The Daily Byte
Breaking
Welcome to The Daily Byte — real stories from across Pakistan.
Saturday, 21 November 2026 · Pakistan

The Daily Byte

Stories from Pakistan that deserve to be heard
Minor Technology

Gemini now controls Mac apps and fills in forms

By The Daily Byte ·20 Nov 2026 ·3 min read
An open silver MacBook Pro laptop on a desk showing the macOS desktop

Google has given its Gemini assistant the ability to take control of a Mac, letting it click, type, navigate menus and fill in forms across desktop apps, local files and websites on the user's behalf.

The feature, known as computer use, was announced on Thursday 19 November for the Gemini app for macOS. Users describe a task in plain language and Gemini carries out the steps, handling repetitive work that would otherwise take dozens of clicks.

The work runs in an isolated background window, with a live preview shown inside the Gemini chat. The user's main screen and cursor stay free, so they can keep typing, designing or taking calls while the assistant works. Users choose which apps Gemini may access, can watch every step as it happens, pause the process at any time, and must approve key actions before they take place.

Google gave several examples of what the tool can do. In creative work, it can batch colour-grade photographs in design software or help set up complex 3D scenes. It can pull weights, dimensions and addresses from locally stored PDF files and use them to fill in multi-box shipping quotes. It can also gather figures and screenshots from live dashboards in different regions and build a presentation in Google Slides, or analyse photographs in a folder, research prices and prepare items for sale on resale platforms.

The launch is initially available in English in the United States, through the Gemini app for Mac, for subscribers to Google AI Plus, Pro or Ultra plans. It requires an Apple Silicon Mac running macOS Sequoia 15.0 or later, and a personal Google account for users aged 18 and over. The app can be downloaded from gemini.google/mac.

The move follows similar agent features from Anthropic, Meta and OpenAI, as competition shifts from chatbots that answer questions to assistants that complete multi-step tasks. Google is also rolling out its wider Gemini Tasks feature more broadly, which can sign into websites, make purchases and book appointments.

The launch also increases pressure on Apple, whose Siri assistant does not yet offer comparable control of desktop apps. Apple is reportedly developing its own computer-controlling AI agent, capable of operating applications, browsing websites and writing code, and has begun hiring staff for roles linked to the project, according to Bloomberg.

There are limits to be aware of. Gemini pauses at logins and payments and asks before sensitive actions, and users must grant it access to each app it is allowed to control. Giving an AI agent broad permission over a computer carries risks, including prompt injection and unwanted file changes, so the approval and pause controls are central to how Google presents the feature.

For Google, the Mac launch is a test of whether people will trust an AI assistant with everyday computer work. If the controls prove reliable and the time saved is real, computer use could become a standard part of desktop software. If it proves fiddly or unreliable, users are likely to keep doing the clicking themselves.

Sources: Mobile World Live; Gadgets360, reporting Google's announcement.