Budgets exist at account, campaign and day level, but pacing is checked by hand, so overspend is found after the fact. In this case, the immediate task is to detect ad spending beyond defined limits. The workflow should return alert rules that compare pacing to each limit on a fixed interval and give the action each breach triggers.
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 detect ad spending beyond defined limits.
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 stated account, campaign and day-level budget limits, spend-to-date per period from the platform exports, the reporting currency, the supported refresh cadence, and every mid-period budget edit with its timestamp]. Compute pacing as spend-to-date divided by the elapsed share of the period and compare it against each limit, raising an alert only when a breach persists across the merchant's stated number of consecutive checks, and marking any period whose export is stale or whose limit was edited mid-way as unverified rather than overspent.
Return the overspend alert rules with the action each one triggers, confirmed against the stated budgets 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 the stated budget limits at account, campaign and day level, the current spend-to-date for each period from the supplied platform exports, the reporting currency, the refresh cadence the data source supports, and every budget edit made inside the window together with its timestamp.
Compute pacing as spend-to-date divided by the elapsed share of the period and compare it against each limit, raising an alert only when a breach persists across the merchant's stated number of consecutive checks, and marking any period whose export is stale or whose limit was edited mid-way as unverified rather than overspent.
Deliver the overspend alert rules with the action each breach triggers and the recipient role that owns it, then verify them by replaying the rules over the supplied spend history and confirming that every alert raised corresponds to a period where spend-to-date exceeded the limit on record.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Pacing is spend-to-date divided by the elapsed share of the period, so a limit can be breached long before the window closes. A period whose export is stale or whose limit was edited mid-way is reported as unverified instead of overspent, because neither figure can be trusted for that comparison.
Only when it clears and then returns; while a condition stays open the rule updates one alert rather than opening new ones. Without that rule the channel fills with identical messages and nobody can see how many limits are actually over at that moment.
Each edit is recorded with its timestamp and spend is compared against the limit in force at each check. Measuring a whole day against the newest limit either excuses real overspend or invents it where the earlier limit was never exceeded.
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.