Competitor notes collected informally cannot be reused because nobody recorded how each field was observed. In this case, the immediate task is to build a structured competitor research brief. The output should fix the question, scope, fields and cadence so repeated passes produce comparable entries.
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 build a structured competitor research brief.
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 research question, the named competitors in scope, the field list with units and allowed values, the source page per field, the owner and review cadence, and a dated baseline pass]. Require every field to be recorded exactly where the brief says it was observed, write not-observed rather than an estimate wherever the page showed nothing, and reject entries missing a source or an observation date so later passes stay comparable.
Return a competitor change log and specific opportunities to investigate with the brief's fields mapped to the supplied records 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.
Fix the research question, the named competitors in scope, the field list with each field's unit and allowed values, the source page observed for each field, the owner and the review cadence, taking a dated baseline pass before any comparison starts.
Require every field to be recorded exactly where the brief says it was observed, write not-observed rather than an estimate wherever the page showed nothing, and reject entries missing a source or an observation date so later passes stay comparable.
Deliver the brief and a change log whose rows each carry the observation date, source URL and observer, check that every competitor in scope has one row per field for every pass, and report any pass that could not be completed.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Comparability across passes depends on identical fields observed identically. A field added mid-study leaves every earlier row without a value, so new fields start a new field set and the change is recorded instead of backfilled across older entries.
Write not-observed along with the page checked and the date, never a plausible estimate. Visible gaps can be chased later, whereas an inferred value becomes indistinguishable from a genuine observation once the source page has moved on.
The owner named in the brief, on the stated cadence, since the log is trustworthy only while the same rules are read the same way. When someone else stands in, the substitute is recorded so any shift in reading style stays visible.
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.