Bids are being adjusted with no documented limits, though the target outcome, margin context, spend caps and conversion delay sit in the merchant's own data. In this case, the immediate task is to design bounded rules for automated bid changes. The workflow should return rules with a maximum change per cycle, an evaluation window and a rollback condition.
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 design bounded rules for automated bid changes.
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: [current bids per campaign, the stated target outcome, the margin context for advertised products, the spend caps in force, the conversion delay in the supplied data, and each campaign's delivery status]. Set one rule per campaign with a maximum bid change per cycle, an evaluation window at least as long as the conversion delay, and a rollback condition that restores the previous bid when the target outcome moves outside the merchant's stated tolerance, keeping any campaign with thin conversion volume out of automated control.
Return the bidding rules with their limits and checks, confirmed against the merchant's stated constraints 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 current bids per campaign or ad group, the target outcome the merchant states, the margin context for the products being advertised, the spend caps in force, the conversion delay present in the supplied data and the delivery status of each campaign.
Set one rule per campaign with a maximum bid change per cycle, an evaluation window at least as long as the conversion delay, and a rollback condition that restores the previous bid when the target outcome moves outside the merchant's stated tolerance, keeping any campaign with thin conversion volume out of automated control.
Deliver the bidding rules with their limits, evaluation windows and rollback triggers plus the previous bid values needed to restore them, then replay the rules against the supplied history and confirm that no simulated cycle breaches the maximum change or the spend cap.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
A bid change judged before its conversions have landed reads as a failure whatever its real effect, so the window must outlast the delay in the merchant's data; shorter windows mainly produce rollbacks that undo correct decisions.
Whenever the target outcome breaches the stated tolerance inside the evaluation window, and the rule must carry the previous bid value, because a rollback without that value becomes a fresh guess rather than a reversal.
No, campaigns with thin conversion volume or a recent structural change stay manual, since their signals are too sparse to support a rule and automation would move bids on noise.
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.