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

Design a unified dashboard across connected sources

Several sources feed the reporting view at different times, and nobody can tell which figures were last refreshed or how reliable they are. In this case, the immediate task is to design a unified dashboard across connected sources. The workflow should produce a unified reporting model and discrepancy log standing behind each composite figure shown.

Topic
Analytics Integrations and Unified Reporting
Target keyword
shopify unified analytics dashboard
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 design a unified dashboard across connected sources.
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 connected source with its supplied dimensions, refresh timing and last successful refresh, the reliability assigned to it, and the questions the dashboard must answer for its audience]. Group figures by source reliability and label each panel with its source and last refresh, blending two figures into one composite number only where their definitions, timezone and currency genuinely match and recording the rule used where they do not.
Return a unified reporting model and discrepancy log standing behind each composite figure shown 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 every connected source with the dimensions it supplies, the refresh timing and last successful refresh for each, the reliability the merchant assigns to it, and the questions the dashboard must answer for its stated audience.

02

Step 2

Group figures by source reliability and label each panel with its source and last refresh, blending two figures into one composite number only where their definitions, timezone and currency genuinely match and recording the rule used where they do not.

03

Step 3

Deliver the unified reporting model and discrepancy log standing behind each composite figure shown, then verify that every panel states its source and refresh time, that each composite figure names the sources folded into it and that no panel combines figures refreshed at different moments without a note.

FAQ

Common questions when running this scenario

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

Why label each panel with its refresh time?

Sources refresh on different schedules, so two panels read together may describe different moments. A visible timestamp lets a reader see whether a gap is a real change or simply a source that has not updated, and panels past their stated refresh expectation are flagged.

When should two figures be blended?

Only when their definitions, timezone and currency match and the merchant has accepted the combined measure. Where either differs, the figures stay side by side and the log records why a single number would mislead, so the reader sees the disagreement instead of a false consensus.

Who needs the discrepancy log?

Anyone who interprets the dashboard or acts on its figures, since it explains why two panels can each be right and still disagree. Hiding it turns a definitional difference into a quiet argument about whose number is correct.

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