An inbound question sits in the inbox with details already on record, but replies are written from memory and miss what was asked. In this case, the immediate task is to draft inquiry emails from verified prospect context. The workflow should produce a message answering that question and a timing plan for the next touch, taken from the prospect's own record.
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.
Act as a Shopify operations specialist.
Help me draft inquiry emails from verified prospect context.
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 prospect record with its source and owner, the prior inquiries and replies on that thread, the offer in play with its approved figures, the stated contact channel and timing preference, and the buyer's role if recorded]. Write the message so it answers the specific question asked, in the order the buyer asked it, using only approved figures and verified details, and leaving any point the record does not support as a question back to the buyer rather than an assumption in the draft.
Return the outreach draft and follow-up schedule 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.Split the work into input, judgment, and deliverable phases. Verify each step's output before moving to the next.
Read the prospect record with its source and owner, the prior inquiries and replies on that thread, the offer currently in play with its approved figures, the stated contact channel and any timing preference, and the buyer's role if one is recorded.
Write the message so it answers the specific question asked, in the order the buyer asked it, using only approved figures and verified details, and leaving any point the record does not support as a question back to the buyer rather than an assumption in the draft.
Deliver the outreach draft with its subject, body, the question it answers and the timing plan for the next touch, then check every claim, figure, term and contact detail against the merchant's records and list any item still needing confirmation before sending.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Only where the buyer asked about cost and the offer in play carries approved figures, quoting exactly those figures with their terms; where pricing depends on quantity or configuration, the reply gives the basis and asks the one question needed, instead of stating a number nobody approved.
Enough to show the question was read: the product or configuration asked about and the constraint the buyer mentioned; unrelated attributes add noise and risk exposing an unverified detail, so anything unsourced stays out of the draft.
Set it from the timing preference on the record or, absent one, from how long the buyer's own question takes to answer; a reply that promised information goes out when that information exists, and any touch is skipped if the buyer has already responded or opted out.
Start with scenarios under the same topic, then expand into cross-topic matches suggested by similarity.
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.