Gemini app now lets users create, view, and edit documents, PDFs, presentations, spreadsheets, and code within chat

Integrated file creation and editing in Gemini

Google has added the ability to generate, preview, and edit a range of file types directly inside its Gemini chat app.

The new functionality lets users work with documents, PDFs, presentations, spreadsheets, code, and other formats without leaving the conversation window.

Users can expand the file view to full screen, type edits directly, or highlight text to request specific changes from Gemini.

The system can also answer follow‑up questions about highlighted sections, turning passive viewing into an interactive editing session.

Supported formats and platform availability

PDF preview and editing are now supported on both the web version of Gemini and its mobile applications.

In contrast, other file types such as Google Docs, Google Sheets, slide decks, Markdown, plain text, and code can be edited only through the web interface at this time.

This distinction reflects the current rollout plan, with broader mobile support slated for future updates.

The feature set is available to every Gemini user wherever the app is offered, regardless of subscription tier.

It also works in all languages that Gemini supports, extending the capability to a global audience.

Practical example and multilingual rollout

To illustrate the workflow, Google demonstrated a scenario where a student uploads handwritten lecture notes.

Gemini then creates a polished PDF study guide from the scanned images.

The user can manually edit the generated guide, highlight passages, and ask Gemini to refine text or graphics.

Additional queries can be posed about the highlighted content, enabling iterative improvement of the document.

The process combines AI‑driven generation with human‑in‑the‑loop editing, aiming to streamline common productivity tasks.

By handling file creation and revision inside the chat, Gemini reduces the need to switch between multiple Google Workspace apps.

The integration builds on Gemini’s existing conversational abilities, extending them into structured content manipulation.

Google’s announcement positions the Gemini app as a more comprehensive assistant for both personal and professional use.

The move aligns with broader industry trends toward embedding generative AI directly into everyday productivity tools.

Enterprises that rely on Google Workspace may find the feature useful for rapid document drafting and collaborative review.

Educators could leverage the PDF study‑guide workflow to convert handwritten notes into shareable resources quickly.

Developers can also benefit from the code editing capability, allowing them to generate snippets and receive inline suggestions.

The current limitation to web‑only editing for most formats suggests that mobile users will initially experience a narrower set of options.

Google has not disclosed a specific timeline for expanding mobile support beyond PDFs.

Security and privacy considerations remain central, as users will be uploading potentially sensitive files to the Gemini service.

Google’s privacy policies for Gemini apply, but the announcement does not detail any new safeguards for file handling.

The feature rollout follows Google’s broader AI strategy, which emphasizes integrating generative models across its product suite.

Analysts will watch how adoption rates compare with competing AI‑enhanced office tools from other vendors.

Early feedback from users will likely shape the prioritization of additional formats and mobile capabilities.

Overall, the update represents a step toward making conversational AI a more hands‑on partner in routine digital work.

Why This Matters: The ability to edit documents directly within Gemini could shorten workflow cycles by removing the need to toggle between separate applications.