How to Create a Quarterly Report in Looker with AI

Creating a quarterly report often feels like a race against the clock, involving hours of pulling data, wrangling spreadsheets, and piecing together charts. It doesn't have to be that way. By using Looker’s built-in AI capabilities, you can build a comprehensive and insightful report in a fraction of the time. This article will walk you through exactly how to create your next quarterly report in Looker using the power of conversational AI.

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

Why Quarterly Reports Are Still Essential

In a world of real-time dashboards, the idea of a static quarterly report might seem a bit old-fashioned. But these reports serve a critical purpose beyond just summarizing past performance. They provide a structured moment to pause, analyze trends, and align your entire team - and your stakeholders - on what’s working, what isn't, and where you should focus your efforts for the next 90 days.

The problem is the process. A typical quarterly reporting cycle looks something like this:

• Manually exporting CSV files from a dozen different platforms (Google Analytics, Salesforce, Shopify, etc.).
• Stitching this data together in Excel or Google Sheets, often struggling with mismatched date formats and inconsistent naming conventions.
• Building charts and pivot tables to visualize key metrics.
• Copy-pasting those visuals into a PowerPoint or Google Slides presentation.
• Dealing with last-minute questions that send you back to Step 1 to re-pull the data.

This process is not only tedious but also prone to error. By the time you present the report, half the week is gone and the data might already be slightly out of date. This traditional approach keeps you trapped in the gathering of data, leaving little time or energy for the actual analysis that drives smart business decisions.

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

Meet Your New Analyst: Looker GenAI

Looker, now part of Google Cloud, has integrated generative AI to address this exact problem. Think of it as having a junior data analyst you can talk to. Instead of navigating complex menus, searching for the right fields, and configuring visualizations manually, you can simply ask for what you want in plain English. This conversational approach dramatically lowers the barrier to entry, empowering more people on your team to explore data without needing a deep technical background.

The core benefit of using AI in Looker is speed. What used to take 30 minutes of clicking, dragging, and dropping can now be accomplished with a single sentence. This frees you up to ask more follow-up questions, drill down into interesting trends, and uncover insights you might have otherwise missed.

A crucial prerequisite, however, is a well-structured LookML model. LookML is Looker's data modeling language that acts as an abstraction layer over your database. For the AI to understand your plain-English questions, your data team needs to have defined your business logic, dimensions, and measures in a clear, semantic way. A good LookML model is the brain, the AI is the friendly interface that lets you talk to it.

How to Create a Quarterly Report in Looker with AI: A Step-by-Step Guide

Ready to build your report? Let’s walk through the process, from defining your metrics to assembling the final dashboard.

Step 1: Set Your Objectives and Define Your KPIs

Before you write a single prompt, you need a plan. A great report tells a story. What story are you trying to tell about the last quarter? Are you focusing on growth, efficiency, or profitability? Start by outlining the key questions you need to answer for your audience.

Some common KPIs for a quarterly business review include:

• Revenue & Growth: Total Revenue, Quarter-over-Quarter (QoQ) Growth Rate, Revenue by Product/Service.
• Marketing Performance: Customer Acquisition Cost (CAC), Return on Ad Spend (ROAS), Website Traffic, Lead-to-Customer Conversion Rate.
• Sales Performance: New Deals Closed, Average Deal Size, Sales Cycle Length, Pipeline Conversion Rates.
• Customer Success: Customer Churn Rate, Net Promoter Score (NPS), Customer Lifetime Value (CLV).

Jot these down. This list will be your roadmap for the prompts you’ll use in Looker.

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

Step 2: Start the Conversation with Your Data

With your KPIs defined, it’s time to generate the core visualizations. In a Looker Explore or a dashboard, find the conversational GenAI interface. It’s typically a chat box where you can type your request. Now, let’s translate your KPI list into simple questions.

Start broad. For an overall business health check, you might ask:

Show me total revenue by quarter for the last 12 months as a bar chart.

Looker’s AI will interpret your prompt, find the relevant fields in your LookML model (like "order date" and "sale price"), aggregate the data, and generate the chart for you. In seconds, you have your first visual. If it’s not quite right - maybe you’d prefer a line chart - you can easily follow up:

Change this to a line chart.

This iterative process feels natural and removes the guesswork of hunting for the right settings.

Step 3: Drill Down to Answer "Why?"

The first chart shows you what happened (revenue grew by 15%), but the most valuable insights come from understanding why. This is where the conversational AI shines. Instead of starting a new report, just ask a follow-up question related to the chart you just created.

Let’s continue our revenue exploration:

• Original Prompt: Show me total revenue by quarter for the last 12 months.
• Follow-up #1: Now break this down by product category.
• Follow-up #2: Show only the "Electronics" category and trend it by month instead of quarter.
• Follow-up #3: Which marketing channel drove the most revenue for electronics this quarter?

Notice how the conversation logically flows from a high-level overview to a granular insight. This process mimics how you would talk to a data analyst, allowing you to follow your curiosity and uncover the root causes behind the numbers without losing your train of thought.

Example Prompts for Other KPIs:

Here are a few more examples of prompts you could use to flesh out your quarterly report:

• For Marketing: Compare my Customer Acquisition Cost and Return on Ad Spend for Facebook Ads vs Google Ads campaigns this quarter.
• For Sales: What's our win rate by sales representative for deals closed in the last 90 days? Show it as a table.
• For Web Performance: Create a line chart of weekly website sessions for Q3 vs Q2 of this year.

Step 4: Assemble Your Quarterly Dashboard

As the AI generates each visual “answer” (called a Look), you can easily add it to a new dashboard. Think of this as your canvas for the final report. Simply pin each chart you create to a new or existing dashboard.

Once all your visuals are on the page, you can arrange them to tell your story. Start with the highest-level summary KPIs at the top (like overall revenue and growth), then group more detailed charts by department (Marketing effectiveness, Sales pipeline, etc.). This structure helps your audience easily digest the information and understand how different parts of the business contribute to the overall picture.

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 5: Add Narrative and Context

A dashboard of charts is not a report. The final, and arguably most important, step is to add your human analysis. Why did that marketing campaign perform so well? What caused the sales cycle to lengthen this quarter? The charts show the data, but you provide the meaning.

Use Looker's text tiles to add titles, section dividers, and short summaries directly onto your dashboard. For each section, write a few bullet points explaining:

• The key takeaway from the data. (e.g., "Paid search continues to be our most efficient acquisition channel.")
• The business reason behind the trend. (e.g., "This is likely due to the new ad copy we launched in August.")
• The recommended next steps. (e.g., "We recommend reallocating 15% of the social media ad budget to expand our top-performing paid search campaigns.")

This commentary turns a set of metrics into a strategic document that can guide decision-making for the coming quarter.

Final Thoughts

Building a quarterly report no longer requires days of tedious data wrangling. By leveraging Looker’s conversational AI, you can shift your focus from simply gathering data to truly analyzing it, allowing you to build more insightful reports in a fraction of the time. The key is to start with clear objectives, ask simple questions, and use follow-up prompts to drill deeper into the trends that matter most.

At its core, this shift toward conversational analytics is about empowering everyone in an organization to make data-driven decisions. While Looker is a powerful tool for companies with dedicated data teams, we believe getting answers from your data should be even simpler. We created Graphed to remove the technical hurdles entirely. You can connect sources like Shopify, Google Analytics, and Salesforce in seconds, then ask a question like, "create a dashboard showing my marketing funnel performance for last quarter," and get a live, interactive dashboard built for you automatically. It lets your entire team have a conversation with your data, without needing to learn LookML along the way.