Back to library
AI
news

Automate Cross-Platform Workflows with Computer Use Tools

Automate desktop and browser tasks with native intent support.

Leverage the 'Computer Use' tool in Gemini 3.5 Flash to create agents that interact with your desktop and browser environment using simplified intents.

Google Gemini

The Scenario

You need an AI agent to perform complex tasks across different software environments, like extracting data from a web browser and pasting it into a desktop spreadsheet.

Before & after

The old way

Manually writing Selenium scripts or RPA macros to automate complex cross-platform tasks takes 1-3 hours of coding and testing.

With AI

Use Gemini 3.5 Flash's Computer Use tool with intents to automate browser or desktop workflows in 3-5 minutes of configuration.

The Prompt

Using Gemini 3.5 Flash's Computer Use tool, write a plan to navigate to [WEBSITE_URL], find [SPECIFIC_DATA], and save it into a local desktop file.

The Computer Use tool simplifies agentic workflows by providing built-in support for browser, mobile, and desktop environments, reducing the need for custom automation glue code.

Source

Release notes  |  Gemini API  |  Google AI for Developers
"Launched public preview support for the Computer Use tool in Gemini 3.5 Flash... built-in support for browser, mobile, and desktop environments."