The Scenario
You are a retention analyst. Every Thursday at 2 PM you present the weekly leadership review. The standing ask: show the January and February signup cohorts on the same retention curve and explain what changed.
The retention data is in Amplitude. The chart is in an Excel workbook that you update every week by hand — two CSV exports, paste into two separate columns in the Retention tab, manually align week numbers.
The slow version every Thursday:
- Open Amplitude, configure the January cohort retention chart, weekly intervals, export CSV
- Go back, configure the February cohort, export a second CSV
- Open the workbook, go to the Retention tab, paste January in column B, paste February in column C
- Manually realign so Week 1 is next to Week 1 in the same row
- Rebuild the chart if the row count changed
- You walk into the 2 PM with a chart that took 45 minutes to assemble.
The fast version is one prompt.
The Easy Way: One Prompt in SheetXAI
SheetXAI queries the Amplitude Retention API directly and writes both curves into the Retention tab in the right structure — no two-export, two-paste sequence.
Open the SheetXAI sidebar and type:
Fetch retention curves for my January 2025 and February 2025 signup cohorts from Amplitude. Use weekly intervals. Write week numbers into column A of the Retention tab, January retention percentages into column B, and February retention percentages into column C. Add a header row.
SheetXAI pulls both curves, aligns them by week number, and writes the table into the Retention tab. Your chart refreshes automatically because the column structure is identical to last week's.
What You Get
A clean three-column retention table in the Retention tab:
- Column A — week numbers (Week 0 through Week N)
- Column B — January 2025 cohort weekly retention percentages
- Column C — February 2025 cohort weekly retention percentages
- Row 1 — headers
Both curves are aligned by week number, not by calendar date. No manual alignment required.
The chart you built two months ago still works — the data shape is identical, only the numbers change.
What If the Data Is Not Quite Ready
Retention analysis rarely starts with two clean, perfectly comparable cohorts. SheetXAI handles the edge cases in the same prompt.
When you want 8-week and 12-week views side by side
Leadership asked for both the short and the full retention horizon this week.
Fetch 8-week and 12-week retention data for my February 2025 signup cohort from Amplitude. Write week numbers in column A of the Retention tab, 8-week retention in column B, 12-week retention in column C. Mark any week beyond Week 8 in column D as "outside 8-week window".
When you want to compare users who completed onboarding versus those who skipped
The product team is debating whether onboarding completion actually drives retention.
Pull 8-week retention data from Amplitude for users who completed onboarding versus users who skipped it. Write week numbers in column A of the Retention tab, 'Completed Onboarding' in column B, 'Skipped Onboarding' in column C. Add a fourth column D with the difference (B minus C) for each week.
When a product change mid-month means the cohorts are not cleanly comparable
The new onboarding flow launched January 18th. Users before and after had different experiences.
Fetch retention curves from Amplitude for users who signed up January 1–17 and users who signed up January 18–31 separately. Write both curves into the Retention tab with week numbers in column A, pre-launch in column B, post-launch in column C. Add a note in cell D1 explaining the January 18 cutoff.
When leadership wants the curves, the week-over-week delta, and a written takeaway all in one output
The Thursday review needs a chart and a one-paragraph summary to read from in the meeting.
Pull weekly retention for January and February 2025 signup cohorts from Amplitude. Write week numbers in column A of the Retention tab, January in column B, February in column C. Calculate the difference in column D and flag any week where it exceeds 5 percentage points with "NOTABLE" in column E. Write a two-sentence summary in cell G1 identifying the largest difference between cohorts and what it implies.
The pattern: instead of two exports, two pastes, and a separately drafted summary, you ask for all three in one prompt.
Try It
Get the 7-day free trial of SheetXAI and open any Excel workbook, then ask it to pull retention curves for any two Amplitude cohorts with whatever interval and date range the review requires. The Amplitude integration is included in every plan. For related workflows, see how to pull funnel conversion data for quarterly reviews or the Amplitude in Excel overview.