How to Use Google Gemini to Automate Tasks
Spark is Google’s AI tool that can perform tasks on your behalf.
One of the promises of AI, on the less “destructive for humanity” side, is to make daily life a little more fluid. Instead of tackling every item on your to-do list yourself, a reliable AI tool might be able to cross off a few entries for you, leaving you to take care of the most important items. Getting a summary of the last 20 emails in your inbox could help you dive into your work faster in the morning, or at least give you a few extra minutes to stare into the distance while sipping your coffee.
If you’re engaged in the Google ecosystem, Gemini Spark could offer a way to automate the tasks you prefer to hand over. Spark is a personal assistant agent announced in May at Google’s annual I/O developers conference. You can give it a task and it can run in the background, taking what Google describes as “proactive action”, while respecting your instructions.
The Gemini Spark website gives some examples of what you can do with it, like turning your last 50 email responses into a style guide for how you respond to emails or setting up tracking for internships. It’s integrated with Google Workspace apps like Docs, Calendar, Slides, and Gmail, as well as Personal Intelligence, a feature Gemini uses to personalize suggestions based on information from your Google apps.
Here’s how to use Gemini Spark to automate tasks.
Before you start
To access Gemini Spark, you must be a Google AI Pro or Ultra subscriber. Some professional subscribers may also have access to it. (You also can’t be located in the European Economic Area, Switzerland, the United Kingdom, or Nigeria.) You’ll also need “Keep Active” enabled, which the company says “lets you pick up chats where you left off.” Spark is available through the Gemini mobile app, Gemini Mac app, and web app. Spark also works with Gemini in Chrome using automatic navigation to complete tasks like booking restaurants, traveling, and more.
Besides the setup basics, Google also recommends a few caveats. As glorious as it is to just set it and forget it, it’s worth remembering that AI can still make mistakes, so keep an eye on the tasks you have set up. Google itself also warns not to insert sensitive information into the discussion thread. This means that you should not give any login or payment information to Gemini. Instead, Google recommends entering this type of information yourself directly on the respective website. Google also warns against scheduling tasks that are too sensitive, especially if the task is set to run when you’re offline. Consider whether an error such as a hallucination could cause actual harm.
How to create a task
Whether you are on the mobile or web application, select Menuthen select Spark. Then you can enter the task you want Spark to accomplish in the text box. The Spark website gives this prompt, for example: “When I receive an email requesting my photography services, automatically extract the client name, requested date and save the lead to my ‘Client Tracking’ sheet.” Then create a new Google Drive folder named after the client. If necessary, this is where you can also upload a relevant file, or something from your Drive or a Notebook. Then tap or click Submit.
Google emphasizes monitoring your tasks in case Gemini needs something from you, like taking over a task in the browser. To keep an eye on your tasks, go to Menu > Spark and then Tasks. This will allow you to see the thread associated with the task, and if you need to make any updates, you can do so here. You can also view the work panel, which shows you information such as completed, in progress, and planned steps, by tapping the progress icon at the top of the thread.
In late September, Google announced that it would replace Gemini Gems with skills as the method for dictating task instructions. In a blog post, the company described how to use its skills to automate repetitive tasks. A skill might be instructions for preparing presentations or adopting a specific writing style. Google said that once you’ve created a skill, if you want to use it again on a task, you’ll be able to enter a forward slash and the name of the skill when you write your prompt.