Beginners can now build their own apps with Google’s latest Gemini update

• Photo courtesy of Google

By TechWatch PH Staff

Google has introduced new updates to its Gemini platform aimed at helping beginners create functional applications without prior coding experience. 

The update allows users to build apps by describing their ideas in natural language, reducing the need to manually write code.

The capability is delivered through Google’s Gemini model via Google AI Studio, a web-based tool that enables users to generate application code, logic, and basic interfaces directly from text prompts. Users can access the platform through a browser without installing additional software.

According to Google, AI Studio supports multimodal inputs, allowing developers to incorporate image, audio, and video processing into their applications. Once an application is completed, it can be deployed directly to Google Cloud with a single action.

The company described the workflow as a shift toward “vibe coding,” where users focus on describing intended functionality while the system handles implementation. The approach is designed to make app development accessible to students, educators, and small teams who may not have formal programming training.

“We’re moving from a world where you have to write every line manually, to a world where you orchestrate. The fundamental skills of critical thinking and creativity are becoming more valuable, not less,” said Logan Kilpatrick, Group Product Manager at Google DeepMind.

Google AI Studio highlights that users can go “from zero to app in minutes,” positioning the platform as a browser-based environment where users describe an idea and the system handles the generation of code, visuals, and application logic. 

According to the platform overview, apps can be built using Gemini models without requiring an API key, and users may start from pre-made templates, including options such as dynamic text-based games and Gemini-powered code review tools.

The interface also emphasizes access to the latest AI models with built-in multimodal capabilities, allowing applications to process text, images, audio, and video within the same workflow.

Once development is complete, applications can be deployed “in a click” to Google Cloud, enabling immediate hosting without additional configuration.

Google AI Studio further notes that users can experiment with up to 1.5 billion free tokens daily, supporting large-scale testing and iteration during development. 

The platform is accessible directly through Google AI Studio, where users can begin building apps powered by Gemini through a web browser.