01
Step 1
Set the buying role and company criteria the merchant accepts, then collect the store's own business customer records, the market and category scope, and any external source permitted, recording where each attribute came from.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Identify relevant B2B prospects for the store
Existing business customers came in through referrals, leaving no repeatable way to describe who else to approach. In this case, the immediate task is to identify relevant B2B prospects for the store. The workflow should produce a qualified prospect shortlist with evidence and next steps derived from the merchant's own customer records.
Topic
Lead Generation and Prospecting
Target keyword
shopify b2b lead generation
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 relevant B2B prospects for the store.
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 buying-role and company criteria the merchant accepts, the store's own business customer records, the market and category scope, and any external source the merchant permits].
Identify companies resembling the existing business customers on the criteria set, capture for each the specific signal that suggests a business need with its source and date, and separate verified attributes from inferred ones rather than filling gaps with plausible guesses.
Return the B2B shortlist with evidence, separating verified details from assumptions 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
Identify companies resembling the existing business customers on the criteria set, capture for each the specific signal that suggests a business need with its source and date, and separate verified attributes from inferred ones rather than filling gaps with plausible guesses.
03
Step 3
Deliver the B2B shortlist with each company's role, matching criteria, signal, evidence source, verified or inferred status and next step with an owner, then confirm every listed company traces to a named source and that existing customers are held in a separate section.
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 company judged relevant to the store?
It must match the criteria the merchant set on both levels: a role that can buy and a company need the catalog serves; a close match on company profile alone is not enough, and where only one level is confirmed the entry is listed as partially qualified with the gap named.
What makes a need signal usable?
A dated, named observation such as an active product line, a stated requirement or a recorded expansion, because an undated claim cannot be checked later; signals inferred from a similar company are marked inferred and never presented as evidence.
Should existing customers appear on the shortlist?
Keep them in a separate profile section: they show the pattern worth mirroring and may hold expansion potential, but counting them as new prospects inflates the list and hides how few genuinely new companies were found.
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.