TLDR
- Google is rolling out expanded Gemini AI features in Docs, Sheets, Slides, and Drive for AI Ultra and Pro subscribers.
- In Docs, Gemini can draft documents, match writing styles, and apply formatting from reference files.
- Sheets users can now build full spreadsheets via text prompts, with real-time data from Google Search.
- Google also unveiled Gemini Embedding 2, a multimodal model that handles text, images, video, audio, and PDFs in one unified space.
- Alphabet (GOOGL) stock was up fractionally in midday trading on Tuesday.
Google is pushing Gemini deeper into its productivity tools. The company announced Tuesday that Gemini AI features are expanding across Google Docs, Sheets, Slides, and Drive — available in beta for AI Ultra and Pro subscribers starting immediately.
Introducing the new Gemini powered Docs, Sheets, Slides, and Drive experience featuring AI Overviews, fulled editable AI made slides, and new grounding sources to make writing docs context aware 📃
Available today to G1 Pro and Ultra users : ) pic.twitter.com/tpYmnN2wV2
— Logan Kilpatrick (@OfficialLoganK) March 10, 2026
The rollout covers English users globally for Docs, Sheets, and Slides. Drive’s new features are U.S.-only for now, with plans to expand to more languages down the line.
In Docs, users can describe what they need and Gemini will generate a document pulling from existing files, emails, and the web. It can also match the writing style of other documents and apply formatting from a reference file — useful for things like populating a travel itinerary template with flight and hotel details from emails.
Sheets gets a similar treatment. Users can prompt Gemini to build entire spreadsheets from scratch. One example Google gave: a moving checklist that pulls contact details from emails and tracks quotes from your inbox.
The Fill with Gemini feature goes a step further — it can pull real-time data from Google Search to populate tables. Think college application deadlines or tuition figures, filled in automatically.
Slides and Drive Also Get Updates
In Slides, Gemini can generate individual slides that match the existing deck’s theme and colors. It can pull context from files, emails, and the web. Google says full presentation generation from a single prompt is still in development.
Drive’s Ask Gemini feature adds AI-generated summaries at the top of search results, pulling from files with citations. Users can query across documents, email, calendar, and web sources from one place.
Gemini Embedding 2 Also Launched Tuesday
Separately, Google unveiled Gemini Embedding 2, a new multimodal model that processes text, images, video, audio, and documents in a single unified embedding space.
The model supports up to 8,192 input tokens for text, handles up to six images per request in PNG or JPEG format, and processes up to 120 seconds of video in MP4 or MOV formats.
It can also ingest audio directly — no transcription needed — and embed PDFs up to six pages long.
Google said the model supports over 100 languages and is designed for tasks like semantic search, sentiment analysis, and Retrieval-Augmented Generation (RAG).
The company positioned it as outperforming models from Amazon and Voyage in text, image, and video tasks — though those are Google’s own comparisons.
Alphabet (GOOGL) stock was up fractionally in midday trading on Tuesday.





