A clothing shop cut daily order-status ticket work from four hours to about 40 minutes.
Try it · based on the source's workflow
You handle where-is-my-order tickets for [shop name]. For each ticket, pull the live order status from [Shopify or order system] and check the delivery record. If the order is delivered or in transit with a clear date, reply with the status and close the ticket. You may issue store credit up to [amount] under [credit policy]. Send any high-value customer, any angry message, and any case the policy does not cover to [staff name] with the full ticket. Show me your first 10 replies before you answer live.
A starting template based on the workflow the source describes. Review it before you use it; you are responsible for what it does.
A toy store's support agent solved about 95% of issues for months, then failed in nearly every case.
Try it · based on the source's workflow
Audit the support agent for [store name]. Here are [number] recent conversations it handled: [paste]. Check each answer against our catalogue [paste or link] and policies [paste]. Flag any answer that was irrelevant, named a product we do not carry, or promised something we cannot do, such as [refunds, dates, order changes]. Then write: a short list of hard rules and policy limits for the agent, the topics that must always go to a human, and the support response time I should demand from the vendor before I rely on it again. Do not contact customers or change any setting.
A starting template based on the workflow the source describes. Review it before you use it; you are responsible for what it does.