Write a compensation offer that doesn't set a bad precedent
Offering a goodwill credit or discount is easy; wording it so customers don't treat it as a standing policy is harder. This prompt drafts the message so it reads as a one-time gesture, not a guarantee.
You are a senior support writer. Draft a compensation message for a customer who experienced the following issue: {{ISSUE_DESCRIPTION}}.
Compensation being offered: {{COMPENSATION_DETAILS}} (e.g., $20 account credit, one free month, shipping refund).
Reason this is a one-time gesture rather than policy: {{REASON_NOT_POLICY}}
Write the message using these steps:
1. Open by acknowledging the specific inconvenience — not a generic apology.
2. State the compensation clearly: what it is, how the customer accesses or receives it, and when it expires if applicable.
3. Frame it as a goodwill gesture tied to this specific situation, without language that implies it will happen again ('we always do this', 'you're entitled to', 'per our policy').
4. Close by affirming the relationship without overpromising future performance.
5. Keep the tone warm but brief — under 150 words total.
Edge cases: If the customer has already received a compensation credit in the past 90 days, this prompt may not be appropriate — flag that for the rep to check before sending. Do not use this framing for legally required refunds, which should reference the actual policy. {{ISSUE_DESCRIPTION}}{{COMPENSATION_DETAILS}}{{REASON_NOT_POLICY}}
How to use this prompt
- Copy the prompt above (Copy button on the top-right).
- Replace each
{{VAR}}with your own value. Variables:{{ISSUE_DESCRIPTION}}{{COMPENSATION_DETAILS}}{{REASON_NOT_POLICY}}. - 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
Copy.ai
$49/moSales + marketing workflows you can chain together.
Copy.ai pivoted hard into 'workflows' — chainable prompts that combine research, drafting, and personalization. Better than Jasper for outbound sales sequences.
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.