The merchant is deciding where to spend next, but channel reports were pulled under different attribution rules. In this case, the immediate task is to compare conversion rates across traffic channels. The workflow should produce a conversion diagnosis and experiment backlog, ranking only channels whose attribution the merchant's records confirm.
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 conversion rates across traffic channels.
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: [sessions and orders with the channel recorded for each, the attribution rule and lookback period used by each source, the channel list to rank, the currency and order status filter, the spend recorded per channel, and the session volume per channel]. Recompute every channel's rate under one attribution rule and one window, counting an order once to the channel credited under that rule, then mark as unconfirmed any channel whose attribution the records cannot reproduce and as low-volume any channel below the merchant's stated minimum session count, reporting both with raw counts instead of a rank.
Return a conversion diagnosis and experiment backlog, flagging any channel whose attribution the records cannot confirm 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 for the comparison window the sessions and orders with the channel recorded for each, the attribution rule and lookback period each reporting source applies, the channel list the merchant wants ranked, the currency and order status filter, the spend recorded per channel, and the volume each channel carries.
Recompute every channel's rate under one attribution rule and one window, counting an order once to the channel credited under that rule, then mark as unconfirmed any channel whose attribution the records cannot reproduce and as low-volume any channel below the merchant's stated minimum session count, reporting both with raw counts instead of a rank.
Deliver a conversion diagnosis and an experiment backlog ranking only the confirmed channels with their sessions, orders, rate, spend and the rule applied, then reconcile the sum of attributed orders with the order export for the window and note each channel whose credited orders were reassigned by the change of rule.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Changing the attribution rule moves orders between channels without changing a single order in the store, so the ranking is rebuilt from the raw records under the one rule the merchant chooses. The rule, its lookback period and the window are written beside the ranking, because a channel that wins under one rule can lose under another.
A channel that rarely closes but often appears earlier in the path is reported with the sessions and orders it touched under the chosen rule rather than being dropped. Reading only the closing rate undervalues the channels that start journeys; where the merchant also runs last-touch reporting, both views are shown so the budget decision sees the difference.
Channels whose attribution cannot be reproduced from the records, and channels below the merchant's stated minimum session count, are reported separately with their raw sessions and orders. Ranking them invites decisions on figures that move with a single order; they rejoin the ranking once the volume or the attribution check is satisfied.
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.