Ad-tagged sessions keep arriving, yet the merchant cannot separate campaigns that produce orders from campaigns that only add visits. In this case, the immediate task is to analyze paid traffic quality and conversion. The workflow should produce a channel traffic analysis with measurement caveats, matching each campaign's sessions and orders to its spend.
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 paid traffic quality and conversion.
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 campaign-tagged sessions, the tagging parameters each campaign uses, the spend and date ranges recorded for each campaign, the store's order and revenue records, the conversion goal the merchant names, and any spend with no tag attached]. Match each campaign's sessions, orders and recorded spend inside one common date range, separate the campaigns whose orders the store records from those that only added visits, and flag every campaign whose tags are missing, whose parameters disagree with the naming map, or whose spend dates do not cover the range.
Return a channel traffic analysis with measurement caveats, flagging campaigns whose tags or dates are inconsistent 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 campaign-tagged sessions, the tagging parameters each campaign uses, the spend and date ranges recorded for each campaign, the store's order and revenue records, the conversion goal the merchant names and any spend with no tag attached.
Match each campaign's sessions, orders and recorded spend inside one common date range, separate the campaigns whose orders the store records from those that only added visits, and flag every campaign whose tags are missing, whose parameters disagree with the naming map, or whose spend dates do not cover the range.
Deliver a channel traffic analysis with measurement caveats carrying one row per campaign with its sessions, orders and spend, then confirm that the tagged sessions counted equal the sum of the campaign rows and report untagged spend as its own line instead of folding it into a campaign.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
The platform and the store attribute differently, so mixing them puts two definitions in one row and neither figure can be checked. The analysis uses the store's own session and order records consistently on both sides and names the attribution setting, keeping the platform figures as a directional cross-check in the caveats.
Flag the row and leave the comparison uncomputed, because a ratio built across mismatched ranges describes neither period. The report sets the two ranges side by side and asks for the corrected spend dates, rather than stretching one side so the row looks complete.
It is reported as producing no orders inside the window rather than as a failure, since the merchant's stated goal and the length of the buying cycle decide its value. The row keeps its sessions and spend so the decision is made on record, and the caveats note where the window is too short to judge it.
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.