Gemini for Mac Adds Computer Use: US English Only at Launch, Requires Google AI Plus, Pro or Ultra
According to TechCrunch, Google has announced computer use for Gemini's macOS desktop app, letting it operate Mac apps and websites on a user's behalf. It is initially limited to US English and requires a paid subscription.
News date: About 4 min read
Contents
According to TechCrunch, Google announced on Thursday that it is bringing "computer use" to Gemini's macOS desktop app, letting the AI complete tasks on the user's behalf. Put simply, Gemini used to mostly answer questions; this feature lets it open apps, handle files and browse websites on your Mac the way a person would.
What does this update change?
TechCrunch reports that computer use is an "AI agent" feature. An AI agent is AI that can carry out a series of actions on its own rather than just reply with text. The feature lets the AI take actions directly on the user's computer, which in Gemini's case is a Mac. It can complete multi-step tasks involving local files, apps and the web, including operating native Mac apps and browsing websites in the background.
TechCrunch notes that after a user gives an instruction, they see a live preview of the agent's work in the chat, while still being free to use their screen and cursor for other things.
TechCrunch views Google's launch as somewhat late, noting that OpenAI, Anthropic and Meta have offered agent features in their desktop apps for some time. The report also mentions that Google only this week announced a broader rollout of Gemini's "Tasks" feature, and only recently began letting early testers try the revamped "CC" agent announced in September.
Who can use it now?
| Item | Initial conditions reported by TechCrunch |
|---|---|
| Platform | Gemini app for Mac |
| Language and region | Initially US only, in English |
| Subscription | Google AI Plus, Pro or Ultra |
| Expansion | Google did not say when it will expand to other markets or platforms |
What tasks does Google suggest using it for?
TechCrunch says Google sees the feature being used for tedious tasks and workflows, such as:
- Filling out forms
- Repeating the same job across a batch of files
- Organizing files into folders based on specific criteria
- Building slides using information from files or online dashboards
Frequently asked questions
Does it work on Windows or phones?
According to TechCrunch, only the Gemini app for Mac is supported for now. Google did not say when it will expand to other platforms.
Can I use it with the free version of Gemini?
According to TechCrunch, no. A Google AI Plus, Pro or Ultra subscription is required.
Can I still use my computer while Gemini is operating it?
TechCrunch reports that the agent's work is shown as a live preview in the chat, and users remain free to use their screen and cursor for other things.
Is it available outside the US or in other languages?
TechCrunch only says it is initially limited to US English and that Google did not say when it will expand to other markets, so availability elsewhere is unclear.
Browse the latest news in this topic
Found this guide helpful? Share it with someone who needs it
Claude Code 2.1.329: Code Mode Works With Telemetry, /tasks Lists Scheduled Tasks, macOS Computer Use Gets Stricter Safety Rules
Anthropic's changelog lists Claude Code 2.1.329, covering Code Mode behavior changes, new diagnostics in /tasks and /mcp, /code-review changes, and new safety rules for macOS computer use.
Kimi Code CLI v2.7.0 Adds a Native Amazon Bedrock Provider: Use Your AWS Credentials Instead of a Separate API Key
AWS Rounds Up 13 SageMaker Inference Features: Managed NVIDIA Dynamo on HyperPod, MIG GPU Partitioning, Cross-Region Routing
BMW Group Shares How It Governs AI Agents: 12,500+ Developers, Three Autonomy Levels and a Four-Stage CI/CD Gate
Sources
Compiled from the references and verification dates listed above; fares, schedules, product features, and terms can change, so please confirm the latest details on the relevant official website before travelling, booking, or purchasing.