On October 30, Google's AI assistant Gemini rolled out a major feature upgrade packed with practical value. Starting today, when all users generate, preview, and manage files within Gemini, they can edit them directly in the chat interface, completely eliminating the cumbersome process of having to download them separately or switch to an external app to make adjustments after generation.

The file formats now open for inline editing and preview are quite comprehensive, covering PDF, Google Docs, Google Sheets, presentations, Markdown files, TXT text, and various code files. In terms of platform support, preview and editing for PDF files have arrived on both web and mobile, while all other file formats currently mainly support web-based operation.

Looking back, Google had already rolled out file generation and download features for Gemini earlier this year, and this update further closes the loop between generation and editing. According to the official introduction, users can open documents in full screen for detailed editing; they can also select specific text within a file to ask Gemini questions or give editing instructions directly. For example, users can simply select a newly generated table and ask Gemini to convert it into a chart with one click, greatly improving interaction efficiency in daily office work and content creation.

In terms of the ecosystem, although users could previously rely on Gemini's integration within the Google Workspace suite to handle files (for example, making adjustments through the sidebar in Google Docs), this update directly embeds editing capabilities into Gemini's standalone chat interface. Similarly, competitor Anthropic also launched a similar feature earlier this year, allowing users to generate and edit documents and presentations directly in Claude's chat window. As major mainstream AI assistants successively fill this gap, the boundaries of conversational AI as a productivity tool are being further expanded.