Re-anchor tone after a hostile customer message
When a customer sends an aggressive or threatening message, your reply sets the emotional trajectory of the entire conversation. This prompt helps you draft a response that acknowledges frustration without matching it or caving unnecessarily.
You are an experienced support specialist trained in de-escalation. A customer has sent a hostile message and I need to draft a reply that lowers the temperature without being dismissive or sycophantic.
Context:
- Customer message: {{CUSTOMER_MESSAGE}}
- Current status of their issue: {{ISSUE_STATUS}}
- What I can and cannot offer right now: {{OFFER_CONSTRAINTS}}
Follow these steps:
1. Identify the core grievance beneath the anger (separate the emotion from the request).
2. Draft an opening sentence that names the frustration specifically—do not use 'I understand your frustration' or 'I apologize for any inconvenience'.
3. Write 2-3 sentences that explain the current status in plain language, without deflecting blame onto other teams or systems.
4. State clearly what will happen next and by when. If no deadline is possible, say so and explain why.
5. Close with one sentence that leaves the door open for follow-up without sounding like a form letter.
6. Flag any part of the message that suggests an escalation risk (chargeback threat, legal language, public complaint threat) and suggest how to handle it separately.
Edge cases: If the message contains hate speech or personal threats, stop at step 1 and recommend escalating to a manager rather than responding directly. If the issue is already resolved, note that in step 3 and skip step 4. {{CUSTOMER_MESSAGE}}{{ISSUE_STATUS}}{{OFFER_CONSTRAINTS}}
How to use this prompt
- Copy the prompt above (Copy button on the top-right).
- Replace each
{{VAR}}with your own value. Variables:{{CUSTOMER_MESSAGE}}{{ISSUE_STATUS}}{{OFFER_CONSTRAINTS}}. - Paste it into one of the recommended tools below.
- Iterate: tighten constraints in the prompt if the output is generic.
Why this prompt is structured this way
The prompt is split into explicit steps because LLMs do better when the path is named, not implied. Each variable forces specificity at the input layer — vague inputs get vague outputs.
Pair this prompt with a tool
Grammarly
$12/moGrammar, tone, and clarity across every app.
Grammarly remains the default for grammar + tone checking. The 'Grammarly Go' generative features are catching up but are not the main reason to subscribe.
Claude (Anthropic)
$0/mo (Pro at $20)Frontier model with long context and strong reasoning.
Claude (Opus / Sonnet / Haiku tiers) is the assistant favored by writers and engineers who care about reasoning quality and tone. 1M token context on Opus.
ChatGPT (OpenAI)
$0/mo (Plus at $20)The category-defining general-purpose AI assistant.
ChatGPT has the broadest feature surface: image gen, voice, custom GPTs, web browsing, code execution. Often the right default; sometimes beaten on specific tasks by Claude or Perplexity.
The PlaybookPrompts weekly
One short email per week. The five sharpest prompts we found, one tool worth your attention, one anti-pattern to avoid. Unsubscribe in one click.
Newsletter signup is not configured. Set PUBLIC_NEWSLETTER_USERNAME in the build env.