Events and transactions in the GA4 property do not line up with what the store records, so the numbers shown cannot be trusted as they stand. In this case, the immediate task is to plan a reliable connection between GA4 and store data. The workflow should produce a unified reporting model and discrepancy log covering untracked sales and duplicated sessions.
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 plan a reliable connection between GA4 and store data.
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: [property timezone and currency, purchase-event and order exports, transaction-to-order identifier mapping, consent and tagging configuration, and timestamped raw events with user/session identifiers and collection-source evidence when available].
Compare mapped transactions and amounts under matched currency and time definitions after the configured processing allowance, distinguish missing or late records from repeated purchase events, and treat aggregate session differences as unverified until raw events and tagging evidence support a specific diagnosis.
Deliver a discrepancy log with matched identifiers, amounts, evidence, unresolved causes and a verification action for each finding, leave session duplication unverified when session-level evidence is unavailable, and rerun the same checks after any proposed correction 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 property timezone and currency settings, purchase-event exports, the order export and an explicit mapping between transaction identifiers and order identifiers, consent configuration and tagging changes, requesting timestamped raw events with user and session identifiers and collection-source evidence for session-level investigation.
Compare mapped transactions and amounts under matched currency and time definitions after the configured processing allowance, distinguish missing or late records from repeated purchase events, and treat aggregate session differences as unverified until raw events and tagging evidence support a specific diagnosis.
Deliver a discrepancy log with matched identifiers, amounts, evidence, unresolved causes and a verification action for each finding, leave session duplication unverified when session-level evidence is unavailable, and rerun the same checks after any proposed correction.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Missing transactions can follow tagging changes, consent settings or delayed processing, but an order mismatch alone does not establish the cause. Check the event payload and configuration history before classifying a discrepancy as a verified implementation defect.
Use an explicit mapping because the event transaction identifier is not necessarily the displayed order number. Compare mapped identifiers and amounts under consistent currency, timezone and processing rules; record unmatched identifiers separately rather than assuming the systems share identical keys.
Aggregate differences do not establish duplicated sessions. Inspect timestamped raw events with user and session identifiers and collection-source evidence, checking for repeated collection rather than assuming every repeated event creates a new session; without this evidence report session differences as unverified.
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.