Ciwi
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant

Analyze performance across multiple marketing channels

Each marketing platform reports in its own naming, currency and time zone, so the numbers cannot be dropped into one table as they are. In this case, the immediate task is to analyze performance across multiple marketing channels. The workflow should produce a unified reporting model and discrepancy log, with totals reconciled against every supplied export.

Topic
Analytics Integrations and Unified Reporting
Target keyword
shopify cross channel analytics
Copyable AI prompt

A prompt you can drop directly into Spark

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.

ai-prompt.txt
Act as a Shopify operations specialist.
Help me analyze performance across multiple marketing 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: [each channel export with its campaign naming convention, currency, timezone and order-linking identifier, and store-side order records covering the same period for every channel]. Align comparable fields across channels by mapping campaign names to one convention and converting currency and timezone to the store's basis, while preserving each platform's own definition of a conversion in the comparison and never summing credited conversions that describe the same order.
Return a unified reporting model and discrepancy log 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.
Use in Spark
How to solve

A recommended resolution workflow

Split the work into input, judgment, and deliverable phases. Verify each step's output before moving to the next.

01

Step 1

Collect each channel's export with the campaign naming convention it uses, the currency and timezone it reports in, the identifier that links its rows to orders, and the store-side order records covering the same period for every channel.

02

Step 2

Align comparable fields across channels by mapping campaign names to one convention and converting currency and timezone to the store's basis, while preserving each platform's own definition of a conversion in the comparison and never summing credited conversions that describe the same order.

03

Step 3

Deliver the unified reporting model and discrepancy log reconciling totals against every supplied export, then verify that each channel's aligned total equals its original export, that overlapping claims are shown as overlap rather than added demand and that unmatched rows are logged with a stated reason.

FAQ

Common questions when running this scenario

Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.

Why do channel totals exceed store revenue?

Each platform credits the conversions it can observe, so the same order is claimed several times. Compare each channel against recorded orders and present the overlap explicitly, rather than adding claimed conversions into a total no order export can support.

How are unmatched rows handled?

Every row that cannot be tied to an order stays in the discrepancy log with its identifier and a stated reason, and is excluded from reconciled totals. Silently dropping such rows would bias the comparison toward whichever channel happened to report cleanly.

Which comparison period should be used?

One the merchant can supply completely for every channel, with the same timezone and currency treatment applied throughout. A period that is partial for one channel distorts every cross-channel ratio, so incomplete periods are marked rather than mixed in.

Related scenarios

Continue with adjacent or same-topic scenarios

Start with scenarios under the same topic, then expand into cross-topic matches suggested by similarity.

Next step

Want these AI scenarios embedded directly into daily operations?

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.

Open Spark product pageBack to Spark scenario library