Google adds computer use to Gemini for macOS, enabling multi-step tasks
Google announced on Thursday that it is bringing computer use to its Gemini desktop application on macOS, allowing the AI agent to organize files, fill out forms, and handle multi-step workflows across local files, desktop apps, and the web. The feature runs in the background with a live preview window in the chat, and users can control which apps Gemini can access. It is rolling out now in English for US users on AI Plus, Pro, and Ultra plans.
Coverage timeline
TechCrunch AISarah Perez
Google's latest update to Gemini brings an AI agent to the Mac that can organize files, fill out forms, and tackle multistep workflows.
The Verge AIJay Peters
Google's Gemini app for macOS now has computer use, meaning it can help you "get multi-step tasks done across your local files, desktop apps, and the web," the company says . Google suggests the feature might be useful for things like speeding up workflows, filling in forms, making presentations, and listing items for sale. Users will be able to decide which of your apps Gemini can access, and be able to follow along as Gemini works because it has its own background window that shows a live preview in your chat, Google says. The feature is rolling out now in English for users in the US. Gemini is introducing the new feature ahead of Apple l … Read the full story at The Verge.

Techmeme
Sarah Perez / TechCrunch : Google adds computer use to Gemini for macOS, letting it work across apps, files, and the web in the background, available to US AI Plus, Pro, and Ultra users — Google on Thursday announced that it is bringing computer use to its Gemini desktop application on macOS, allowing its AI …

Related stories
Google rebrands Spark AI agent as Tasks, makes it free
Google is rebranding its Spark AI agent as "Tasks" and making it free, powered by the Gemini 4 Hydrogen model. The agent can create meal plans, manage calendars, and scan emails for recurring expenses. In the US, users can also have it call businesses to compare prices and check inventory, purchase items with Google Pay, and log into accounts via Google Password Manager, with task assignment by email or text.
4 reports · 4 sources57 points · 75 comments

Google opens Gemini and Search to developers via new platform
Google announced a new developer platform that allows businesses to integrate their services into Google's AI experiences, including Gemini and Search. This move could reshape how consumers discover and use apps as AI agents become more prevalent.
1 reports · 1 sources
Google launches Gemini 4 Hydrogen, a low-cost agentic model, across products
Google announced Gemini 4 Hydrogen, a new Flash-level multimodal model with a 1M token window, priced at $1.50/1M input and $7.50/1M output tokens. It is available across AI Studio, the Gemini API, Search, the Gemini app, and Antigravity, and introduces an xhigh reasoning level. Benchmarks show it nearly ties Claude Sonnet 5.5 and GPT-6.1 Sol on the Artificial Analysis Intelligence Index at lower cost, and it powers an upgraded AI Mode in Search.
9 reports · 6 sources570 points · 352 comments

Google Gemini now lets users generate and edit Docs, Sheets, PDFs in chat
Google has rolled out new file editing capabilities in Gemini chats, allowing all users to generate, preview, and edit PDFs, Google Docs, Google Sheets, slide decks, Markdown files, TXT files, and code directly within the Gemini interface. The feature is available starting today for all Gemini users, with PDF previews and editing working on both web and mobile, while other file formats are currently limited to the web version. Users can expand documents to full-screen mode for editing and highlight text to ask Gemini questions or prompt actions.
1 reports · 1 sources

News updates every hour. Subscribe in your RSS reader to get new stories automatically.
Subscribe