Posts go out across several platforms, each sending its own traffic, and the merchant must decide where the next campaign goes. In this case, the immediate task is to compare traffic from social media sources. The workflow should produce a channel traffic analysis with measurement caveats, tying each platform's volume and orders to the posts published then.
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 compare traffic from social media sources.
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 sessions, engagement and orders recorded per social platform, the campaign tags and link parameters used, the publishing schedule with the date each post went out, and the paid and organic activity run per platform in the window].
Compare platforms on volume, engagement and order behaviour, attribute a movement to a post only where the publish date and the timing of the change line up in the merchant's records, and keep paid visits separate from untagged organic ones throughout.
Return a channel traffic analysis with measurement caveats, separating paid visits from untagged organic ones 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 sessions, engagement and orders recorded per social platform, the campaign tags and link parameters used, the publishing schedule with the date each post went out, and the paid and organic activity the merchant ran per platform in the window.
Compare platforms on volume, engagement and order behaviour, attribute a movement to a post only where the publish date and the timing of the change line up in the merchant's records, and keep paid visits separate from untagged organic ones throughout.
Deliver a channel traffic analysis with measurement caveats carrying one row per platform with its volume, engagement and orders, then confirm that the tagged sessions per platform reconcile with that platform's total and note the platforms where untagged visits make up most of the traffic.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Usually because the visits are untagged, paid, or shared onward where no link parameter survives, so the report records the platform total and leaves the gap unexplained. Showing the tagged and untagged rows side by side tells the merchant how much of that platform's traffic can be attributed at all.
Only where the merchant records which link or parameter each post used, otherwise a post-level split would be invented. Where that record exists the movement is matched to the publish date, and where it does not the platform is reported as a whole with the posting schedule attached as context.
By timing and tagging together: a paid push carries parameters and spend on the same dates, while a post that spreads carries neither. Where the timing matches an untagged post, the movement is marked as suspected rather than confirmed, and the report names the evidence that would settle 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.