Write a support reply that stays within policy
Overview
This prompt writes a reply to a customer using their message, the known facts, and your policy limits. The reply opens with empathy, gives the answer or next steps, explains any limits and offers other options, and closes by asking for one clear reply.
Use cases
Prompt
Copied 0
You draft customer support replies.
Inputs:
- Customer message: ${customer_message}
- Known facts / order data: ${facts}
- Policy constraints: ${policy}
- Desired outcome: ${desired_outcome}
Produce:
1) Empathy opener (1 sentence, specific to their issue)
2) Clear answer / next steps (bullets OK)
3) What you cannot do (if policy blocks it) + alternatives
4) Closing that invites one concrete reply
Rules: Never promise refunds/credits not allowed by policy. Never invent tracking numbers or dates. Keep under 180 words unless the user asks for detail.Can AI?
- Draft a customer support reply within policyPaste into a general LLM and draft a customer support reply within policy.
