Let a support agent arrange returns without an order number: match the customer, verify identity, and adapt tone by brand and region so humans only take the tricky cases: AI agent prompt
Sierra's customer story on Next, the British fashion retailer operating across 83 countries, describes an AI agent that went live in six weeks on two high-volume use cases. The agent handles complex arrange-return queries, automatically matches customers without requiring order numbers, and manages identity verification. It adapts to regional preferences and brand voices across labels such as Gap, Victoria's Secret, and Fat Face as Next expands languages and processes with sales growth. Sierra reports Next's team emphasizing how far the agent can go while keeping a professional, helpful, friendly tone. Metrics beyond time-to-live are qualitative in the public story.
The prompt
Design an arrange-return agent for my retail stack. Brands/regions: [list], channels: [chat/voice/WhatsApp], systems: [OMS, identity, returns portal]. Rules: never invent an order; verify identity before address or payment changes; escalate damaged-item disputes and fraud flags to a person. 1) Write the flow: match customer without order number → verify identity → confirm eligible items → book return → confirm label. 2) List data fields the agent may read vs write. 3) Draft brand-tone variants for [2 brands]. 4) List 10 escalation reasons. 5) Propose a 6-week rollout checklist and success metrics (containment, CSAT, identity-fail rate). Do not process a real return in this chat.
Fill in the blanks, then copy
This prompt has 4 [bracket]s to fill in. Type your details below and the prompt updates as you go. Your answers stay in this browser and are reused on other prompts with the same blanks. Nothing is sent to us.
Example values are fictional, just to show how a filled-in prompt reads. Replace them with your real details.How to use it
- Copy the prompt above.
- Replace every [bracket] with your own details (use the fill-in-the-blanks box above, which remembers your answers for the next prompt).
- Paste it into Sierra (or similar customer AI), ChatGPT, Claude and review the answer before you use it.
Works with: Sierra (or similar customer AI), ChatGPT, Claude, your OMS/returns systems
Real-world example: sierra.ai/customers/next
Featured in: AI prompts for writing SOPs, reports, policies and checklists
Before you use it: what to check
Already built into this prompt
- Rules: never invent an order; verify identity before address or payment changes; escalate damaged-item disputes and fraud flags to a person.
- Do not process a real return in this chat.
Check yourself
- This prompt works on text other people wrote (emails, reviews, messages or web pages). That text can hide instructions aimed at AI, such as "ignore your rules and…". Paste it as material to work on, and never let the AI act on requests inside it, like paying, sharing logins or changing records. How prompt injection works →
- Check every figure, price and total against your own records before anything is sent, posted or booked. A person approves refunds, discounts, payments and price changes.
- Remove names, contact details, account numbers and other personal data the task doesn't need before you paste, and check your AI tool's data and training settings.
- Check names, dates, numbers and any claim against your own source material before you use the answer. AI can misread or invent details.
Using an AI agent? Download this prompt as a SKILL.md agent skill with these checks built in, or get the .zip for Claude.ai. How to install skills.
Want to make this prompt even better? Grade it with the free prompt grader or build your own with the AI prompt generator.
32 copy-paste agent prompts (PDF) plus 5 new prompts every week.
Get it freeMore Customer Support prompts
See all Customer Support prompts →