01
Step 1
Collect the ideal customer profile, the criteria the merchant has chosen, the weight or order each criterion carries, the permitted source data and the rules for handling attributes that cannot be verified.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Score lead fit using explicit business criteria
Enthusiasm rather than criteria decides who gets called first, and the reasoning is never written down. In this case, the immediate task is to score lead fit using explicit business criteria. The workflow should produce a qualified prospect shortlist with evidence and next steps verified against the merchant's own records.
Topic
Lead Generation and Prospecting
Target keyword
ecommerce lead scoring
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 score lead fit using explicit business criteria.
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 scoring criteria the merchant has chosen, the weight or order each criterion carries, the permitted source data, and the rule for unverifiable attributes]. Score each prospect criterion by criterion against those weights, recording the evidence behind every score, leaving unknown attributes unresolved rather than awarding them a neutral value, and flagging entries whose total depends on an unverified attribute.
Return a qualified prospect shortlist with evidence and next steps verified against the 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.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
Score each prospect criterion by criterion against those weights, recording the evidence behind every score, leaving unknown attributes unresolved rather than awarding them a neutral value, and flagging entries whose total depends on an unverified attribute.
03
Step 3
Deliver the qualified prospect shortlist with each entry's per-criterion scores, total, evidence, unresolved gaps and next step with an owner, then recheck a sample by rescoring it from the cited evidence and confirm the totals reproduce.
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 a missing attribute scored?
It stays unresolved with the gap recorded, because assigning a neutral value silently raises or lowers the total on an assumption; an entry whose rank depends on unresolved attributes is flagged, so the owner knows the score may move once the gap is filled.
Why record the weights used?
Because without them the same prospect can be rescored differently tomorrow, and results cannot be compared across runs; writing down each criterion's weight or order makes the score reproducible and lets the merchant change one weight and see what moves.
What does a score change in practice?
Only the order and the next step: a higher score moves a prospect earlier in outreach and picks the angle, while a low score sends it to nurture or back to research; the score never replaces the evidence line, which stays on the record.
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.