Google LLC’s Android Studio got a significant upgrade Monday with an experimental capability that can handle complex developmental tasks by just chatting with Gemini, the company’s flagship artificial intelligence model.
The new feature, called Agent Mode, is part of Gemini in Android Studio, the company’s development environment for designing, building and testing applications for Android smartphones. It integrates features and programming languages for Android phones as well as the Gemini AI-powered coding companion that can assist with tasks such as code generation, finding resources and code transformation documentation.
Agent Mode introduces agentic AI capabilities, allowing developers to spell out complex goals using their own words. This could involve tasks such as generating unit tests or performing intricate code refactoring. The agent will create an execution plan that can encompass multiple project files and execute the plan under the developer’s guidance.
Google first gave a glimpse of this upcoming capability at Google I/O 2025 when the company demonstrated how it works. This new mode employs various tools in the editor for reading and modifying code, working on projects, searching the codebase and managing lengthy tasks with minimal oversight.
Although powerful, Google stressed that developers remain in control of Agent Mode. As it works, it will reach stop points where they can refine and guide agent outputs and choose to accept or reject them. Additionally, developers can choose to enable “auto-approve” if they don’t want to be bothered.
The default Gemini model can be used for daily work at no cost with a fairly generous quota and a limited context window. Users with a paid subscription to Gemini can use their application programming interface key to expand Agent Mode’s context window using Gemini 2.5 Pro’s 1 million token context window, which can span enormous codebases.
A larger context window lets developers send more instructions, code and attachments to Gemini for higher-quality responses, Google said. That can be especially useful when working with agents, since the larger context provides Gemini 2.5 Pro with the ability to reason about complex or long-running tasks.
Gemini in Android Studio can also interact with external tools via the Model Context Protocol, an open standard pioneered by Anthropic PBC. This feature provides a standardized way for AI models to use tools and communicate with other AI agents, thus extending its capabilities.
Users can download and try out the latest experimental preview version of Android Studio on the canary release channel of Narwhal today to explore Agent Mode.
Image: Google
Support our open free content by sharing and engaging with our content and community.
Join theCUBE Alumni Trust Network
Where Technology Leaders Connect, Share Intelligence & Create Opportunities
11.4k+
CUBE Alumni Network
C-level and Technical
Domain Experts
Connect with 11,413+ industry leaders from our network of tech and business leaders forming a unique trusted network effect.
SiliconANGLE Media is a recognized leader in digital media innovation serving innovative audiences and brands, bringing together cutting-edge technology, influential content, strategic insights and real-time audience engagement. As the parent company of SiliconANGLE, theCUBE Network, theCUBE Research, CUBE365, theCUBE AI and theCUBE SuperStudios — such as those established in Silicon Valley and the New York Stock Exchange (NYSE) — SiliconANGLE Media operates at the intersection of media, technology, and AI. .
Founded by tech visionaries John Furrier and Dave Vellante, SiliconANGLE Media has built a powerful ecosystem of industry-leading digital media brands, with a reach of 15+ million elite tech professionals. The company’s new, proprietary theCUBE AI Video cloud is breaking ground in audience interaction, leveraging theCUBEai.com neural network to help technology companies make data-driven decisions and stay at the forefront of industry conversations.
