01
Step 1
Record the size, budget ceiling, exclusions such as materials or allergens, preferred categories and the occasion or use the shopper described, marking each item as stated rather than assumed.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Recommend products based on stated shopper needs
A shopper has stated size, budget and exclusions and expects a list shaped by them rather than by popularity. In this case, the immediate task is to recommend products based on stated shopper needs. The workflow should produce a personalized list that shows the matching criteria used and checks each item against the supplied product data.
Topic
AI Shopping and Product Recommendations
Target keyword
shopify personalized product recommendations
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 recommend products based on stated shopper needs.
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 shopper's stated size, budget ceiling, exclusions such as materials or allergens, preferred categories and described occasion or use, each marked as stated rather than assumed]. Apply those constraints as hard filters before any ranking, drop items missing a value the shopper cares about instead of filling the gap with an assumption, then order the survivors by how many stated requirements they satisfy and record the criteria that put each one where it landed.
Return the personalized list with the matching criteria shown and checked against the supplied product data 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
Apply those constraints as hard filters before any ranking, drop items missing a value the shopper cares about instead of filling the gap with an assumption, then order the survivors by how many stated requirements they satisfy and record the criteria that put each one where it landed.
03
Step 3
Deliver the personalized list showing the matching criteria used, each item's fulfilment of them and any requirement relaxed for it, and reconcile every entry against the supplied product data including its price and the variants currently available.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
What makes the list personal rather than popular?
It is built from requirements the shopper actually expressed, and each entry shows the criteria it matched; popularity or revenue ordering never overrides a stated filter, so nothing enters the list on those grounds alone.
How strictly is a stated budget applied?
As a hard filter before ranking, never as a soft preference. An item above it appears only as a flagged exception stating the difference and its advantage, because slipping such items quietly into the main list rewrites the shopper's constraint.
How are exclusions such as certain materials handled?
They run as filters ahead of ranking using values the catalogue actually stores; a product missing that attribute is treated as non-compliant rather than acceptable, since an absent value is not evidence of absence.
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.