Build Dashboards and Kanban Boards with the Google Sheets Canvas Tool

With the new Sheets Canvas feature, we can build professional-looking interactive dashboards directly in our Google Sheets, using nothing more than natural language prompts. It’s a huge upgrade from how we used to build dashboards in Sheets.

Sheets Canvas to build a professional dashboard

Previously, we clumped together charts and used formatting tricks such as borders and background cell colors to try and recreate a professional look. It was all rather challenging and time-consuming, with limited interactive options. (Read this post to see what I mean.)

Alternatively, we might have connected Google Sheets to a third-party tool, but these incurred extra costs, introduced security risks, and were often still pretty janky.

In this post, we are going to take a look at this new Sheets Canvas feature.

Sheets Canvas Availability

At the time of writing (August 2026) the Sheets canvas feature is available only in English and to users in the Gemini Beta program for work or school accounts, or the Google AI Ultra or AI Pro personal accounts.

How To Build A Dashboard with Sheets Canvas

Firstly, you need to have your data ready to go in a Google Sheet, preferably in a Tables format, which is best for Gemini.

Secondly, it pays to think about your dashboard before launching into building it.

That way, you won’t end up building something that isn’t useful. Instead, you plan what information will be shown on the dashboard and how it will work, which will result in a more successful outcome.

For example, ask yourself these questions:

  • What are the key metrics to show?
  • Who is the intended audience for this dashboard?
  • How technically literate are they? Will they understand how to read complex charts?
  • How familiar are they with this data and its background context?

With your data and design plan to hand, you’re ready to start creating a Sheets Canvas.

There are three entry points:

  1. From the toolbar: Insert > Canvas
  2. Using the “Create a canvas” button in the bottom left of your Sheet, next to the Sheet names.
    (Both 1 and 2 open the Gemini sidebar with the Canvas option pre-selected.)
  3. You can select “Create canvas” directly in the Gemini sidebar too.

1. Insert menu:

Toolbar menu to insert a Sheets Canvas

2. Create a canvas button:

Insert button for Canvas feature in Google Sheets

3. Create canvas in Gemini Sidebar:

Canvas feature in Gemini sidebar of Google Sheet

With Gemini sidebar open and the canvas feature selected, make sure you select the correct dataset(s) for the dashboard.

Use the button next to the Canvas option and choose the sheet containing your data. If you already have that sheet open, then it will automatically be selected, and you can deselect the other sheets if you don’t need them.

Select data in Sheets Canvas

Now you’re ready to insert your prompt.

Example 1: Real Estate Dashboard

Consider this dataset of real estate transactions:

Real Estate data in Google Sheets

Here’s an example prompt to build a dashboard for this data:

Build a comprehensive real estate transaction dashboard to track performance, commissions, and lead generation. Include the following elements:

1. Key Performance Indicators (KPIs): Calculate the total sum of Sales Price, Commission Income, Agent Commission, and Net Profit for Tax for all “Closed” and “Paid” deals.

2. Agent Performance: Create a summary table or chart showing the total Commission Income and Net Profit generated by each Agent.

3. Lead Source Analysis: Create a bar chart breaking down total Sales Price and total number of transactions by Lead Source to see which marketing channels are most effective.

4. Buyer vs. Seller Split: Create a visual breakdown comparing the number of transactions and total Commission Income based on the Deal Side (Buyer vs. Seller).

5. Deal Pipeline: Provide a quick count of transactions categorized by Deal Status to show how many deals are currently pending versus closed.

Please format this with a clean, professional layout, using bold headers for each section and placing the charts logically next to the summary tables. 

Use hex color #0F9E59 as the primary color and #9E0F9C as the secondary color.

Pro Tip: Save your best dashboard prompts in a prompt library for future reuse.

Typically, Gemini takes a few minutes to build the dashboard, depending on how complex your prompt is.

The output for the real estate data example looks like this:

A real estate dashboard built using Google Sheets Canvas

Notice how the colors match the colors mentioned in the prompt (#0F9E59 as the primary color and #9E0F9C as the secondary color).

Also, notice the “Add New Deal” button in the top right corner. When you click this, it opens a pop-up with a form to add new deals:

Add new data button in Sheets Canvas

This data is inserted directly into your original data table in Google Sheets. It’s a great way for users to add new data without leaving the dashboard view, and it saves users from needing to navigate the data in the spreadsheet itself.

At the the top of the canvas is a small edit bar for making changes, sharing, or deleting the canvas:

To use the “Copy link” button to share the canvas, you need to first grant file access (through the regular “Share” button in the top right of your Google Sheet) to anyone you want to share the canvas with.

Example 2: Kanban Board

The Sheets canvas tool is not limited to regular dashboards, though.

It can also build interactive Kanban boards, which is my favorite use case and a killer feature.

Build a Kanban board in Google Sheets with the Canvas feature.

Kanban boards are visual project management tools that organize tasks into columns and allow you to drag and drop cards between these columns.

Previously, this sort of interactivity was impossible inside of Google Sheets, but now with this new Sheets Canvas feature, you can build a fully featured Kanban board with a single prompt.

For example, here is a client pipeline data set for training contracts:

Sales Data Pipeline in Google Sheets

And here’s an example prompt to generate a Kanban board from this data:

Please generate a Kanban board layout with the following specifications:

1. Structure: Group the data using the “Stage” column.

2. Card Details: Under each Stage header, create individual “cards” or grouped cells for each transaction. Each card should display the most critical information at a glance:

  • Company & Client Name
  • Deal Size & Expected Value

3. Formatting:

  • Please apply conditional formatting or color-coding to the cards based on the “Probability” column (e.g., green for high probability, yellow for medium, red/gray for low) so I can easily identify which deals are most likely to close.
  • Ensure the layout is clean and minimalist.

The output from this prompt looks something like this:

Kanban Board in Sheets Canvas

You can then drag these cards into different columns as needed to show progress. When you drag a card into a new column, the data in the underlying sheet also updates to reflect that, so they are always synced in real time.

And as with the dashboard from earlier, there is also a button to add new data from the Kanban canvas rather than having to go back to the actual spreadsheet data.

Limitations

At the moment, if you want to modify the dashboard generated by the Sheets Canvas tool, you give it an additional prompt in the Gemini sidebar. For example, you might prompt Gemini with “change the leads pie chart into a bar chart“.

Unfortunately, when Gemini updates the dashboard, other elements might inadvertently change too.

I think the real breakthrough will come when we can click on individual features within the Dashboard or Kanban board and give specific instructions to modify that specific feature only with a prompt. Hopefully that is something coming down the line.

Conclusion

This new Sheets Canvas feature is a fantastic tool that dramatically expands the possibilities of what you can do with data in Google Sheets.

And, whilst the regular chart tool will remain extremely useful for specific analysis and one-off charts, the old way of building dashboards is rapidly becoming obsolete.

I can’t imagine spending hours manually positioning charts, hand-picking background cell colors and borders, and all manner of other dark arts, to build a dashboard the old way, knowing it wouldn’t even look half as good as what this new canvas tool can build in a few minutes.

If you have access to this canvas tool, then I encourage you to experiment with it to build your dashboards.

How to Build a Content Engine with Apps Script, NotebookLM, and a Gemini Gem

Most of us are sitting on an absolute goldmine of unstructured data.

Think about it: years of client reports, research notes, project documentation, YouTube videos or, in my case, a decade’s worth of newsletter archives.

Usually, this information just sits there dormant. Why? Because it’s spread all over the place, too tedious to search through and catalog, and way too dense to summarize manually.

But by combining Apps Script, NotebookLM, and Gemini Gems, we can transform that forgotten archive into an AI content engine. We’re talking about a system that can access all your content and generate new work based on that specific foundation.

Why NotebookLM AND a custom Gem?

By using NotebookLM as the data foundation and a Gemini Gem as the creative interface, we create a workflow that captures the best of both worlds.

NotebookLM acts as a secure vault containing our data, ensuring that new derivative work is strictly grounded in our own history. However, NotebookLM is a research tool built more for consuming (reading, listening, slide decks, flash cards etc.) rather than creating “new” content. It lacks the ability to remember our voice between chats or access the live web.

A Gemini Gem, on the other hand, serves as a creative foil. It can remember our specific voice and formatting preferences, so we don’t have to explain this each time. It can also access the web to incorporate external data, if required. And it can generate images and video too.

This architecture allows us to take our archived knowledge and quickly transform it into new, high-quality content.

How To Build a Content Engine

To build this workflow, we need to solve for three things: 1) extracting our data, 2) storing our data, and 3) generating new content from this data.

If you don’t have much source data then you can just add it directly as sources in your NotebookLM (go straight to step 3 below).

But if you have a lot of source data (in my case, 375 newsletters at about 500,000 words and 240 blog posts at about 700,000 words) then it’s not as simple as just uploading them one-by-one to NotebookLM. For one thing, you can’t upload that many separate source docs to NotebookLM (the limit on the free plan is 50 sources). Secondly, can you imagine how tedious it is to manage almost 600 different sources!

The solution is to create a script to scrape all these web links and dump the content into a series of Google Docs. I created ten Google Docs, each with about 60 pieces of content. Don’t try to put everything into one single giant Doc, as again, you might run into the size limits in NotebookLM, which is up to 500,000 words per source.

1. Code Your Scraper (Optional)

I started with a Google Sheet containing a list of newsletter subject lines in column A and the URLs of the hosted newsletter content in column B, with 375 rows in total.

(Sign up to get the newsletter here)

Don’t worry, we don’t need to write the script ourselves from scratch! Simply prompt Gemini to write a Google Apps Script for you.

I used this prompt in Gemini to generate the script that would visit each URL in turn and save the text into a Google Doc. To ensure it could handle the volume of data without timing out (Apps Script has a 6-minute limit) I asked Gemini to grab content in batches and keep track of rows, so the script could “resume” where it left off.

Generate a Google Apps Script that takes a list of website links from a sheet called ‘Newsletter URLs’ and saves them into a single Google Doc. Put the subject line from Column A as a Heading 1 and then pull all the text from the URL in Column B underneath it.

It needs to remember where it left off if it hits a time limit, so I can just hit ‘Run’ again to pick up the progress. Also, make sure it pauses for a few seconds between each link and refreshes the document connection every few rows so it doesn’t crash or get blocked by the websites.

In your Sheet with the list of links, go to Extensions > Apps Script

Copy in the script that Gemini created.

Make sure your insert the correct ID from your Google Doc

To begin with, run a test with 5 URLs to ensure the script works as intended. If you encounter any errors, paste them back into Gemini and ask for a fix.

Once you’re happy its working, move to step 2 and start consolidating your online content into Google Docs.

2. Extract and Consolidate Your Data

Run your script from the Google Sheet containing your source URLs. It will visit each link in turn and paste the data into your Google Doc in batches.

This centralizes disparate web data into a single, clean Google Doc.

3. Create Your NotebookLM Archive

Visit NotebookLM and create a new notebook.

Upload your consolidated Google Docs as Sources.

This “grounds” the AI, ensuring it only uses your verified history and doesn’t “hallucinate” outside facts.

4. Distill Your Voice to Create a Style Guide

Back in Gemini, in a new chat, connect it to one of these Google Docs, which contains your best writing.

Prompt Gemini to analyze your voice and identify your unique formatting habits, vocabulary preferences, and “persona”.

Based on the attached google doc of my writing published online, write a style guide for a custom Gem that captures my voice. The instructions should enable the gem to write in my voice, using a notebooklm backend with access to all my previous published writings

In my example, this was the response from Gemini, which was a good starting point that could be tweaked to create my unique style guide:

Once you’re happy with the response, save it as a Style Guide in a Google Doc.

5. Build the Gem (The Interface)

In Gemini, open the Gem Manager and create a New Gem.

Link your NotebookLM archive in the “Knowledge” section and paste your Style Guide rules from section 4 into the Instructions box.

Hit Save and move to step 6!

6. Use Your Gem to Create New Content

Test the Gem with a prompt like: “Using the logic from [Source Name], draft a new response in my voice”.

In my example, I tried this prompt:

draft a newsletter about the VSTACK function

And here is the newsletter Gem taking this simple start prompt about the VSTACK function and generating a newsletter that is a pretty good mimic of the real thing.

Of course, if I was to use this example, I would need to review the text with a fine tooth comb, check all the examples, fix the links, and rewrite sections to make it my own.

However, as a first step, to generate ideas or scaffolding, it’s incredibly helpful.

Now, instead of spending hours drafting, I can ask my Gem to “draft a new tip about data validation based on the logic I used in Tip #210.” It generates a plausible draft in my voice, using my historical data, in seconds.

How I Used Google Forms, AI, and Apps Script Automation to Analyze 1,700 Survey Responses

This post describes how I designed and ran an audience survey with over 1,700 responses, using Google Forms, Sheets, Apps Script, and ChatGPT. I’ll show you the entire process from end-to-end, including how I:

  1. Created a survey with Google Forms
  2. Used Apps Script to automatically say thank you to 1,700 respondents
  3. Analyzed the response data in Google Sheets
  4. Used AI to help me understand the qualitative data
  5. Presented the results in Google Docs

This flowchart shows how the system is set up:

Survey Flow Chart
Continue reading How I Used Google Forms, AI, and Apps Script Automation to Analyze 1,700 Survey Responses

Three Ways To Use AI Tools With Google Sheets

AI course for Google Sheets

Although AI has been around for decades, it’s only really been available to the public in its current form for the past year or so. And with the rise of these generative AI tools, like ChatGPT and Google Bard, AI is more accessible than ever.

But where does AI fit with Google Sheets?

And how do we use AI tools with Google Sheets?

In this post we’re going to look at how to use the most popular AI tools with Google Sheets. You’ll see how easy it is get started and learn that AI isn’t rocket science. It’s simply another useful tool that can save you time when you work with Google Sheets.

Specifically, we’ll look at three ways to use AI tools with Google Sheets:

  1. Chatbots like ChatGPT or Bard
  2. Google Sheets Add-Ons
  3. Via the API and Apps Script (advanced)

Continue reading Three Ways To Use AI Tools With Google Sheets

What AI Can Do For You As A Google Sheets User. Is The Hype Justified?

In this post, we’re going to take a 40,000 ft view of the Artificial Intelligence (AI) landscape and see how you can use it alongside Google Sheets to boost your productivity.

And, at the end of the post, I’ll answer the question about whether I think the AI hype is justified.

Before looking at what AI can do with Google Sheets though, let’s start with a quick AI 101 to ensure we’re up to speed with the lingo.

Green Tea Image generated by Dall-E
Image generated by Dall-E, a deep learning model, using the prompt “a cup of tea with a green potion inside with thin swirling vapors rising out of it”

Continue reading What AI Can Do For You As A Google Sheets User. Is The Hype Justified?