Scores are quoted as though every period carried equal weight, while only a trickle of responses follows some order types. In this case, the immediate task is to analyze customer satisfaction feedback with response context. The workflow should produce a service performance report and improvement priorities read alongside the tickets behind each score.
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 analyze customer satisfaction feedback with response context.
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: [satisfaction responses with scores, comments and timestamps, the ticket or order identifier behind each survey, and survey invitation counts per period]. Read each score against the ticket it came from, separating scores that followed a fast resolution from those that followed a slow or reopened one, and report every period with its response count and response rate so a thin period is not read as a shift in sentiment.
Return a service performance report and improvement priorities 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 every satisfaction response with its submitted timestamp, score and comment, the ticket or order identifier that triggered the survey, and the number of invitations sent in the same period so the response rate is computed against invitations rather than against responses.
Read each score against the ticket it came from, separating scores that followed a fast resolution from those that followed a slow or reopened one, and report every period with its response count and response rate so a thin period is not read as a shift in sentiment.
Deliver the service performance report with a satisfaction section showing score spread, response volume and the topics behind the lowest scores, then verify that each linked response matches a real ticket and list the ones that cannot be tied to one.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Invitations sent in that period, not responses received, because a period with few replies can otherwise look like a shift in sentiment; where invitation counts are missing, the period reports raw response counts and states that the rate cannot be computed.
Only to locate the topic behind a score, never to re-score it, since a comment often describes a different moment than the survey question; comments that contradict the linked ticket's subject are flagged so the score is not attributed to the wrong cause.
Yes, a survey sent after support contact asks about the handling while one sent after purchase asks about the product, and pooling them mixes two different questions; each type carries its own volume, and a period with too few of either is marked indicative.
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.