Home / Technology / Tech News / Gemini Spark launches in India: Here's how Google's personal AI agent works
Gemini Spark launches in India: Here's how Google's personal AI agent works
Google is rolling out Gemini Spark to AI Pro subscribers in India. Here is how the personal AI agent uses tasks, schedules and skills to automate workflows
Gemini Spark is now rolling out in India to Google AI Pro and AI Ultra subscribers
Google has started rolling out Gemini Spark in India to Google AI Pro and Google AI Ultra subscribers. Introduced at the company's developer-focused I/O event earlier this year, Gemini Spark is positioned as a personal, round-the-clock artificial intelligence (AI) agent designed to automate tasks and carry out actions on behalf of users.
Google said the feature would become available to AI Pro subscribers in India over the next few weeks.
What is Gemini Spark
Gemini Spark is Google's attempt to create a personal AI agent that can operate continuously in the background. Unlike a conventional chatbot that responds only after receiving a prompt, Spark can perform tasks, monitor conditions and take actions on a user's behalf. It can continue working even when the user's laptop is closed or phone is locked, according to Google.
Google describes it as a 24/7 personal agent that can automate workflows across different services and applications while remaining under the user's direction.
On the web, Spark appears as a dedicated tab within the Gemini app. Android and iOS users can access it alongside Search chats and Daily Brief. Gemini Spark is powered by Google's Gemini 3.6 Flash model, which the company has designed for complex and agentic workflows.
What can Gemini Spark access
Google said Gemini Spark can use information from connected applications, skills, Gemini chats, websites on which the user is signed in, Personal Intelligence and location data, depending on the permissions granted by the user.
It connects with Google services and Workspace applications such as Gmail, Docs and Sheets. Since Spark runs on Google's cloud infrastructure, users do not need to set up or maintain a separate computing environment.
Google said users can decide whether to enable Spark and which applications it can access. The company also said the agent would seek confirmation before carrying out high-stakes actions, such as spending money or sending emails.
Gemini Spark can interact with websites on a user's behalf through a browser-based environment. However, Google has not specified whether all such capabilities will be available immediately as part of the India rollout.
How Gemini Spark works
As an AI agent, Gemini Spark can perform multistep tasks and continue working in the background without requiring constant instructions from the user. The system is built around three key components: Tasks, Schedules and Skills.
Tasks
A Task represents the outcome a user wants Spark to achieve. This could be a relatively simple request, such as organising emails, or a more complex workflow, such as planning a business trip across different services. Users can monitor assigned work through the Tasks page in the Gemini app. The page shows the progress of tasks and lets users pin, rename, filter or delete task threads.
Schedules
Schedules determine when Gemini Spark should perform a task. A schedule can be based on a particular date and time, a recurring interval or a condition. For example, users can ask Spark to run a workflow every Monday morning or act when a particular type of email arrives in their inbox. This allows users to automate recurring activities or set up workflows that begin when a specified event occurs.
Skills
Skills are reusable sets of instructions and context that teach Gemini Spark how to perform a particular activity. Instead of repeatedly entering the same preferences, instructions or files, users can create a Skill once and apply it to multiple Tasks.
Skills can specify how Spark should approach a task and which tools or information it should use. Several Skills can also be combined to manage more complex workflows.
Gemini Spark can automatically identify and use a relevant enabled Skill, or users can instruct it to apply a specific one.
Together, Tasks, Schedules and Skills allow Gemini Spark to move beyond responding to individual prompts and automate ongoing workflows across connected services.