Google just shipped the biggest update to Workspace since it rebranded from G Suite. And this time, it's not a chatbot sidebar you'll ignore after a week.
The March 2026 Gemini Workspace update rolls AI directly into the tools 300 million people already use — Docs, Sheets, Slides, and Drive. We're talking doc generation that pulls context from your Gmail and Drive simultaneously, spreadsheet cells that auto-populate with live web data, and slide decks that build themselves from a prompt.
We've spent the past week testing every new feature. Here's what actually works, what's still half-baked, and exactly how to use each one.
What's New: The Full Feature List
| Feature | App | What It Does |
|---|---|---|
| Cross-app doc generation | Docs | Generates documents using context from Gmail, Drive, and the web |
| Match writing style | Docs | Analyzes your past writing and mimics your personal voice |
| Fill with Gemini | Sheets | Auto-populates cells with AI-generated or live web data |
| Auto-generated decks | Slides | Creates full presentations from a text prompt |
| Semantic Drive search | Drive | Finds files by describing their content, not their filename |
| Gemini Embedding 2 | Platform | Multimodal embedding model powering semantic search |
Let's break each one down.
1. Cross-App Doc Generation in Google Docs
This is the headline feature, and honestly, it's the one that feels most like the future.
Previously, Gemini in Docs could help you write — but only with whatever you typed into the prompt. Now it can pull context from across your entire Google Workspace: emails in Gmail, files in Drive, and even live web results.
How to Use It
- Open a new or existing Google Doc
- Click "Help me write" (the Gemini icon in the toolbar)
- Write a prompt that references your other apps, e.g.: "Draft a project status update based on my email thread with Sarah about the Q2 launch, the timeline spreadsheet in Drive called 'Q2 Milestones,' and current industry trends."
- Gemini surfaces a panel showing which sources it's pulling from — you can remove sources you don't want
- Review and edit the generated document
Honest Assessment
What works well: The cross-app sourcing is genuinely impressive. It correctly identified relevant Gmail threads about 80% of the time, and Drive file retrieval was reliable when filenames or content matched the prompt.
What's still rough: It occasionally pulls the wrong email thread when you have multiple conversations with the same person about similar topics. And the generated output still needs a human editing pass.
2. "Match Writing Style" in Docs
Every AI writing tool promises to "write in your voice." Google's approach is different: it actually analyzes your existing documents.
Select 3-5 docs that represent your typical writing. Gemini creates a style profile and summarizes your patterns: "Your writing tends to be conversational, uses short paragraphs, favors active voice, and includes rhetorical questions." Toggle "Use my style" when generating content.
What works well: The style analysis is surprisingly nuanced. It picked up on tendencies like em dashes, short paragraphs, and direct address correctly.
What's still rough: It works best with 5+ samples of similar type. It mimics patterns well but can't capture genuine personality — it's your voice at 70%.
3. "Fill with Gemini" in Google Sheets
This is the feature that's going to convert skeptics.
"Fill with Gemini" lets you select a range of cells and have Gemini auto-populate them with AI-generated data, calculations, or live web data. Think of it as VLOOKUP, but instead of looking up from another sheet, it looks up from the entire internet.
Google reports that Gemini Sheets scored 70.48% on SpreadsheetBench, approaching human expert performance.
How to Use It
- Enter your column headers (e.g.,
Company Name | Founded | CEO | Latest Funding Round) - Fill in the first column with your data
- Select empty cells → right-click → "Fill with Gemini"
- Gemini reads your headers and existing data, infers what belongs, and fills them in
You can also use Gemini directly in formulas:
=GEMINI("What is the current market cap of " & A2)
What works well: Factual data population is remarkably accurate for well-known entities. Formula generation handles standard calculations reliably.
What's still rough: Data freshness is inconsistent — some cells pull current data, others seem cached. For niche entities, accuracy drops significantly.
4. Auto-Generated Slide Decks in Slides
Creating presentations is the most universally hated productivity task. Auto-generated decks won't win design awards, but they'll get you from "blank screen panic" to "decent first draft" in under a minute.
Describe your presentation (e.g., "Create a 10-slide pitch deck for a sustainable packaging startup"), optionally reference Drive files, and Gemini generates the full deck — slides, titles, bullet points, speaker notes, and layouts.
What works well: Content structure is solid. Gemini understands presentation conventions — problem before solution, financials need charts, end with a clear ask.
What's still rough: Visual design is generic. You'll spend time redesigning if aesthetics matter. Complex data visualization is limited.
5. Semantic Drive Search
Traditional Drive search works like a filename search engine. Semantic search lets you describe what you're looking for by its content.
Type natural language queries like: "The spreadsheet where I tracked our advertising spend last quarter" or "That presentation Sarah shared about the rebrand with the blue mockups."
Under the hood, it's powered by Gemini Embedding 2, a multimodal embedding model that works across text, images, video, audio, and documents in a unified space.
What works well: For text-heavy documents, semantic search found the right file in the top 3 results about 85% of the time.
What's still rough: Image and video search is less reliable. Search across very large Drives (10,000+ files) can be slow.
Google vs. Microsoft's AI Office
| Feature | Google Workspace + Gemini | Microsoft 365 + Copilot (Claude) |
|---|---|---|
| Doc generation | Cross-app context (Gmail, Drive, web) | Cross-app context (Outlook, OneDrive, web) |
| Style matching | Yes (analyze your docs) | Limited (instruction-based) |
| Spreadsheet AI | Fill with Gemini (70.48% SpreadsheetBench) | Excel Copilot (formula generation, data analysis) |
| Presentation generation | Full deck from prompts | Slide generation with design suggestions |
| Semantic search | Gemini Embedding 2 (multimodal) | Microsoft Graph + Claude |
| Pricing | Included with AI Premium ($20/mo) | Included with Copilot Pro ($20/mo) |
The honest take: If you're already in Google Workspace, these updates are a massive quality-of-life improvement. If you're in Microsoft 365, Copilot with Claude is equally compelling. Neither is worth switching ecosystems for.
Getting Started
These features are rolling out to all Google Workspace users with Gemini access ($20/month Google One AI Premium or Workspace with Gemini add-on).
- Check your plan at one.google.com
- Make sure you're on the latest app versions
- Look for the Gemini icon in each app's toolbar
- Enable semantic search in Drive settings → "Gemini features"
Recommendations by User Type
Freelancers: Start with Fill with Gemini in Sheets for competitive research, then cross-app doc generation for proposals. Could save 5-10 hours/week.
Small Teams: Semantic Drive search is your killer feature. No more "where did someone save that file?" Combine with auto-generated Slides for internal presentations.
Students: Match writing style helps maintain consistency. Fill with Gemini is excellent for research data collection. Remember: use these to accelerate your process, not replace your thinking.
Power Users: Chain the features. Cross-app doc generation → Match writing style → auto-generate Slides from the finished doc. A day of work becomes an hour of review.
The Bottom Line
Google's March 2026 Workspace update is the most significant productivity AI release since ChatGPT plugins. Not because any single feature is revolutionary — but because they're integrated into tools 300 million people already use.
What's genuinely great: Fill with Gemini in Sheets, cross-app doc generation, semantic Drive search.
What needs another iteration: Slides design quality, data freshness in Sheets, style matching fidelity.
Start with Sheets — it's where the most immediate, practical value lives.
Top comments (0)