did a little experimenting with Gemini Agent, a feature Google is testing for Ultra subscribers inside the Gemini app.

Like other agentic features, Gemini Agent aims to perform tasks on your behalf, such as adding reminders to your calendar and creating reservations. One example shared by Google shows Gemini Agent organizing a Gmail inbox, so I asked the tool to do the same -- and, well, it followed my orders.

Common Questions Answered

What new "generative UI" feature is Google testing for Gemini 3 Pro subscribers?

Google is testing a visual "magazine‑style" interface that wraps Gemini 3's responses in a glossy layout or a dynamic interactive webpage. This feature aims to present AI‑generated content as a finished product rather than plain text.

How does the visual UI present a travel‑plan prompt, such as a three‑day trip to Rome?

When given a Rome travel‑plan prompt, Gemini 3 displays the itinerary within a magazine‑style spread, complete with images, formatted text, and interactive elements that resemble a travel brochure. The layout is designed to help users visualize the trip more intuitively.

What types of content did the test run show Gemini 3 could render without crashing?

The test run demonstrated that Gemini 3 could successfully display code snippets and 3D visualizations within the magazine‑style UI. These elements loaded smoothly, indicating the visual interface can handle technical and graphical outputs.

Did the new visual UI meet expectations for handling complex workflows?

While the UI performed well with simple prompts, it struggled with more complex workflows, often stalling or requiring additional user input. Google notes that the model's "agentic" abilities are still being refined for advanced tasks.

LIVE03:21OpenAI's Miles Wang in Talks for USD 2B AI Drug Discovery Startup