Google has enabled direct generation and editing of documents, PDFs, spreadsheets, and code within the Gemini chat interface. This update allows users to expand files into full-screen mode for modification or highlight specific text to prompt the model with questions. While PDF previews and editing are available on both web and mobile platforms, support for other formats remains restricted to the web version at this time. The feature builds on earlier capabilities that permitted file creation and downloading, shifting the workflow from a request-and-download cycle to an immediate interaction loop. Users can now refine content without leaving the application, reducing the friction of switching between tools. This change primarily affects how individuals manage documents within the Gemini ecosystem rather than altering underlying API behaviours or customer account structures.
The practical impact lies in streamlining routine document workflows for those already invested in Google’s productivity suite. By keeping the editing context within the chat, the process becomes more linear for tasks like drafting reports or adjusting data tables. However, the availability of these advanced editing tools on mobile devices is still limited compared to the desktop experience. The scope of the update is currently confined to the Gemini app environment without expanding to third-party integrations.
- PDF editing works on web and mobile devices
- Other file formats are web-only for now
- Users can highlight text to ask specific questions
