The total budget and each campaign's cap are fixed, and the objective and results so far are recorded, but the split was never argued from them. In this case, the immediate task is to improve ad budget allocation under stated constraints. The workflow should return a revised allocation with per-campaign reasoning, reconciled against the spend data.
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 improve ad budget allocation under stated constraints.
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 total budget, each campaign's cap and current setting, the stated objective with its representative metric, per-campaign results over the evaluation window, and the conversion lag and attribution setting those results carry]. Rank campaigns by how much of the objective metric they produced per unit of spend inside the window, treating any campaign below the minimum evidence bar as unranked, and propose shifts only within each campaign's cap and only where the receiving campaign has shown it can hold its result as spend rises.
Return the revised allocation with the reasoning per campaign, verified against the supplied spend data 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.
Assemble the total budget, each campaign's cap and current setting, the stated objective with the metric that represents it, the results per campaign over the merchant's evaluation window, and the conversion lag and attribution setting those results carry.
Rank campaigns by how much of the objective metric they produced per unit of spend inside the window, treating any campaign below the minimum evidence bar as unranked, and propose shifts only within each campaign's cap and only where the receiving campaign has shown it can hold its result as spend rises.
Deliver the revised allocation with the per-campaign amount, the change from current and the reason stated in the objective's metric, then verify that the sum of allocations equals the total budget, that no campaign exceeds its cap and that every shifted campaign clears the evidence bar.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
It is left unranked rather than placed at the bottom, because thin results produce unstable ratios in both directions; the campaign keeps its current budget until it clears the merchant's minimum evidence bar inside the window.
Only up to the receiving campaign's cap, and usually in steps, since a campaign that performs at one spend level has not demonstrated the same efficiency at a much larger one.
The reconciliation at the end, where the sum of proposed allocations is checked against the stated total and each campaign against its own cap; a plan that looks right only per campaign is the common way totals drift.
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.