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

Explain product features using supported details

Feature text on the page has drifted from what the product documentation states, and some attributes have no source at all. In this case, the immediate task is to explain product features using supported details. The workflow should produce feature descriptions that carry their source, mark attributes with no recorded origin and list the gaps still open.

Topic
Product Features and Benefits Copy
Target keyword
shopify product feature descriptions
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 explain product features using supported details.
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 documented specifications, the variant attributes on record, the approved terminology and units, and the feature text currently on the page].

Describe each feature using only the attributes those records confirm, keep the recorded unit and term rather than a looser synonym, and mark any attribute with no recorded origin as unverified instead of inferring it from a similar product.
Return the descriptions with their sources 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

Start from the documented specifications, the variant attributes on record, the approved terminology and units, and the feature text currently on the page so any drift can be measured.

02

Step 2

Describe each feature using only the attributes those records confirm, keep the recorded unit and term rather than a looser synonym, and mark any attribute with no recorded origin as unverified instead of inferring it from a similar product.

03

Step 3

Deliver the feature descriptions with their source beside each attribute, then verify the wording against the supplied records, list the attributes still missing an origin and note every point where the new text differs from what the page says today.

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 drift from the documentation measured?

Compare the current page text against the documented attribute by attribute and record each difference. A rewrite that matches the documentation in meaning but not in wording is still drift, and it is worth noting.

Can an attribute be written from a photo or a sample?

No, only from a record, because appearance does not establish a measured value. Mark it unverified and request the figure, since a written attribute becomes a promise at the moment of checkout.

Should units and terminology be standardised while describing?

Yes, to the units and terms the merchant has approved, but keep the conversion visible. Changing a unit silently leaves the new text disagreeing with every record that still uses the old one.

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