Gemini File Editing: Create Docs, PDFs and Slides in Chat

For most of the chatbot era, asking an AI for a document meant copying its answer into a word processor and fixing the formatting yourself. Google is closing that gap. As of October 29, 2026, the Gemini app can generate, preview and edit files directly inside a conversation, from PDFs and Google Docs to spreadsheets, slide decks and code, according to Google's announcement on The Keyword.

• What's new: Gemini creates files in chat, shows a live preview, and lets you edit by typing or by asking Gemini to revise
• Formats: PDFs on web and mobile; Google Docs, Sheets, slide decks, Markdown, TXT and code on the web
• Exports: slide decks open in Google Slides or download as PPTX or PDF, and sheets open in Google Sheets, per 9to5Google
• Availability: all Gemini users, in every language where the Gemini app is offered

How Does Gemini File Editing Work?

The workflow is designed to feel like a co-authoring session rather than a one-shot prompt. You ask Gemini for a file, it renders a preview inline, and from there you have three ways to refine it. You can expand the file to full screen and type edits yourself, highlight a passage to ask a question about it, or select a section and have Gemini rewrite the text or adjust a visual.

Google's own example captures the appeal for students: upload photos of handwritten lecture notes, ask for a PDF study guide, then tidy it by hand and ask Gemini to sharpen the sections that still feel thin. The same loop applies to a project tracker, a pitch outline or a lesson plan.

Which File Types Can the Gemini App Create?

9to5Google's breakdown shows the feature spans most everyday office formats:

• Slide decks: draft outlines or full slide content, preview the layout, adjust tone and structure, then open in Google Slides or download as PPTX or PDF
• Spreadsheets: generate trackers, tables and simple data models from a prompt and open them directly in Google Sheets
• Documents and PDFs: draft PDFs, Google Docs, LaTeX, Markdown or plain text, edit inline or in full screen, and save to Google Drive
• Code files: preview and edit generated code alongside the conversation

PDF preview and editing works both on gemini.google.com and in the mobile apps, while the other formats are web-only for now.

Why In-Chat Editing Matters for AI Productivity

From a research perspective, the interesting shift is where the human sits in the loop. Earlier generative AI tools optimized for the quality of a single output. In-place editing treats the model's draft as a starting point and makes correction cheap: you fix a heading yourself, ask the model to restructure a paragraph, and keep both changes in one artifact. That mixed-initiative pattern tends to produce better final documents than either a person or a model working alone, because each handles the part it is best at.

It also reduces a quiet source of friction. Every copy-and-paste between a chatbot and an editor risks lost formatting, broken tables or a stale version. Keeping generation, preview and editing in one place means the file you approve is the file you export.

The rollout lands alongside a refreshed Gemini overlay design reaching all Android devices, and just days after Google introduced its new frontier model, Gemini 4 Carbon. It also builds naturally on the deeper Gemini integration across Docs, Sheets and Slides that Workspace users have had since spring. For more on assistants and models, browse our AI coverage.

Sources: Google, The Keyword — October 29, 2026; 9to5Google — October 29, 2026.