Google has expanded Gemini Spark with Chrome web browsing capabilities, allowing the AI agent to handle complex web errands using users’ logged-in accounts and saved passwords with permission.
The Chrome integration enables Gemini Spark to complete tasks such as scheduling apartment viewings from saved listings, researching flight options and starting the booking process. Google says these capabilities include protections against threats such as prompt injection. For sensitive actions like payments, Spark hands the task back to the user.
Gemini Spark task automation
Gemini Spark is designed to automate complex workflows and manage ongoing tasks in Gemini Apps. It can use information from sources such as Connected Apps, skills, chats, websites users are signed into, Personal Intelligence, location and other available data sources to complete tasks based on user instructions.
Users can use Spark for tasks such as summarising or managing newsletters, creating custom news digests and conducting research on topics with cited sources. With Chrome auto browse, Spark can also help with web-based activities such as shopping, travel bookings and making reservations.
Availability
Google is rolling out Gemini Spark access to Google AI Pro subscribers in over 160 additional countries starting today.
The Chrome auto browse capabilities are initially rolling out in the U.S., with plans to expand to additional regions in the future.