01
Step 1
Collect the URL list, each URL's title tag, the page's own heading, and the search topic each page serves, so similarity can be judged against intent.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Identify repeated meta titles across URLs
A merchant suspects several product and collection pages compete with each other because their title tags came from one template. In this case, the immediate task is to identify repeated meta titles across URLs. The workflow should produce a grouped list of duplicate and near-duplicate titles with one distinct replacement drafted per affected URL.
Topic
SEO Metadata and Content Audits
Target keyword
shopify duplicate meta titles
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 identify repeated meta titles across URLs.
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 URL list, each URL's title tag, the page's own heading, and the search topic each page serves]. Group titles that are identical or differ only by a variant word, distinguish template-generated similarity across variant pages serving one product family from accidental collision between distinct topics, and draft a distinct replacement only for affected URLs whose topics genuinely differ.
Return a duplicate-title audit with grouped URLs and one replacement title per URL 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
Group titles that are identical or differ only by a variant word, distinguish template-generated similarity across variant pages serving one product family from accidental collision between distinct topics, and draft a distinct replacement only for affected URLs whose topics genuinely differ.
03
Step 3
Deliver the grouped duplicate list with one replacement per affected URL, then verify each replacement against its page heading and topic, and document intentionally shared template titles as accepted.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
How is template similarity told apart from accidental collision?
Variant pages generated from one template legitimately share wording, so each group is checked against whether its pages serve the same product family or genuinely distinct topics. Template similarity is documented as accepted; accidental collision between distinct topics is queued for rewriting. The distinction is recorded per group, not decided by similarity alone.
Which duplicates are left untouched?
Groups the merchant confirms as intentional, typically template-driven variant pages whose shared titles match their shared purpose, and any page whose title change would conflict with a migration already in flight. These are documented as accepted with the reason. Everything else serving a distinct topic receives a distinct replacement.
How is each replacement tied to its page?
Each drafted title is checked against the page's own heading and stated search topic, so the replacement describes that URL rather than the group it came from. The deliverable pairs old and new titles per URL. No replacement is published without its page-level check, which prevents one fix from creating a new collision elsewhere.
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.