01
Step 1
Define the ideal customer profile, the target segments and the qualification rules, and list the sources the merchant permits, before drawing any candidates, recording the profile attributes in the order they will be checked.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Create a focused prospecting shortlist
Lists get scraped first and qualified later, so the week goes to companies that were never going to buy. In this case, the immediate task is to create a focused prospecting shortlist. The workflow should produce a qualified prospect shortlist with evidence and next steps taken from the merchant's own profile rules.
Topic
Lead Generation and Prospecting
Target keyword
ecommerce lead prospecting tool
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 create a focused prospecting shortlist.
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 ideal customer profile, the target segments, the qualification rules, the sources the merchant permits, and the profile attributes in the order they will be checked]. Draw candidates from the permitted sources and keep only those whose profile attributes are evidenced, recording for each entry the rule it passed, the source and date of the evidence, and marking any prospect whose fit rests on an unverified attribute as unconfirmed.
Return a qualified prospect shortlist with evidence and next steps, marking any prospect whose fit stays unconfirmed 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
Draw candidates from the permitted sources and keep only those whose profile attributes are evidenced, recording for each entry the rule it passed, the source and date of the evidence, and marking any prospect whose fit rests on an unverified attribute as unconfirmed.
03
Step 3
Deliver the prospecting shortlist with each entry's profile match, evidence, source, status and next step with an owner, then verify that every entry passes at least one stated rule with cited evidence and that entries marked unconfirmed are counted separately.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
When is a source acceptable?
When the merchant has permitted it and each entry can be traced to a named, dated record, because an anonymous export cannot be checked; purchased or scraped lists are acceptable only under that same test, and any entry failing it is dropped rather than carried on trust.
What makes an entry qualify rather than merely look close?
Evidence for each profile attribute the rules actually test; a company sharing the segment but missing the buying signal stays unconfirmed, and the shortlist reports confirmed and unconfirmed counts separately so outreach effort is planned on the confirmed ones.
How big should the shortlist be?
As large as the evidence supports and no larger: every entry must carry a checkable source, so a smaller list with complete evidence beats a long one with gaps, and remaining candidates stay in a backlog until evidence is found for them.
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.