Google is introducing its Auto Browse AI agent within Chrome, starting today. This new feature allows the AI to handle tasks such as filling forms and extracting information, aiming to streamline the browsing experience. The update, based on the latest Gemini models, also integrates Gemini with other Google services like Gmail and YouTube.

The update includes an easier-to-access AI button for initiating AI tasks, now defaulting to a split-screen view. Auto Browse can open tabs, access content, and request permissions for sensitive data. Users can run multiple tasks simultaneously, with the AI checking in when needed or complete. AI Pro subscribers get 20 daily tasks, while AI Ultra users get 200.

Auto Browse is designed to be a time-saver by automating tedious browser actions. It's similar to tools like OpenAI's Atlas. However, Google has implemented safety measures to prevent misuse. For instance, Auto Browse won't automatically make purchases, stopping at the purchase screen to allow manual approval, mitigating potential risks.

This move by Google reflects the growing trend of integrating AI into everyday tools, aiming to enhance user productivity. The success of Auto Browse hinges on its reliability and accuracy. As AI continues to evolve, expect more such integrations across various platforms, potentially transforming how we interact with the web.