The Scenario
The retention analyst who built the last RFM model left three months ago. Their methodology lived in their head and a half-finished spreadsheet that's now orphaned in a shared drive. You've been tasked with rebuilding it — and you need a fresh extract of all 1,500 Remarkety customers, including email, total revenue, last purchase date, and order count, to do it.
Remarkety doesn't have an export button that produces exactly what you need. The built-in export gives you everything, in a format that requires another round of cleanup before it's useful. You download it, open it in Sheets, delete fifteen columns you don't need, rename four columns to match the naming convention the analysis model expects, and realize the date format is MM/DD/YYYY but your formula expects YYYY-MM-DD.
That's the easy part. The hard part is that you need to refresh this every month.
The bad version:
- Download the full Remarkety customer export. Delete the columns you don't need. Rename the columns that matter. Reformat the date column. Paste it into the analysis sheet.
- Discover that the export cut off at 1,000 rows because of a pagination limit nobody warned you about. Run the export again with different date filters to get the rest. Merge the two files.
- Do this again in thirty days, and again in sixty, for as long as this model is in use.
You're supposed to be building the analysis, not fetching the data for it.
The Easy Way: One Prompt in SheetXAI
SheetXAI is an AI agent inside your Google Sheet. It reads the sheet, connects to Remarkety, and writes the data you actually need — formatted the way you need it — without the export-cleanup roundtrip.
Fetch all Remarkety customers and write email, total revenue, last purchase date, and number of orders into columns A through D. Use YYYY-MM-DD format for dates. Sort by total revenue descending.
What You Get
- All customers pulled from Remarkety across all pages — no pagination cutoffs.
- Email, total revenue, last purchase date, and order count written into columns A through D with the column headers on row 1.
- Dates formatted as YYYY-MM-DD so downstream formulas don't need to convert them.
- Sorted by total revenue descending so the highest-value customers are visible immediately.
What If the Data Is Not Quite Ready
You need first and last name included for personalization matching later
Fetch all Remarkety customers and write email, first name, last name, total spend, last purchase date, and number of orders into columns A through F. Sort by last purchase date ascending so the most lapsed customers appear first.
You only want customers who haven't purchased in the last 90 days
Pull all Remarkety customers whose last purchase date is more than 90 days before today. Write email, total revenue, last purchase date, and order count into columns A through D. Sort by last purchase date ascending.
You need to join the Remarkety data with a loyalty tier column already in the sheet
The sheet has customer emails in column A and loyalty tier in column B from our internal system. Fetch the matching Remarkety customers for each email in column A and write their total spend and last purchase date into columns C and D.
Full cleanup + segment tagging + export in one shot
Pull all Remarkety customers. Remove any rows where email is blank or total revenue is zero. Add a column E that labels each customer as "Champion" if total revenue is over 500 and last purchase was within 180 days, "At Risk" if revenue is over 500 but last purchase was over 180 days ago, and "Lapsed" otherwise. Write all results into columns A through E with headers.
One prompt does the extract, the filter, and the segmentation labeling — the analysis sheet is ready before you've finished your coffee.
Try It
Get the 7-day free trial of SheetXAI and open a blank Google Sheet, then ask it to pull your Remarkety customer list into whatever shape your RFM model needs. Also see: Bulk Import Contacts Into Remarkety and the Remarkety overview.