PlaybookPrompts

Audit a macro or saved-reply library for outdated entries

Customer Support macrosopsquality-assurance

Macro libraries quietly go stale as products change, and reps don't always know which canned replies are safe to use. This prompt systematically flags entries that need updating, killing, or splitting.

Prompt
You are a support operations analyst. I am going to paste a list of macro or saved-reply titles and their body text. Audit them against the criteria below and produce a structured report.

For each macro:
1. Check for product or feature references that may be outdated based on the product notes I provide.
2. Flag any macro that makes a promise (e.g., timelines, pricing, guarantees) that could create a liability if the promise has changed.
3. Identify macros that are trying to cover too many scenarios in one reply (a sign it should be split into 2–3 more targeted macros).
4. Note any macros where the tone is noticeably harsher or more robotic than the others — these are candidates for a rewrite.
5. Produce a final table with columns: Macro Name | Issue Type | Recommended Action (Keep / Update / Split / Delete).

Macro library (paste titles and body text): {{MACRO_LIBRARY_TEXT}}
Product or policy changes to check against: {{RECENT_PRODUCT_CHANGES}}
Brand tone standard (brief description): {{BRAND_TONE_STANDARD}}

Caveat: This audit flags candidates — a human should verify any 'Delete' recommendation before removing macros that may be in active use.
Variables to fill in
  • {{MACRO_LIBRARY_TEXT}}
  • {{RECENT_PRODUCT_CHANGES}}
  • {{BRAND_TONE_STANDARD}}

How to use this prompt

  1. Copy the prompt above (Copy button on the top-right).
  2. Replace each {{VAR}} with your own value. Variables: {{MACRO_LIBRARY_TEXT}}{{RECENT_PRODUCT_CHANGES}}{{BRAND_TONE_STANDARD}}.
  3. Paste it into one of the recommended tools below.
  4. 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.

Heads up: some of the links on this page are affiliate links — meaning we may earn a commission if you sign up after clicking, at no extra cost to you. We only recommend tools we'd put on our own stack. You can see our full affiliate disclosure here.

Pair this prompt with a tool

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.