Google's Gemini app can now generate, preview and edit PDFs, Docs, Sheets and slides inside a chat

Google announced on October 29 that the Gemini app can now generate, preview and edit documents, PDFs, presentations, spreadsheets, code and other files directly inside a chat. You can expand a file to full screen and type edits yourself, highlight text to ask questions about it, or tell Gemini to refine the file. Google says the capabilities are available to all users in all languages where the Gemini app is offered.

The demo in Google's post is a study guide. A user uploads handwritten lecture notes and asks Gemini for a PDF study guide, then edits it by hand, highlights sections so Gemini changes the text or visuals, and asks follow up questions, all in one session. Chrome Unboxed describes a floating Describe changes bar for targeted edits to highlighted passages.

Platform support is uneven. PDF preview and editing works on both web and mobile. Google Docs, Google Sheets, slide decks, Markdown files, TXT files and code are supported on the web only, according to Google. So a phone user can work on a PDF in chat, but not yet on a spreadsheet or code file.

This builds on file generation Google introduced on April 29, 2026, when Gemini could already create PDFs, Word and Excel files, Docs, Sheets and Slides from a prompt. Unite.AI notes that under that version editing happened elsewhere, with users exporting the file to Drive or downloading it. The new release adds the editing layer in the same place the file was made. 9to5Google reported it alongside a new Gemini design for all Android devices.

For developers and AI builders, the practical change is fewer round trips. Drafting a README, a spec, a CSV or a small script in Gemini no longer means copying text out and cleaning up formatting, and you can fix one paragraph without regenerating the whole file. It also moves chat assistants closer to a canvas style workspace, the pattern many coding and document tools are converging on.

Google's announcement does not mention pricing tiers, limits on file size, or an API for the editor, so it is unclear whether developers building on the Gemini API get the same behavior. If you use Gemini day to day, the thing to try is a web chat that generates a Doc or Sheet, then edits by highlighting. Check mobile if you rely on anything other than PDFs.

Building with AI? See this week's hot AI repos and how to use each one.