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

Define a repeatable product research process for a Shopify store

Research results depend on who runs it, so two people reach different conclusions from the same data set. In this case, the immediate task is to define a repeatable product research process for a Shopify store. The workflow should produce a written research procedure a colleague can rerun, checked against the merchant's stated rules.

Topic
Product Research and Market Opportunities
Target keyword
shopify product research app
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 define a repeatable product research process for a Shopify 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: [current sourcing steps as practiced, product acceptance and rejection criteria, available data sources with access limits, and unstated judgments held by individual staff]. Rewrite those steps as a fixed sequence with explicit entry criteria stating the minimum evidence a candidate needs, evidence requirements per step, and one written decision point whose accept, reject and research-further outcomes are defined.
Return a written research procedure that a colleague can rerun, checked against the merchant's stated rules 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 sourcing steps actually used today, the criteria the merchant applies to accept or reject products, the data sources available with their access limits, and any unstated judgments that currently live only in one person's head.

02

Step 2

Rewrite those steps as a fixed sequence with explicit entry criteria stating the minimum evidence a candidate needs, evidence requirements per step, and one written decision point whose accept, reject and research-further outcomes are defined.

03

Step 3

Deliver the written procedure with a run sheet someone else can follow unchanged, then verify it by having a second reader walk one candidate through the sequence and confirming every step names its input, its evidence source and its decision rule.

FAQ

Common questions when running this scenario

Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.

What must the entry criteria specify?

The minimum evidence a candidate carries into review, typically dated demand data, a quoted landed cost and a named source for each figure; the rule prevents opinions entering before facts exist, and candidates below the bar are returned with the exact missing items listed rather than debated.

How is repeatability actually tested?

A second person runs one candidate through the written sequence without help and records where they had to guess; any guess marks a step whose criteria are not explicit enough, and the procedure is only confirmed when the rerun reaches the same decision from the same inputs.

What makes a decision point valid in the procedure?

It names the outcomes available, the rule that selects among them and the evidence the rule reads, so two operators with the same inputs cannot disagree; a step that still ends in a judgment call is flagged as needing criteria before the procedure can be final.

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