01
Step 1
Collect the contact records used for outreach with their email and phone fields, the consent state recorded for each channel, the bounce and delivery outcomes available, and the merchant's stated rules for permitted follow-up.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Organize customer contact records for reliable follow-up
Outreach keeps bouncing and some recipients never gave permission, so no one knows which records are safe to use. In this case, the immediate task is to organize customer contact records for reliable follow-up. The workflow should produce a contact cleanup plan and proposed duplicate groups, splitting usable contacts from those needing correction.
Topic
CRM and Contact Management
Target keyword
shopify customer contact management
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 organize customer contact records for reliable follow-up.
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: [contact records with their email and phone fields, the consent state recorded for each channel, available bounce and delivery outcomes, and the merchant's stated rules for permitted follow-up]. Mark each record usable, needing correction or out of scope by testing its channel against the recorded consent state and delivery outcome, and never read a missing permission as permission granted.
Return a contact cleanup plan with proposed duplicate groups, verifying each entry and flagging anything unverified 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
Mark each record usable, needing correction or out of scope by testing its channel against the recorded consent state and delivery outcome, and never read a missing permission as permission granted.
03
Step 3
Deliver the cleanup plan with usable contacts split by channel, the correction list and the proposed duplicate groups, verify every entry against its source record, and flag anything the supplied records cannot confirm.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
What happens to a bounced address?
The channel is marked unusable and dropped from outreach while the order history stays with the customer, so a later correction can restore it without the record itself being lost.
How is consent recorded for more than one channel?
Per channel, because permission for email says nothing about messaging; a record usable on one channel stays in that channel's list and is kept out of the others.
Why not delete unusable contacts?
Deletion is a retention decision the merchant's own policy owns, and a contact that cannot be messaged may still be a customer with orders, so the plan separates them instead of removing them.
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.
Organize customer information for practical CRM use
Identify likely duplicate customer records for review
Create delivery-status notifications from reliable evidence
Define a consistent sales follow-up workflow
Plan operational alert delivery to a WeCom destination
Automate product updates using explicit change rules
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.