Follow-up runs in manual batches, so some customers hear twice in one week while others are never contacted at all. In this case, the immediate task is to build a targeted customer winback workflow. The workflow should produce a winback automation with measurement points set from the merchant's triggers, channels and ownership rules.
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 build a targeted customer winback workflow.
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 at-risk definition, available channels with sending limits, the message frequency cap and cadence, the owner for each step, and the suppression and consent rules]. Map each trigger to its entry conditions, the message it sends and the exits that stop it, so a customer leaves the flow on a completed order, an opt-out, a suppression match or the end of the stated plan, and resolve conflicting triggers by the precedence the merchant states instead of letting one customer run through two flows at once.
Return a winback workflow with its measurement points 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 at-risk definition that feeds the flow, the channels available with their sending limits, the message frequency cap and contact cadence in force, the owner responsible for each step, and the suppression and consent rules that gate any send.
Map each trigger to its entry conditions, the message it sends and the exits that stop it, so a customer leaves the flow on a completed order, an opt-out, a suppression match or the end of the stated plan, and resolve conflicting triggers by the precedence the merchant states instead of letting one customer run through two flows at once.
Deliver the workflow with its measurement points at entry, send, order and exit, dry-run it against the supplied customer records to confirm the trigger fires for the intended segment and stays silent for everyone else, and note which conditions could not be tested and what must be watched after launch.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
The precedence order the merchant states decides, with the higher-priority flow taking the customer and the other suppressed, because running both sends overlapping messages and leaves the measurement unable to attribute any order to a single flow.
A completed order, an opt-out or suppression match, and the end of the stated plan, each recorded as a separate exit reason so the flow can report how many customers left by ordering rather than by exhausting the sequence.
By running the trigger against the supplied records and comparing the customers it selects with the at-risk list, then confirming every excluded customer has a recorded reason, so a silent misconfiguration shows up as a mismatch rather than as a missing send.
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.