Bring these inputs
Comparable GA4, store and advertising exports with metric definitions, currency and timezone.
Use approved, minimized data. Replace personal details with anonymous IDs.
Work through the lesson
- Choose the question first: for example, why did mobile purchase conversion fall? Define sessions, users, orders and revenue before combining exports.
- Check missing dates, duplicate orders, tracking changes, consent effects, refunds and timezones. Do not sum attributed revenue across ad platforms.
- Ask AI to show formulas and compare channel, device, landing page and new-versus-returning cohorts where available.
- List possible explanations and evidence that would distinguish them. A traffic shift is not proof that a design change caused the result.
- Recalculate a sample manually. End the report with one next investigation, one owner and a date.
Try this prompt
Replace the bracketed fields with your own evidence.
Analyze [exports] for [question]. First check definitions, missing data, date alignment and duplicate counting. Show calculations and denominators. Separate observed changes from causal hypotheses. Return three findings, confidence limits and one next test. Never invent missing rows.
Worked example
Illustrative data: 80 orders / 4,000 sessions = 2% session conversion. A later 60 / 4,000 = 1.5%, a 0.5 percentage-point fall, not a 0.5% relative fall. Check traffic mix before explaining it.
Before you use the result
- Denominators and dates match.
- A sample of calculations has been reproduced.
- The report labels hypotheses.
Complete the exercise
Create the deliverable described at the top of this lesson. Save the input evidence, your edited output, unresolved questions and the name of the reviewer in your workbook.