Google has added file creation, previews and editing within Gemini conversations. Users can revise content manually or select a passage or visual element and ask the assistant to change it. PDF editing works on the web and mobile, while editing other formats currently uses the web interface, according to the company.
Google has introduced creation and editing of files within Gemini, its AI assistant. A user describes a document in conversation and receives an in-chat preview of the result. Changes can continue from that preview. The addition brings work on the file into the conversation beyond the earlier workflow of generating it and downloading it for use elsewhere.[1], [2]
Opening the preview in a full-screen view allows manual text changes. Users can instead highlight a passage or visual element and ask Gemini to revise that specific part. They can ask follow-up questions about the same selection. Google illustrates the feature by turning uploaded handwritten notes into a study guide, with subsequent changes made within the same conversational workflow.[1]
PDF documents can be edited through both the web and mobile applications. Editing the other supported file types currently requires the web interface. These include text documents, spreadsheets, presentations and code files. Google says the feature is rolling out in supported languages to all users. Selecting part of a file, asking about it and manually editing it are distinct supported interactions.[1]
