Ciwi
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant

Plan an assortment around seasonal demand

Assortment decisions are being made without a written view of which categories peak when or how much stock can be held. In this case, the immediate task is to plan an assortment around seasonal demand. The workflow should produce a seasonal assortment plan by period, reconciled against the merchant's historical records.

Topic
Product Research and Market Opportunities
Target keyword
seasonal product research
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 plan an assortment around seasonal demand.
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: [multi-period sales history covering a full seasonal cycle, category season definitions, supplier lead times, storage and holding constraints, and the stated in-season availability target].

Identify peaks by comparing the same periods across years for a repeatable rise, size each category's seasonal buy against lead time and holding limits rather than the peak week alone, and mark any category whose history covers too few cycles to support a plan.
Return a seasonal assortment plan by period, reconciled against the merchant's historical 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.
Use in Spark
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.

01

Step 1

Collect the multi-period sales history covering at least one full seasonal cycle, the season definitions per category, supplier lead times, storage and holding constraints, and the merchant's stated target for in-season availability.

02

Step 2

Identify peaks by comparing the same periods across years for a repeatable rise, size each category's seasonal buy against lead time and holding limits rather than the peak week alone, and mark any category whose history covers too few cycles to support a plan.

03

Step 3

Deliver an assortment plan by period showing categories, intended stock depth, order-by dates derived from lead times and off-season dispositions, then reconcile the planned quantities against the historical records period by period before committing.

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 genuine seasonal peak confirmed?

The same period is compared across the available years, and a peak counts only when the rise repeats rather than appearing once as a strong month; a single-cycle category is flagged with its evidence limit and planned conservatively instead of from its lone peak.

Why do order-by dates sit in the plan?

Because a seasonal buy that arrives after the peak contributes nothing, so each category's order date is derived from its lead time working back from the peak window; the dates make timing failures visible while they can still be prevented.

How are off-season items handled in the plan?

Each item gets an explicit off-season disposition of keep listed, discount out or retire, decided by its year-round demand in the records and the holding cost it incurs; leaving the decision until after the season turns unsold stock into an unplanned cost.

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.

Open Spark product pageBack to Spark scenario library