> ## Documentation Index > Fetch the complete documentation index at: https://docs.omni.co/llms.txt > Use this file to discover all available pages before exploring further. # Using AI to build a cohort analysis with month offset > Use the Omni Agent to create a cohort analysis that tracks user behavior over time using monthly offsets. export const categoryIcons = { 'administration': 'lock', 'api': 'terminal', 'connections': 'database', 'dashboards': 'table-columns', 'embed': 'code', 'errors': 'exclamation', 'modeling': 'wrench', 'patterns': 'plus', 'schedules & alerts': 'envelope', 'visualizations': 'chart-column', 'workbooks': 'book' }; export const GuideSidebar = ({category, relatedLinks, updatedDate}) => { const [progress, setProgress] = React.useState(0); React.useEffect(() => { const sidebar = document.querySelector('.guide-sidebar'); if (!sidebar) return; let container = sidebar.parentElement; while (container && !container.querySelector('.guide-header')) { container = container.parentElement; } if (container && !container.classList.contains('guide-page-layout')) { container.classList.add('guide-page-layout'); } }, []); React.useEffect(() => { const handleScroll = () => { const scrollTop = window.scrollY; const docHeight = document.documentElement.scrollHeight - window.innerHeight; const scrollPercent = docHeight > 0 ? scrollTop / docHeight * 100 : 0; setProgress(Math.min(100, Math.max(0, scrollPercent))); }; window.addEventListener('scroll', handleScroll, { passive: true }); handleScroll(); return () => window.removeEventListener('scroll', handleScroll); }, []); const icon = category ? categoryIcons[category.toLowerCase()] || 'book' : 'book'; return ; }; export const GuideTitle = ({title}) => { return

{title}

; }; ## Requirements To follow the steps in this guide, you'll need: * **Permissions in Omni** that allow you to use the [Omni Agent](/ai/queries). * **A dataset that includes at least two date fields** — a fixed user attribute date (e.g., account creation date) and an activity or event date. These should be accessible from a single Omni topic. To start, you need to establish the fixed date for your users and the activity date you are measuring. 1. Select the user creation date (for example, `Created At`). This serves as your fixed dimension for the X-axis. 2. Select the date field representing user activity or transactions: Cohort Date

Instead of writing complex SQL, use the Omni Agent to calculate the time difference between your two dates. 1. Click **AI calcs** ( icon) in the workbook toolbar. 2. In the Omni Agent prompt, enter: `"Calculate the difference in months between column a and b."` Create AI Field

3. After the calculation generates, hover over the column and click the icon. 4. Click **Save to workbook** to make the field available for your analysis. Promote to Workbook

5. Rename the new field to something clear, such as `Months since Created`, by clicking the icon next to the field name in the field picker and opening the Edit Field view. This can also be done via double clicking on the header of the new column. Rename Field

Once your offset is calculated, you can arrange your data to see the "cohort triangle" pattern. 1. Create a pivot on the new `Months since Created` field. Pivot

2. Select a measure to track, such as a **Count** of users or **Count Distinct** of specific behaviors. 3. The results will automatically format into a cohort-style visualization: Results

Enhance your table to visually highlight performance trends across different cohorts. 1. Navigate to the **Visualizations** tab and click the **Table** visualization. 2. Click the **Conditional Formatting** tab in the **Chart Options** panel. 3. Choose **Color Scale**. 4. Select your primary measure to apply the color scale:

Use a sequential color scale (e.g., light to dark blue) to make it easier to see where retention or activity drops off in later months. ## Video walkthrough