Visits keep coming from directories, blogs and partner sites, and the merchant suspects some domains send traffic that never shops. In this case, the immediate task is to analyze referral traffic and its purchase behavior. The workflow should produce a channel traffic analysis with measurement caveats, judging each domain by its landing pages and orders.
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 referral traffic and its purchase behavior.
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 referral sessions grouped by referring domain, the landing pages each domain reaches, the engagement and orders attributed to it, the merchant's partnership and affiliate records, and the domains already known to link to the store]. Judge each domain on whether its visitors browse and order or leave at once, classify it as a known partner, an unrecognised domain or an unresolvable label from the partnership records, and keep the whole channel separate from direct traffic so untagged campaigns do not drift between the two.
Return a channel traffic analysis with measurement caveats, listing domains whose labels could not be resolved 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.
Gather the referral sessions grouped by referring domain, the landing pages each domain reaches, the engagement and orders attributed to it, the merchant's partnership and affiliate records, and the domains already known to link to the store.
Judge each domain on whether its visitors browse and order or leave at once, classify it as a known partner, an unrecognised domain or an unresolvable label from the partnership records, and keep the whole channel separate from direct traffic so untagged campaigns do not drift between the two.
Deliver a channel traffic analysis with measurement caveats listing the domains whose labels could not be resolved, then confirm that the domain rows sum to the referral total for the window and that no domain is reported on volume alone without its order behaviour beside it.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Flag them rather than delete them, because they usually mark a payment or redirect step that breaks the session instead of a real referring site. The row keeps its volume and is noted as a self-referral, so the reconciliation still balances and whoever fixes the tagging can see how much traffic the break was moving.
Against the partnership and affiliate records first; if nothing names it, the domain keeps its own row with its landing pages and order behaviour instead of being folded into a partner bucket. Volume alone never promotes a domain to known partner, and the caveats list unresolved domains for the merchant to confirm.
Yes. Once a link carries campaign parameters the visit is reclassified to that campaign, so a domain can appear to lose traffic that was merely relabelled. The report names the tagging changes on record in the window and compares channel totals before and after, rather than reading the change as a drop in referrals.
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.