How to Create a Simple Dashboard in Looker with AI

Creating a dashboard in Looker Studio (formerly Google Data Studio) can feel intimidating, especially when you're just starting out. But with the introduction of AI-powered features, you can now build reports by simply describing what you want to see. This guide will walk you through creating a simple dashboard in Looker Studio using natural language prompts, turning a once-complex task into a quick conversation.

Graphed

Build AI Agents for Marketing

Build virtual employees that run your go to market. Connect your data sources, deploy autonomous agents, and grow your company.

Build Your First Agent

First, What is Looker Studio?

Looker Studio is Google's free business intelligence and data visualization tool. It lets you connect to hundreds of data sources - like Google Analytics, Google Sheets, Google Ads, and BigQuery - and transform that raw data into interactive and shareable dashboards. Businesses use it to monitor key performance indicators (KPIs), track marketing campaign performance, and understand customer behavior.

Traditionally, building reports involved dragging and dropping dimensions (like 'Country' or 'Campaign') and metrics (like 'Sessions' or 'Revenue') onto a canvas. While powerful, this manual process required a clear understanding of your data structure and a bit of a learning curve to master the interface. The new AI capabilities aim to flatten that curve, making data analysis more accessible to everyone on the team, regardless of their technical expertise.

Setting Up Your Looker Studio Environment

Before you can start chatting with your data, you need to connect it to Looker Studio. For this tutorial, we'll use Google Analytics, a common starting point for marketers and business owners. The process is similar for other data sources.

AI Agents for Marketing

Crash Course

Graphed

Free PDF · the crash course

AI Agents for Marketing Crash Course

Learn how to deploy AI marketing agents across your go-to-market — the best tools, prompts, and workflows to turn your data into autonomous execution without writing code.

Download the PDF

Step 1: Connect Your Data Source

Getting your data into Looker is the most important first step. Luckily, connectors for Google products are straightforward.

• Log in to Looker Studio with your Google account.
• On the main page, click the + Create button in the top left and select Report.
• You'll be taken to the connector gallery. This is where you choose where your data is coming from. Find and select Google Analytics.
• You may be asked to authorize Looker Studio to access your Google Analytics account. Click Authorize.
• Once authorized, you will see a list of the GA accounts and properties you have access to. Select the account and the specific GA4 property you want to analyze (e.g., your company's website data).
• Click the Add button in the bottom right corner. A confirmation pop-up will appear, click Add to Report.

That's it! Your blank report canvas is now connected to your Google Analytics data, ready for you to create visualizations.

Using Looker's AI to Build Your Dashboard

Now for the fun part. Instead of manually building charts, we'll use prompts to tell Looker what we want to create. Looker’s prompt-based report generation works a bit like ChatGPT, but it's specifically designed to understand your connected data schema.

Meet the "Prompt to Report" Feature

When you create a new report, you might see a dialog box that says, "Quickly get started by generating the full report from a text prompt." This is your entry point to AI report building.

If you don't see this, you can still generate individual charts using prompts. Go to Insert > Prompt to chart from the top menu. This will open a panel where you can type your request.

Building Your First AI-Generated Chart (Step-by-Step)

Let's start with a simple request. We want to see where our website traffic is coming from geographically.

Instead of manually finding and adding a "Geo chart" and then configuring the "Country" dimension and "Sessions" metric, you can just ask for it. In the prompt box, type:

Create a map showing sessions by country

Press enter, and Looker Studio will analyze your request and generate a world map where countries are color-coded based on the number of website sessions. It handles picking the chart type, dimensions, and metrics for you in seconds.

You can then click Add to report to place this chart on your dashboard canvas.

Pro Tip: Be Specific with Your Prompts

The quality of your AI-generated chart depends heavily on the quality of your prompt. Vague prompts lead to generic (or incorrect) results. The key is to be as descriptive as possible.

• Include the chart type: "Create a bar chart...", "Show me a pie chart...", "Generate a time series chart..."
• Name the dimensions and metrics: Use the exact names from your data source if you know them (e.g., 'New users', 'Conversion rate').
• Specify the timeframe: Mention a date range like "...for the last 30 days" or "...for Q4 2023."

Example of a vague vs. strong prompt:

• Vague: "Traffic over time"
• Strong: "Create a line chart showing daily new users for the last 90 days"

Graphed

Build AI Agents for Marketing

Build virtual employees that run your go to market. Connect your data sources, deploy autonomous agents, and grow your company.

Build Your First Agent

Asking Follow-Up Questions and Refining Visualizations

The AI feature is conversational, allowing you to iterate and refine your charts. Let's say you've created your map but now want to see the same data as a list. You can simply ask:

Show this as a table instead

Looker will regenerate the visualization as a table with countries and their corresponding session counts. This iterative process is powerful because it lets you explore different ways to view your data without starting from scratch each time.

Here are a few other follow-up prompts you could try:

• "Sort this table by highest sessions"
• "Add a column for engagement rate"
• "Only show countries from Europe"

This back-and-forth conversation makes data exploration faster and feel more intuitive than clicking through menus.

Laying Out a Full Dashboard

A true dashboard isn't just one chart, it's a collection of visualizations that give you a complete picture of performance. You can use AI to build each element and then arrange them on your reporting canvas.

Building Several Charts for a Cohesive View

Start populating your report with the most important KPIs. Generate a few key charts one by one to monitor top-level metrics:

• User Overview: Start with some scorecards. Prompt: "Create scorecard for total users, new users, and sessions for the last 28 days"
• Traffic Source Analysis: Understand where users come from. Prompt: "Create a pie chart showing sessions by default channel grouping"
• Engagement Trends: See how performance changes over time. Prompt: "Generate a time series chart of user engagement by date for the last 90 days"

After each prompt, add the generated visual to your report. You'll now have a canvas with three or four distinct charts.

AI Agents for Marketing

Crash Course

Graphed

Free PDF · the crash course

AI Agents for Marketing Crash Course

Learn how to deploy AI marketing agents across your go-to-market — the best tools, prompts, and workflows to turn your data into autonomous execution without writing code.

Download the PDF

Organizing Your Dashboard for Clarity

How you arrange your visualizations is crucial for readability. A cluttered dashboard is an ignored dashboard. Here are a few simple design principles to follow:

• The Upper Left is Prime Real Estate: Place your most important KPIs, usually your scorecards, in the top left corner. This is where people naturally look first.
• Think in Rows or Columns: Group related charts together. For example, you might have a row dedicated to user acquisition metrics and another row for on-site engagement.
• Add Context: Use the Text box tool (Insert > Text) to add clear titles for your dashboard and individual sections. A title like "Monthly Website Performance" immediately tells the viewer what you're looking at.
• Maintain Space: Avoid packing charts too closely together. White space makes the report easier to scan and comprehend.

Click and drag your AI-generated charts into a logical layout. You can easily resize them by dragging their corners to fit your grid.

Beyond the Basics: Customization and Sharing

Once you've generated charts with AI, you still have full manual control. Select any chart, and the Properties panel will appear on the right. Here you can:

• Change colors, fonts, and backgrounds under the Style tab.
• Add a chart-level filter or tweak dimensions and metrics under the Setup tab.

When your dashboard is ready, you can share it with your team. Click the Share button in the top right. You can invite specific people via email or get a shareable link, controlling whether they can view or edit the report. This real-time collaboration is one of Looker Studio's core strengths.

Final Thoughts

By leveraging Looker Studio's AI features, you can significantly reduce the time it takes to build insightful reports. The ability to use plain-English prompts lowers the technical barrier, empowering more people to move from simply having data to actually understanding it and making better decisions.

While Looker's AI is a big step forward inside the Google ecosystem, bringing data together from multiple platforms - like your ads, CRM, and e-commerce store - can still be cumbersome. We designed Graphed to take this natural language approach to the next level by specializing in just that. By connecting sources like Google Analytics, Facebook Ads, Shopify, and Salesforce in one click, you can create unified, real-time dashboards with a single prompt like, "Show me a dashboard of my marketing funnel, from Facebook ad spend and clicks to Shopify sales," and Graphed builds it for you instantly.