Every source label in the reports is spelled differently, so the merchant can only rank channels on session counts. In this case, the immediate task is to report traffic volume and quality by source. The workflow should produce a channel traffic analysis with measurement caveats, ranking sources on quality beside volume and isolating unattributed traffic.
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 report traffic volume and quality by source.
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, orders, revenue and device split recorded for every source label inside one fixed date range, one attribution setting and one timezone, the merchant's channel naming map, and the labels already recorded as unattributed]. Apply the naming map so every spelling that denotes the same source is merged under one channel, keep unresolvable labels in their own unattributed category instead of distributing them, then rank the channels on volume beside order behaviour rather than on volume alone.
Return a channel traffic analysis with measurement caveats, keeping unattributed traffic in its own category 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.
Assemble the sessions, orders, revenue and device split recorded for every source label inside one fixed date range, one attribution setting and one timezone, together with the merchant's channel naming map and the labels already recorded as unattributed.
Apply the naming map so every spelling that denotes the same source is merged under one channel, keep unresolvable labels in their own unattributed category instead of distributing them, then rank the channels on volume beside order behaviour rather than on volume alone.
Deliver a channel traffic analysis with measurement caveats stating the date range, attribution setting and timezone used, then confirm that the merged session totals still sum to the store-wide session count for the window and list every label the naming map could not resolve.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Through the merchant's channel naming map, applied once and recorded, with the raw label kept in an appendix so any merge can be reversed and checked. Merging on resemblance alone would combine sources that behave differently, so a label with no mapping entry stays unattributed rather than being guessed into a channel.
Usually because of timezone, attribution window or bot filtering applied on one side and not the other. The report names the settings used on both sides and shows the difference as a reconciliation line, so a gap becomes a stated caveat rather than a silent discrepancy that undermines every figure beneath it.
No. It keeps its row with its volume and an empty order count, because removing it would present a channel mix that never existed. Such sources are simply ranked below those that convert, and the caveats note where their volume is too small to judge quality in either direction.
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.