Google Gemini adds native file generation and editing to chat

Streamlining the workflow

Google recently announced a significant update to Gemini that allows users to generate, preview, and edit files directly within the chat interface. This move is designed to redefine how people compile information into different formats based on their specific needs. By integrating these capabilities, Google aims to make the AI a more central part of daily work routines.

Previously, users often had to copy text from a chatbot and manually arrange it into a separate word processor or spreadsheet. This new feature removes that extra step, allowing the AI to handle the heavy lifting of document structure. As Technowize reported, the goal is to eliminate the frustration of manual arrangement in tools like Word or Google Docs.

The update makes it possible for the next document a user receives to be generated from start to finish by AI. This is particularly useful for tasks that require specific layouts, such as creating slide decks for a class or a formal PDF for a manager. It positions Gemini as a more capable alternative to traditional office suites by handling the transition from raw data to finished files.

Multimodal capabilities in action

One of the most convenient aspects of this update is its multimodal capability, which allows the AI to process different types of inputs. For example, a user can share images of handwritten notes or excerpts from existing documents with the chatbot. Gemini can then compile these various sources into one consolidated file in a preferred format.

The editing tools provided within the chat are quite granular and allow for significant customization. Users can expand a file to full screen to type in direct edits or highlight specific sections of the text to ask the AI follow-up questions. This allows for a more interactive way to refine the content as it is being built.

The system also supports redesigning elements within a generated document, similar to how one might set up a blog on a platform like WordPress. Users can perform specific actions such as converting a data table into a graph or inserting additional information into the middle of a results section. Once the document is perfected, it can be exported to local storage or saved directly to Google Drive.

Platform and format availability

The availability of these new features depends slightly on the device the user is using and the specific file type they want to create. PDF preview and editing functions are currently available to all users in all supported languages on both web and mobile platforms. This ensures that mobile users can still interact with and modify PDF documents on the go.

However, there are some limitations regarding other file types like Google Docs, Google Sheets, slide decks, Markdown files, and TXT files. These specific formats can currently only be created and edited on the web version of Gemini. This distinction may affect how different users choose to interact with the tool depending on their hardware habits.

Despite these minor differences in platform access, the update is available to all users of the Gemini app. This broad availability makes it a significant step toward making AI-driven document creation a standard part of the user experience. It allows for a more seamless transition between brainstorming an idea and producing a finished, shareable file.

The competitive landscape

Google is not the only company looking to simplify the way people interact with AI and documents. Earlier this month, Claude introduced add-ons for Google Workspace that allow its AI to edit and add content directly into Docs, Sheets, and Slides. This creates a similar experience where users can skip the back-and-forth of copying content between different applications.

While Claude offers a way to edit content within the Google Workspace environment, Gemini has a built-in advantage by being integrated into the Google ecosystem by default. Claude users can also paste links to Google documents into the Claude page to request edits, but this is a separate integration rather than a native file generation tool. The two tools are essentially competing to offer the most frictionless path from prompt to finished product.

The competition highlights a broader trend where AI tools are trying to become more deeply embedded in professional workflows. By reducing the number of steps required to produce a final output, both Google and its competitors are trying to capture more of the lucrative work-routine market. The focus is shifting from what the AI can say to what the AI can actually build and organize for the user.

Shifting skills and expectations

These advancements in AI technology are doing more than just saving time; they are reshaping the skills and knowledge that people build. As tools become more capable of handling layout, formatting, and data organization, the need for manual proficiency in these areas may decrease. This raises questions about what skills will be prioritized as AI takes over more of the