Back to library
AI
news

Automate Mundane UI Tasks with Gemini 3.5 Flash Computer Use Tool

Automate desktop and browser tasks using Gemini 3.5 Flash Computer Use.

Enable the Computer Use tool in Gemini 3.5 Flash to automate repetitive UI-based tasks across browser and desktop environments using intent-based commands.

Google Gemini

The Scenario

An office worker needs to extract data from a legacy web portal and paste it into a desktop-based report every morning.

Before & after

The old way

Automating cross-app workflows usually requires writing complex scripts or manually clicking through UI elements, which can take 30–60 minutes to set up.

With AI

With the Gemini 3.5 Flash 'Computer Use' preview, you can automate browser or desktop workflows by describing the intent, completing the task in 1–2 minutes.

The Prompt

Using the Computer Use tool, please browse to [WEBSITE_URL], find the information regarding [TOPIC], and copy the relevant data into a new document on my desktop.

The tool features simplified actions with 'intents' and built-in support for browser, mobile, and desktop environments.

Source

Release notes  |  Gemini API  |  Google AI for Developers
"Launched public preview support for the Computer Use tool... includes simplified actions with intents, built-in support for browser, mobile, and desktop."