01
Step 1
Collect customer order histories with dates, each customer's prior purchase gaps where a repeat exists, the stated observation window, the merchant's recorded category cycle for fallback, and the refund treatment.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Estimate which customers may be ready to buy again
Retention work is planned from one list where long-standing customers and people who bought last week sit together. In this case, the immediate task is to estimate which customers may be ready to buy again. The workflow should produce a repeat-purchase cohort analysis, using the merchant's order histories, purchase dates and stated observation window.
Topic
Repeat Purchase and Retention Analytics
Target keyword
shopify repeat purchase prediction
Copyable AI prompt
A prompt you can drop directly into Spark
First replace every [bracketed] placeholder with real store scope and constraints, then add any actual records or data you have, and paste it into your preferred AI assistant or Spark agent. Spark will follow this page's workflow to produce structured output and verification steps.
ai-prompt.txt
Act as a Shopify operations specialist.
Help me estimate which customers may be ready to buy again.
My store context is [describe the business, products and target audience].
My scope is [specify the affected products, pages, customers or reporting period]. Use these inputs: [customer order histories with dates, prior purchase gaps per customer, the stated observation window, the recorded category cycle for fallback, and the refund treatment]. Score each customer's readiness as elapsed time since the latest order measured against their own prior gap or the fallback cycle, label which basis was applied per customer, and hold back customers whose time since first purchase is shorter than the observation window.
Return a repeat-purchase cohort analysis for the specified task.
Show the relevant evidence or before-and-after examples and explain how I can verify the result.
If essential data is missing, ask for it and mark unsupported conclusions as unknown.
Do not invent metrics, product claims or customer facts.
For any publication, message, account or store change, use only connected tools within my explicitly authorized scope and report success only after verification; otherwise provide the draft or proposed steps.How to solve
A recommended resolution workflow
Split the work into input, judgment, and deliverable phases. Verify each step's output before moving to the next.
02
Step 2
Score each customer's readiness as elapsed time since the latest order measured against their own prior gap or the fallback cycle, label which basis was applied per customer, and hold back customers whose time since first purchase is shorter than the observation window.
03
Step 3
Deliver the scored cohort analysis clearly labelled as an estimate rather than a measured rate, then verify the readiness ordering against the purchase dates in the supplied records.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
What distinguishes a readiness score from a measured rate?
A readiness score estimates how soon a customer's next order may come, based on elapsed time against a gap basis; a measured rate reports what a cohort already did. The output is labelled as an estimate wherever scores appear, so no one reads it as observed behaviour. Scores support prioritization, not reporting.
When is the fallback cycle used instead of a customer's own gaps?
Only when the customer has no prior repeat, so there is no personal gap to compare against. The merchant's recorded cycle for that product or category stands in, and the basis column marks which value was applied. Where neither exists, the customer is held back rather than scored on an invented basis.
Why are some customers held back from scoring?
Customers whose time since first purchase is shorter than the stated observation window have not had a fair chance to reorder, so low readiness would be an artifact of timing. They are held back and listed, not scored. Once their window matures they enter the next run on the same terms as everyone else.
Related scenarios
Continue with adjacent or same-topic scenarios
Start with scenarios under the same topic, then expand into cross-topic matches suggested by similarity.
Next step
Want these AI scenarios embedded directly into daily operations?
Ciwi Spark builds Shopify-native AI tools and agents around the workflows merchants actually run: research, ads, translation, and customer support. Stop rewriting the same prompts by hand.