01
Step 1
Collect each reported symptom with the affected URL, the device and browser used, the account state if one was involved, the time it was seen and the action that preceded it.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Find observable website errors and affected pages
Error reports from customers and staff vanish before anyone checks whether the errors repeat. In this case, the immediate task is to find observable website errors and affected pages. The workflow should gather the reported symptoms, affected URLs and triggering conditions, then attempt reproduction and log only what can be shown.
Topic
Store Health Audits
Target keyword
shopify website error checker
Copyable AI prompt
A prompt you can drop directly into Spark
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.
ai-prompt.txt
Act as a Shopify operations specialist.
Help me find observable website errors and affected pages.
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: [each reported symptom with its affected URL, the device and browser used, the account state in play, the action preceding it and the time it was seen]. Attempt reproduction under the recorded conditions and mark an error repeatable only when it appears again under the same conditions, leaving anything seen once as unconfirmed while keeping the reported conditions attached.
Return an error log with pages and reproduction steps 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.How to solve
A recommended resolution workflow
Split the work into input, judgment, and deliverable phases. Verify each step's output before moving to the next.
02
Step 2
Attempt reproduction under the recorded conditions and mark an error repeatable only when it appears again under the same conditions, leaving anything seen once as unconfirmed while keeping the reported conditions attached.
03
Step 3
Deliver the error log with one row per symptom carrying its URL, reproduction steps, repeat status and the evidence captured, then recheck the corrected pages and confirm every row ends as repeatable, unconfirmed or resolved with a date.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Why record the conditions and not just the URL?
The same URL behaves differently by device, account state and preceding action, so the conditions tell the next person where to stand to see the error. Without them a report often cannot be reproduced at all.
How is a repeatable error separated from a one-off?
By reproducing it under the recorded conditions and getting the same result. One occurrence may come from a transient network or cache state, so it belongs in the log at low priority rather than driving the fix order.
What happens to an error that clears before anyone looks?
It stays in the log as unconfirmed with the reported conditions and the last time seen. Marking it resolved would claim a fix that nobody verified.
Related scenarios
Continue with adjacent or same-topic scenarios
Start with scenarios under the same topic, then expand into cross-topic matches suggested by similarity.
Next step
Want these AI scenarios embedded directly into daily operations?
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.