Marketing plans are being written from impressions rather than from the campaign records the store already holds. In this case, the immediate task is to assist with grounded marketing planning and execution. The workflow should produce a task plan and action log citing each draft prepared and the export or account data behind it.
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 assist with grounded marketing planning and execution.
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: [campaign objectives, audience segments, connected ad account identifiers, channel access, per-campaign spend revenue and order exports for the reporting window with their currency timezone and attribution setting, and the merchant's budget and approval limits]. Treat a pattern as observed only when it holds across the whole window in the export rather than in a partial period, mark any recommendation whose supporting figure is missing or drawn from a different attribution setting as an assumption, and keep every action outside the merchant's permitted budget change as a draft proposal rather than an executed change.
Return the task plan and action log citing each draft prepared and the evidence behind it 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 one merchant-defined reporting window, the campaign objectives, audience segments and channel access, the connected ad account identifiers, and the exported spend, revenue and order figures per campaign, recording the currency, timezone and attribution setting each export was generated under along with the budget and approval limits the merchant permits the assistant to act within.
Treat a pattern as observed only when it holds across the whole window in the export rather than in a partial period, mark any recommendation whose supporting figure is missing or drawn from a different attribution setting as an assumption, and keep every action outside the merchant's permitted budget change as a draft proposal rather than an executed change.
Deliver the task plan and action log citing, for each draft prepared, the campaign record and export row behind it, reconcile the total of proposed spend changes with the merchant's stated budget before anything is published, and list each recommendation blocked by missing audience data with the record needed to unblock it.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
A pattern counts as observed only when the same movement appears across the full reporting window in the supplied export, so a single strong day stays a hypothesis; assumptions are labelled as such in the plan and never presented as a result the merchant can act on.
Only within the budget and approval limits the merchant states in advance, because publishing is irreversible inside the ad account; anything larger stays a draft with the supporting figures so a person can approve it first.
Both figures are recorded, the currency, timezone and attribution setting of each export are compared, and the campaign is reported under the setting the merchant nominated; where the gap survives that check the campaign is marked unresolved rather than averaged.
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.