Stock questions arrive constantly, and an answer built on a stale reading leads to cancelled orders. In this case, the immediate task is to answer availability questions using current stock evidence. The workflow should produce availability replies that state the reading time and do not promise future stock.
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 answer availability questions using current stock evidence.
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 latest inventory reading per variant with its timestamp and source system, the variant options and parent product structure, the merchant's restock and backorder records, and the policy on selling through oversold stock]. Answer availability only at variant level from that reading, state the reading time in the store's timezone, distinguish in stock, below the merchant's stated low-stock threshold and unavailable, and never quote a parent-product total when variants differ.
Return the availability replies with their source timestamp verified against the supplied inventory data 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.
Pull the latest inventory reading per variant with the timestamp and source system of that reading, the variant options and parent product structure, the restock and backorder records the merchant maintains, and the policy on selling through oversold stock.
Answer availability only at variant level from that reading, state the reading time in the store's timezone, distinguish in stock, below the merchant's stated low-stock threshold and unavailable, and never quote a parent-product total when variants differ.
Deliver the availability replies carrying their source timestamp and the variant each describes, offer notification in place of dates when no confirmed restock record exists, and re-read the inventory system before any availability commitment is repeated.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
It uses the newest reading the connected system offers and states that time so the shopper can judge the answer, because between the reply and the purchase another channel may already have taken the last unit.
Only when the merchant's own record carries a confirmed date; otherwise it offers to notify when the variant returns, since an estimated date quietly becomes a promise the store has to keep.
Availability is quoted for the specific option asked about, and the bot confirms the size or option before committing, because a parent-level answer hides that the shopper's chosen variant is already unavailable.
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.