ipIterPrompt

Angry Customer Reply — Education Platform

De-escalate a furious customer whose complaint is at least partly justified. Purpose-built for education platform contexts.

iterpromptUpdated 2026-07-103,254 copies

A structured customer support prompt for de-escalation: de-escalate a furious customer whose complaint is at least partly justified, tailored to a learning platform serving students, parents, and instructors. It walks the model through a proven process with an explicit quality bar, and delivers a reply that validates the specific grievance, owns the failure plainly, presents the make-good, and invites them back without groveling.

The prompt

Variables to fill in: {{customer_message}}{{history_facts}}{{constraints}}

You are a de-escalation specialist who turns furious customers into salvaged relationships. I need your help in the context of a learning platform serving students, parents, and instructors.

TASK: De-escalate a furious customer whose complaint is at least partly justified.

DELIVERABLE: Produce a reply that validates the specific grievance, owns the failure plainly, presents the make-good, and invites them back without groveling.

PROCESS:
1. Review the inputs below. If anything critical is missing or ambiguous, ask me up to three clarifying questions before producing the deliverable.
2. Separate the emotion from the facts in the customer's message; name the legitimate grievance explicitly.
3. Own what the company got wrong without deflection, then move decisively to what happens now.
4. Set boundaries respectfully where the customer's demand cannot be met, and always leave a path forward.
5. Produce the deliverable in a clean, skimmable format I can use directly.

QUALITY BAR:
- Never argues, never matches anger, never hides behind policy language.
- Apologies are specific and tied to actions, not reflexive.
- The customer can tell a human read their message.

INPUTS:
- The angry or difficult message, pasted verbatim: {{customer_message}}
- What actually happened, previous contacts, and what you can offer: {{history_facts}}
- What you cannot do, and any policy limits that apply: {{constraints}}

Run this prompt on a real model without leaving the page. Every run is saved to your history for this prompt.

Fill in the variables

How to use

  1. 1Fill in the {{customer_message}}, {{history_facts}}, {{constraints}} variables with your real details — specifics in, specifics out.
  2. 2Paste the prompt into ChatGPT, Claude, Gemini, or any capable model.
  3. 3Answer the clarifying questions it asks; that step is what makes the output fit your situation.
  4. 4Iterate on the deliverable: ask for alternatives, tighter versions, or a different angle on any section.

Pro tips

  • If the output feels generic, add more concrete detail to the inputs — names, numbers, and constraints sharpen everything.
  • Works well in a thread: keep the conversation going to refine a reply that validates the specific grievance, owns the failure plainly, presents the make-good, and invites them back without groveling.

Related

Repeat-Issue Apology — Fintech & Banking

Apologize to a customer hit by the same problem more than once. Purpose-built for fintech & banking contexts.

4,319 copiesOpen ↗

Negative Public Review Response — B2B SaaS

Respond publicly to a harsh review that other customers will read. Purpose-built for b2b saas contexts.

4,316 copiesOpen ↗

Repeat-Issue Apology — Enterprise Accounts

Apologize to a customer hit by the same problem more than once. Purpose-built for enterprise accounts contexts.

2,916 copiesOpen ↗

Negative Public Review Response — Fintech & Banking

Respond publicly to a harsh review that other customers will read. Purpose-built for fintech & banking contexts.

4,165 copiesOpen ↗