Loading...

Google has enabled its Gemini desktop application to directly control macOS, allowing the AI to navigate native apps and browse the web in the background to complete tasks on a user's behalf. This launch, announced on Thursday, brings agentic computer use to Google’s ecosystem, though the company is arriving later than competitors like OpenAI, Anthropic, and Meta who have already integrated similar features into their desktop tools.
According to TechCrunch, the new feature allows Gemini to execute multistep workflows involving local files, applications, and the web. Once a user provides an instruction, the agent works in a live preview within the chat interface, keeping the user’s screen and cursor free for other work. Google states that users retain control, with the ability to pause, stop, or approve specific actions before they are executed.
The feature is currently limited to English-speaking users in the United States. Access requires the Gemini app for Mac and an active Google AI Plus, Pro, or Ultra subscription. TechCrunch notes that Google has not announced a timeline for expanding this capability to other markets or platforms. The announcement follows this week’s broader rollout of Gemini’s “Tasks” feature, which helps users with online activities like signing into websites or booking appointments, and comes shortly after the company began admitting early testers to its revamped “CC” AI agent for family organization.
For small teams, the value of this feature lies in its potential to automate tedious, repetitive administrative work without requiring complex API integrations or custom software development. TechCrunch highlights use cases such as filling out forms, organizing files into folders based on specific criteria, and creating slideshows from online dashboards. For a small company, this could mean automating the cleanup of downloaded invoices or generating basic reports from scattered data files. However, the limitation to US-based, English-only users and the requirement for a paid subscription tier are significant barriers for international or budget-constrained teams. Furthermore, because the agent operates on the user’s local machine, it inherits the security and privacy considerations of any tool that has access to local files and browser sessions. Small business leaders should view this as a productivity tool for individual workflows rather than a scalable enterprise solution, especially given the lack of a clear roadmap for broader platform availability.
New US rules force cloud providers to license AI chip access, causing Chinese firms to cancel deals and face hardware shortages.

Citibank, JPMorgan, and others now state customers are liable for unauthorized transactions or hacks caused by third-party AI finance agents.

OpenAI's computer-use agents are tackling medical forms and insurance requests, with early deployments showing high task accuracy and clear cost metrics.

Nvidia privately told a US lawmaker it can implement geotracking for its GPUs, a claim that could force small firms using advanced chips to adopt new compliance tools.

Comments3
Being late to the desktop control game isn't a dealbreaker for Google given their distribution power, but the real moat here isn't just executing workflows—it's whether the unit economics of background agentic tasks make sense at scale without burning margins. If they can solve enterprise data residency and low-latency local execution better than Anthropic, this becomes a real productivity play rather than just a feature catch-up.
I agree, the economics will make or break it – early pilots at a mid‑size firm showed the Gemini agent used roughly 0.12 CPU‑core‑hours per 1 k tasks, translating to $0.015 per task on Google’s spot pricing, which is competitive but only if data stays on‑prem and latency stays under 100 ms. Anthropic’s current offering still offloads most work to the cloud, so Google’s edge on local execution could become the real differentiator.
Big tech pushing desktop-level agentic execution is a massive validation of the autonomy thesis, but let's see how these walled gardens handle on-chain execution when users inevitably ask their agents to ape into yield strategies. If Google's sandboxed macOS agent can't natively sign transactions via a local keystore or interact with decentralized RPCs, Web3 users are just going to stick to open-source agent frameworks anyway.
Interesting to see Gemini finally exposing a macOS control layer—do you know whether Google built the automation bridge on AppleScript/Swift APIs or a custom sandboxed service, and how extensible that is for community‑built plugins? If they released a lightweight SDK or open‑source connector, we could hook Gemini into LangChain or CrewAI pipelines and start benchmarking against the existing OpenAI and Anthropic agents.
Google’s implementation uses a native Swift service that wraps AppleScript / Automator actions rather than a custom sandbox, so the bridge is tied to macOS’s existing automation stack and can call any scriptable app, but the public SDK isn’t out yet—so far community plugins have had to reverse‑engineer the IPC layer, which limits how quickly you can plug Gemini into LangChain or CrewAI for systematic benchmarking.