A reactivation batch is ready to send, but the copy is generic because nobody pulled what each customer last bought or when they last heard from the store. In this case, the immediate task is to draft emails to reactivate suitable inactive customers. The workflow should produce a winback plan with drafts grounded in the merchant's own records.
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.
Act as a Shopify operations specialist.
Help me draft emails to reactivate suitable inactive customers.
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: [the inactive list with each customer's last purchased product and date, the message history and last contact date, the permitted offer limits, and the consent and contact rules]. Write each draft around the product or category recorded for that customer, keep the offer inside the permitted limits, stay inside the stated contact rules, and make no claim the records do not support, so nothing is said about browsing, preferences or reasons for the silence that the order and message history cannot show.
Return sample reactivation email drafts inside a winback plan 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.Split the work into input, judgment, and deliverable phases. Verify each step's output before moving to the next.
Collect the inactive list with each customer's last purchased product or category and its date, the message history showing when each customer last heard from the store, the offer limits permitted, and the consent or contact rules that apply to the channel.
Write each draft around the product or category recorded for that customer, keep the offer inside the permitted limits, stay inside the stated contact rules, and make no claim the records do not support, so nothing is said about browsing, preferences or reasons for the silence that the order and message history cannot show.
Deliver the drafts inside the winback plan with the recipient, referenced product, offer and send position for each one, check every recipient against the supplied records to confirm the inactivity and last contact still hold, and flag any customer whose purchase context is missing so the generic version is a visible choice rather than a quiet default.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Only as a clearly separated suggestion and only where the merchant's offer rules permit it; the default is to reference the recorded purchase, because inventing a preference is a claim the records cannot support and cannot be defended if the customer challenges it.
They receive a neutral version that references the store rather than a product and they are listed as context-missing instead of being given a guessed product, so the weaker copy is traceable to a data gap rather than hidden inside the results.
It decides whether the customer is due another message under the merchant's cadence and keeps the copy from opening as though the store had never been in touch; a customer contacted recently is held back however strong the draft is.
Start with scenarios under the same topic, then expand into cross-topic matches suggested by similarity.
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.