Google is expanding Gemini’s role inside Workspace by allowing users to interact directly with images stored in Google Drive. The new feature, already rolling out and set to reach everyone by September 9, adds a Gemini sidebar that lets you “talk” to images — whether that means extracting details, summarizing content, or even generating alternative descriptions.
The feature is clearly designed with scanned documents in mind. Receipts, invoices, and contracts can now be processed more conversationally, sparing users from manually parsing text-heavy images. But it also works with less formal files. For instance, Gemini can generate captions for photos or even spin short stories from what it sees, though Google positions those as side perks rather than the main draw.
For now, access is limited. You’ll need a paid Workspace plan such as Google One AI Premium or Business Standard to try it out. Free accounts don’t have the option yet.
Using Gemini with images in Drive works in a couple of ways. If you select an uploaded image and click the Gemini icon in the top-right corner, a sidebar opens where you can type prompts and get contextual responses. Right-clicking on an image and choosing “Summarize this file” also works, though it offers fewer immediate options and may require more manual prompting.
Google has been steadily weaving Gemini deeper into Workspace apps, from Docs to Gmail, and Drive’s image support is the latest step. However, the convenience comes with caution. Security researchers have previously demonstrated attacks that hide malicious instructions in otherwise harmless-looking calendar and image files. That means uploading unfamiliar files and asking Gemini to process them isn’t risk-free.
For most users, though, the update could turn Drive into more than just storage. Instead of digging through scans or old paperwork, you’ll be able to query Gemini for quick answers — as long as you’re paying for the right Workspace tier.
