ServiceNow Ticket Categorisation Quality and Reporting Accuracy Audit
Check whether categories support reliable reports.
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.
Audit classification quality. Sample of 100 tickets with category, subcategory, short description and resolution notes: [TICKET_SAMPLE]. State the sample size and method so someone else can repeat it: two reviewers independently classify the tickets from the description and resolution, then compare. Compute agreement as matching divided by 100 and count tickets in other or miscellaneous categories and categories with very few tickets. Group disagreements into causes: overlapping definitions, missing categories, and agents choosing the first option. Explain how misclassification distorts reports, such as understating access requests, and set a target agreement level. Propose a simplified category list with a one-page guide of examples and training. Return a table and a plan. Names of fields and features vary by release and set-up; flag what you cannot confirm [VERIFY] instead of presenting it as fact. Keep the guide to one page with three examples per category, and state which categories you would merge first. List the reports that would change if the categories were corrected, so the owners can be told.
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.