Google has introduced an auto-browse feature in Chrome to handle multi-step tasks independently. This new capability is supported by Gemini, Google's Artificial Intelligence (AI) model.
For now, this advanced browsing capability is only available to AI Pro and Ultra customers in the US. Users can now not only fill out a simple form, but also be able to quickly research hotel and flight costs on various dates.
This auto browse feature also supports professional workflows, for example, such as collecting tax documents or submitting expense reports. Users can even use this feature to speed up SIM extensions or check the status of monthly bill payments.
"You can also use it for more complicated things," Google said in its official release, quoted on Thursday, January 29. "You (can) plan a Y2K-themed party and find inspiration in a photo that perfectly depicts the era."
Google explains that this feature is supported by Gemini 3 multimodal technology so that it can identify images in depth. If users see a photo of a party inspiration, Chrome can search for similar items and immediately add them to the shopping cart.
Google also ensures the security of this feature due to the integration of Google Password Manager. Although it can handle the login process automatically, the AI agent can only act if the account owner has given special permission.
By presenting the auto browser feature, Google hopes this feature can reduce repetitive or boring burdens for humans. Google is also trying to make Chrome a smarter and adaptive productivity center.
The English, Chinese, Japanese, Arabic, and French versions are automatically generated by the AI. So there may still be inaccuracies in translating, please always see Indonesian as our main language. (system supported by DigitalSiber.id)
