Published on March 20, 2026

Gemini in Google Sheets AI Assistant Now Works with Data

Gemini in Google Sheets: AI Assistant Now Works with Data at a State-of-the-Art Level

Google has announced new beta features for Gemini in Sheets: the AI assistant can now create, edit, and analyze entire tables based on a text prompt.

Products 4 – 5 minutes min read
Event Source: Google 4 – 5 minutes min read

Working with spreadsheets often involves spending excessive time on routine tasks or encountering challenges when a task becomes slightly more complex than usual. Formulas, pivot tables, and conditional formatting all require either specialized knowledge or considerable patience. Google has decided to address this problem in a new way: by allowing users to simply ask an AI to perform these tasks.

The company recently announced new beta features for Gemini in Google Sheets. In essence, the AI assistant is now capable of more than just suggesting formulas or answering questions about data; it can fully work with tables, including creating them from scratch, editing, structuring, and analyzing them – all from a simple text description.

What Has Changed in Google Sheets AI

What Exactly Has Changed

Previously, Gemini in Sheets was primarily perceived as a smart assistant: it could explain concepts, suggest formulas, or help with queries. Now, it is taking on a more active role by directly manipulating the table's contents.

Simply put: you describe the task in words, and Gemini executes it. Want to create a table to track a household budget? Just ask – and you'll receive a pre-built structure. Need to analyze sales data and highlight key trends? Describe what you're looking for, and the AI will take care of it.

It's worth noting that Google claims to have achieved so-called state-of-the-art performance, meaning Gemini in Sheets now delivers results on par with the best existing solutions in its category. This is not merely a marketing claim; it signifies that the model has reached the forefront of competing approaches in its quality of handling tabular data.

Gemini Handles Complex Data Tasks

It Works for Complex Tasks, Too

Here's a key point: these new capabilities are not limited to simple operations. Gemini can handle basic tasks (like creating a table, adding rows, and formatting data) as well as more sophisticated analysis.

For example, you can ask the system to find patterns in a dataset, group information by desired criteria, or prepare a summary from a large set of records. Previously, this would have required either a strong command of Excel-like tools or the involvement of specialists. Now, it's accessible through a simple text prompt.

This fundamentally changes who can work effectively with spreadsheets. Whereas the barrier to entry for complex data analysis was once quite high, it is now significantly lower.

Impact of Google Sheets AI Beyond Workspace

Why This Matters Beyond Google Workspace

One might view this as just another update to a corporate product – and in some sense, that's true. However, there's a broader context at play here.

Spreadsheets are among the most universal tools globally, utilized by financiers, students, marketers, researchers, small businesses, and large corporations alike. Google Sheets, meanwhile, is one of the most widely used spreadsheet editors worldwide, available for free. When an AI assistant in such a tool achieves best-in-class performance, it impacts a very large audience.

Furthermore, this is part of a broader trend: AI is ceasing to be a separate application or chatbot and is becoming more deeply embedded into familiar workflows. There's no need to switch between tabs, copy data, or re-explain the context – everything happens right where you work.

Beta Features Mean AI Not Perfect Yet

Beta Means It's Not Perfect

To be fair, these features are announced as being in beta. This means they aren't immediately available to all users, and Google is still gathering feedback to refine the system.

In practice, this means you might encounter inaccuracies, limitations with certain data types, or situations where the AI misinterprets your request. This is a normal part of the development cycle; the company is intentionally releasing the product to a broader audience to observe its performance in real-world conditions, not just on test datasets.

So, if you give it a try and something goes wrong – that's to be expected. The important thing is that the direction is clear, and judging by the stated quality metrics, there is plenty of room for growth.

Key Takeaways on Google Sheets AI

The Bottom Line

Google has integrated an updated Gemini into Sheets, which can now fully work with data: creating tables from a description, editing, structuring, and analyzing information – from simple tasks to complex analysis. According to the company, the quality of its performance is on par with best-in-class solutions.

For those who regularly work with spreadsheets but are not experts in formulas and pivot tables, this is a potentially game-changing update. For the industry as a whole, it's another step towards AI becoming not a separate tool, but an integrated part of what you already use every day.

Original Title: Gemini in Google Sheets just achieved state-of-the-art performance.
Publication Date: Mar 10, 2026
Google blog.google An international technology company developing digital services, cloud platforms, and AI technologies for search, advertising, productivity, and consumer products.
Previous Article How GitHub Secures Agentic Workflows: A Look Inside the Security Architecture Next Article Adobe Firefly: New Tools for Video and Image Editing, and Support for Custom Models

Related Publications

You May Also Like

Explore Other Events

Events are only part of the bigger picture. These materials help you see more broadly: the context, the consequences, and the ideas behind the news.

From Source to Analysis

How This Text Was Created

This material is not a direct retelling of the original publication. First, the news item itself was selected as an event important for understanding AI development. Then a processing framework was set: what needs clarification, what context to add, and where to place emphasis. This allowed us to turn a single announcement or update into a coherent and meaningful analysis.

Neural Networks Involved in the Process

We openly show which models were used at different stages of processing. Each performed its own role — analyzing the source, rewriting, fact-checking, and visual interpretation. This approach maintains transparency and clearly demonstrates how technologies participated in creating the material.

1.
Claude Sonnet 4.6 Anthropic Analyzing the Original Publication and Writing the Text The neural network studies the original material and generates a coherent text

1. Analyzing the Original Publication and Writing the Text

The neural network studies the original material and generates a coherent text

Claude Sonnet 4.6 Anthropic
2.
Gemini 2.5 Pro Google DeepMind step.translate-en.title

2. step.translate-en.title

Gemini 2.5 Pro Google DeepMind
3.
Gemini 2.5 Flash Google DeepMind Text Review and Editing Correction of errors, inaccuracies, and ambiguous phrasing

3. Text Review and Editing

Correction of errors, inaccuracies, and ambiguous phrasing

Gemini 2.5 Flash Google DeepMind
4.
DeepSeek-V3.2 DeepSeek Preparing the Illustration Description Generating a textual prompt for the visual model

4. Preparing the Illustration Description

Generating a textual prompt for the visual model

DeepSeek-V3.2 DeepSeek
5.
FLUX.2 Pro Black Forest Labs Creating the Illustration Generating an image based on the prepared prompt

5. Creating the Illustration

Generating an image based on the prepared prompt

FLUX.2 Pro Black Forest Labs

Don’t miss a single experiment!

Subscribe to our Telegram channel —
we regularly post announcements of new books, articles, and interviews.

Subscribe