Posts go live without a consistent check, so incomplete entries and unapproved drafts reach the blog. In this case, the immediate task is to automate blog publishing after required checks. The output should hold anything missing fields or approval and log every check with the resulting publication state.
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 automate blog publishing after required checks.
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: [post sources with their identifiers, the required-field list and completeness rule, approval records showing which drafts were cleared, the duplicate-check key such as handle or title, the destination blog and author, publisher access scope, and each item's last published state]. Run the checks in one fixed order before anything publishes, holding an item whose required fields are incomplete or whose approval is missing, marking as a suspected duplicate any item whose duplicate key matches an existing post, and recording for every item the check name, the result, the timestamp and the identifier of the run that produced it.
Return a content workflow and sample output batch logging every check, failure and resulting publication state 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 post sources with their identifiers, the required-field list together with the rule that decides whether a field is complete, the approval records showing which drafts were cleared, the key used to detect a duplicate such as the handle or title, the destination blog and author, the access the publisher runs under, and each item's last published state so a repeat run can be told from a first publication.
Run the checks in one fixed order before anything publishes, holding an item whose required fields are incomplete or whose approval is missing, marking as a suspected duplicate any item whose duplicate key matches an existing post, and recording for every item the check name, the result, the timestamp and the identifier of the run that produced it.
Deliver a content workflow and a sample output batch logging every check, every failure and the resulting publication state for each item, then reconcile the published count against the merchant's post list, confirm no item carries two published entries from one run, and confirm every held item names the check that blocked it and the condition that releases it.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
The merchant supplies the required-field list and the rule for completeness, covering the fields a post cannot ship without, and every one of them is checked before publication. Completeness is judged by content and not by presence, so a field holding a placeholder fails; any field the sources cannot fill blocks the item rather than being skipped.
Posts are compared on the key the merchant names, usually the handle or the title, against the existing post list before publication. A match holds the item for review instead of publishing it, because a duplicate handle is treated as the same address; near-matches differing only in punctuation are reported as suspected duplicates for a person to decide.
A retry is safe only when the run recorded the state before publishing and the failure is visible in that log. The item stays unpublished until the check passes, and the log shows whether the earlier attempt reached the blog; if it did, the merchant's records decide whether to edit the existing post instead of publishing a second copy.
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.