Speed complaints point at photography, yet heavy files, delivery and theme behaviour can each produce the same visible delay. In this case, the immediate task is to identify why product images load slowly. The workflow should produce a findings list that attributes the delay to one cause at a time and pairs each cause with the fix it calls for.
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 identify why product images load slowly.
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: [affected page URLs, per-image file sizes and formats, recorded timing baselines, and theme loading behaviour notes]. Test one image request at a time against the baseline, attributing each delay to a single cause — oversized file, inefficient format, delivery conditions or page behaviour — and refusing to log a cause the measurement does not support.
Return a findings list attributing the delay with a fix per cause, rechecked against the evidence on record 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 affected page URLs, each image's file size and format from the store's asset records, the merchant's recorded timing evidence as the baseline, and notes on how the theme loads imagery such as lazy-loading and request count per gallery.
Test one image request at a time against the baseline, attributing each delay to a single cause — oversized file, inefficient format, delivery conditions or page behaviour — and refusing to log a cause the measurement does not support.
Deliver a findings list pairing each attributed cause with the fix it calls for, then re-measure the same image request after each change and compare it with the recorded baseline before the finding is closed.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Because heavy files, delivery conditions and page behaviour all produce the same visible delay, and a combined diagnosis hides which fix actually works; each finding names the single cause the request-level measurement supports, so the fix can be tested on its own.
By the placement each file serves: hero images keep more quality because they face the buyer full-size, while thumbnails can be compressed harder; the rule follows the stated placement rather than applying one compression level across the gallery.
The same image request is measured again after the change and compared with the baseline recorded in the collection step; a finding closes only when the re-measurement shows the delay removed, not when the file has merely been edited.
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.