Google extends its in-depth research tools to Gemini Android apps. So far, Gemini’s first artificial intelligence (AI) proxy is only available on the web version of the platform. The Mountain View-based tech giant released the tool in December 2024 and described it as a research assistant who can develop a multi-step research plan, run a web search and prepare detailed reports on complex topics. It is worth noting that the proxy function is currently only available to paid subscribers of Gemini.
Deep study AI agents are added to Android’s Gemini app
Gemini’s official handle on X (formerly known as Twitter) announced the extension of AI proxy in its post. The post highlights that it is currently launching, so it may take several weeks before users around the world start to see the feature on Android apps. Once added, you can access the in-depth study in the Gemini Advanced drop-down menu.
The company said at launch that the feature will be available in 45 languages, including Arabic, Bengali, English, French, Japanese, Russian, Russian, Tamil and Vietnamese. In-depth research is powered by the recently released Gemini 1.5 Pro, which can serve as a research assistant to users.
Once tips on complex topics are added, AI agents develop multi-step research plans. Users can check and edit plans to add, delete, or change items in the list. Afterwards, it views relevant information through relevant research papers, articles and other trustworthy sources. It also examines the latest developments on the topic, current trends, and future prospects.
It can also run several new web searches if the AI agent thinks it needs to get context from other topics. Once the agent has enough information, it generates a detailed report on the topic. Users can intervene and control at any time during the entire process.
Based on its knowledge, agents can also run several new web searches to gain a deeper understanding of the topic. Once the agent has enough information, it generates a detailed report. The user can choose to intervene in any step and then edit the study plan or add subsequent prompts to modify the output.
