SI Agent News
DevelopingGemini

Google Gemini adds scheduled tasks to track product price drops

Gemini Pro users can now automate price monitoring and discount alerts for specific products during major shopping events like Black Friday.

Papercut shadow box: picture for the story 'Google Gemini adds scheduled tasks to track product price drops'
AI-made papercut shadow box for this story. No real people or products are shown.
$200Example price drop target

The short version

Why it matters

This shifts Gemini from a reactive chatbot to a proactive personal assistant that can perform recurring research. It allows shoppers to automate the tedious process of checking multiple tabs for the best deals without manual effort.

From chatbot to proactive agent

Google is evolving Gemini from a standard chatbot into an AI capable of executing tasks on behalf of the user. While users have previously used Gemini Notebook and Gems for mundane tasks, the new Schedule feature represents a significant upgrade in automation. It allows the AI to act as a persistent assistant that performs actions over time rather than just responding to immediate prompts.

This functionality is part of a broader trend where AI models are being given the ability to access connected apps and perform actions. However, Google maintains that Gemini cannot perform any actions without explicit user permission. The tool functions as a 24/7 bot that follows specific instructions provided by the owner of the subscription.

To access these capabilities, users must have a Gemini Pro subscription or higher. The update improves upon a previous, clunkier version of the scheduling tool by adding a dedicated settings page. This new interface allows for much finer tuning of how the AI handles automated requests and recurring tasks.

How to set up price tracking

Setting up a scheduled task is designed to be simple and does not require complex manual toggles. Users can access the feature by clicking the hamburger menu in the upper-left corner and selecting the Scheduled option. From there, users can describe the automation they want using the standard chat box.

For example, a user can instruct Gemini to monitor a specific smartphone and send a notification if the price falls below a certain amount. It is often more efficient to provide specific dates and time intervals for these tasks. This helps prevent the AI from burning through tokens, which are the units of processing power used by the model.

As reported by Android Police, it is often better to narrow the scope of the search to specific products rather than broad categories. If a user wants to track a deal across multiple websites, they can set up a single task for several pages. Alternatively, they can create separate automations for each specific product to ensure the AI does not miss a unique opportunity.

Technical limitations and workarounds

The Gemini task feature utilizes a built-in browser to navigate the web and find information. While it can access many brand websites, it currently faces limitations with major retailers. Specifically, the browser cannot access Amazon because the company has upgraded its systems to block AI bots.

Because of these blocks, users may need to verify which websites Gemini can actually reach. It is recommended to provide the product name and ask the AI to search for listings on accessible websites. This ensures the AI doesn't waste cycles trying to reach a blocked domain while still providing the user with relevant data.

For those who primarily shop on Amazon, there is an alternative workaround using Alexa. Amazon offers a dedicated Alexa for Shopping tab that allows for price charting and auto-buys. This service is currently free and works across various devices, including Echo speakers and Fire tablets, to automate purchases when prices hit a target.

Managing token usage effectively

One of the primary considerations for users of this new feature is managing how much of the AI's processing power is consumed. Broad, open-ended requests can cause the model to burn through tokens very quickly. For instance, asking the AI to scan an entire category at a major retailer can exhaust the limit in an instant.

To maximize the utility of a Gemini Pro subscription, users should be specific about the items they want to track. Setting a task to run twice a day during a specific window, such as the Black Friday sale period, is a more controlled approach. This ensures the AI remains active during the most relevant times without wasting resources on unnecessary checks.

Users can also cross-reference the links provided by the AI to ensure accuracy. While the AI can find reliable product links, manually checking the final website remains a good practice. This hybrid approach combines the speed of AI automation with the reliability of human verification for high-value purchases.

The future of automated shopping

The introduction of scheduled tasks marks a shift toward a more autonomous way of interacting with AI. Instead of asking the AI to find a deal once, users can now delegate the ongoing monitoring of those deals to the software. This creates a more hands-off experience for consumers who want to save money without constant manual checking.

As Google continues to refine these tools, the integration between Gemini and other Google apps will likely deepen. This could eventually lead to even more complex automations, such as moving from price monitoring to automated inventory alerts or personalized deal summaries. The current update provides the foundation for these more sophisticated agentic behaviors.

For now, the best way to use these tools is to be highly specific with instructions. By defining clear price points, specific dates, and target websites, users can effectively turn Gemini into a dedicated shopping assistant. This allows for a more efficient way to navigate the high-pressure environment of major holiday sales.

Sources and links

Liked it? Say why

Add a line for other readers.

No account needed. We never show your email. Comments with links, ads or abuse are held and not shown. Your comment shows after a quick check.

Listen to the AI Wire headlines

Listen to the AI Wire

Listen to our daily AI shows every morning: on your commute, in the shower, wherever you are

Listen to the daily shows

First reported by Android Police · Read the original. Written by the SI Agent News Desk from the reporting above.Written with AI from the source above. Every number is checked against the source. Spot a mistake? Corrections.

More AI news