Audit intermediate Works with: Any AI

Canned Response Library Audit: Tone, Accuracy and Overuse

Table output

Review saved replies for staleness and stiffness.

The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.

[VERIFY] is an editorial flag, not a blank to fill. Wherever the prompt shows [VERIFY], check that item against a reliable source before you use it.

Rate this prompt

Loading ratings…

Audit our canned responses. The library of saved replies with titles and text: [CANNED_RESPONSES]. How often each is used if known: [USAGE_COUNTS]. Policies and product details that changed recently: [RECENT_CHANGES].

Check each reply for accuracy against the current policies I give, clarity, tone, length, personalisation points, links that may be stale, and whether it asks the customer for information we already have. Make a table with Reply, Used, Problems, Action (keep, edit, merge, retire), and Rewrite. Identify duplicates and conflicts between replies. Count how many need action with the arithmetic. Provide guidelines for writing a template (placeholders for names, a first sentence that responds to the customer's situation, one next step) and a review schedule with an owner for each reply.

Do not invent policy details. Mark gaps as [VERIFY].

Add a worked rewrite of a stiff template ('Your request has been received and will be processed in due course') into a human version ('Thanks, we have your request and a person will reply by Thursday'), and a rule for placing the next step and a date in the first two sentences.

Fill in before use

Optional: type your details and the prompt above updates. Nothing is saved or sent.

Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.

Related prompts