Give a support rep specific coaching on a weak ticket reply
Generic QA feedback ('be more empathetic') does not change behavior. This prompt produces specific, actionable coaching notes tied to exact lines in a rep's reply, making it useful for weekly 1:1s or async review.
You are a support team lead conducting quality review. Your job is to give a rep clear, specific coaching on a ticket reply—not a score, not vague praise, but line-level feedback they can apply immediately.
Context:
- Rep's reply to review: {{REP_REPLY}}
- Original customer message they were responding to: {{ORIGINAL_CUSTOMER_MESSAGE}}
- Your team's top 3 quality standards: {{QUALITY_STANDARDS}}
Follow these steps:
1. Quote the strongest sentence or phrase in the reply and explain in one sentence why it works.
2. Identify up to 3 specific issues. For each issue:
a. Quote the exact sentence or phrase that is the problem.
b. Name the issue type (e.g., unclear next step, assumed knowledge, deflection, unnecessary apology).
c. Write a revised version of that sentence.
3. Check whether the reply directly answered the customer's actual question. If not, note what was missed.
4. Give one piece of structural feedback (length, format, ordering of information).
5. End with a single sentence summary the rep can remember going into their next ticket.
Edge cases: If the reply is genuinely strong with no meaningful issues, say so clearly in step 2 rather than manufacturing criticism. This prompt works best for written email or chat replies; it is not calibrated for phone call transcripts. {{REP_REPLY}}{{ORIGINAL_CUSTOMER_MESSAGE}}{{QUALITY_STANDARDS}}
How to use this prompt
- Copy the prompt above (Copy button on the top-right).
- Replace each
{{VAR}}with your own value. Variables:{{REP_REPLY}}{{ORIGINAL_CUSTOMER_MESSAGE}}{{QUALITY_STANDARDS}}. - 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
Notion AI
$8/user/mo add-onAI baked into the docs/wiki/projects tool you already use.
Notion AI is unremarkable as a standalone writer but indispensable if Notion is your team's source of truth — it works on the docs and databases you already have.
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.