01
Step 1
Document the intake sources, the capture triggers, the fields each source carries and the qualification criteria the team already accepts, with the owner responsible for each stage and the system where the record lands.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Design a repeatable qualified lead collection process
The team collects leads through several channels, but each rep decides what counts as qualified in a different way. In this case, the immediate task is to design a repeatable qualified lead collection process. The workflow should produce the documented steps with named owners and a first shortlist drawn from the sources and criteria the team accepts.
Topic
Lead Generation and Prospecting
Target keyword
shopify lead generation automation
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 design a repeatable qualified lead collection process.
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 intake sources, the capture triggers, the fields each source carries, the qualification criteria the team accepts, the owner per stage, and the system where each record lands]. Turn them into repeatable steps with a named owner per branch, automate only the stages whose rules are stable and fully recorded, keep judgement steps with a person, and remove any branch that depends on a field the store cannot capture or a rule nobody has agreed.
Return the collection process and first shortlist 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
Turn them into repeatable steps with a named owner per branch, automate only the stages whose rules are stable and fully recorded, keep judgement steps with a person, and remove any branch that depends on a field the store cannot capture or a rule nobody has agreed.
03
Step 3
Deliver the documented process with each step's trigger, owner, system and exit condition plus the first shortlist drawn from the accepted sources, then verify that every automated branch traces to a recorded field and rule and that each shortlist entry names an owner.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Which stages should be automated first?
Capture and routing, where the rule is stable and written down, because those steps repeat identically every time; qualification and anything needing judgement stay with a named owner, and a stage with no agreed rule is left manual until the rule exists.
How does the team keep one definition of qualified?
Write the criteria into the process as a checklist each record must pass, with the evidence field required per criterion; a rep can still override, but the override is recorded against the rule it skipped, which makes disagreements visible instead of silent.
When should the process be rechecked?
Whenever a source, a field or a criterion changes, plus a periodic sample audit where records are rescored against the written rules; entries that pass automation but fail the audit show which rule the automation is applying incorrectly.
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.