Audit intermediate Works with: Any AI

Help Center Article Audit: Findability, Accuracy and Steps That Work

Table output

Review help articles against real customer questions.

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 help centre. The article titles and text for a sample of articles: [ARTICLES]. The top customer questions from support tickets: [TOP_QUESTIONS]. Search terms customers use if known: [SEARCH_TERMS].

Match each top question to an article and rate: does an article exist, is the title the way customers phrase it, does the first paragraph answer the question, are steps numbered and correct for the current product (mark steps I should test [VERIFY]), are screenshots described and up to date, and is there a clear next step if it does not work. Make a table with Question, Article, Rating, Problem, and Fix. Count questions without an article and articles that no question maps to, with the arithmetic. Suggest merges, retitles, and five new articles. Propose a review calendar and a metric (tickets per article view) that I can track.

Do not assume product behaviour; ask me to verify.

Add a worked mapping of five questions to articles with a rating and a rewrite of one title from 'Account configuration' to 'How to change your email address'. Include a test routine: follow each article's steps on a fresh account and note where the screen differs.

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