Self-Service Deflection Audit
Check whether help content reduces contacts.
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 self-service effectiveness. Monthly ticket volumes by topic, help article views for the same topics and satisfaction ratings: [DEFLECTION_DATA]. Contact form and chatbot flow: [CONTACT_FLOW]. Product release dates: [RELEASE_DATES]. Compare article views with tickets by topic to find topics where customers read the article and still contact us, topics with high tickets and low views, and flows that hide the contact option. Be careful not to treat reduced contact as success if customers gave up. Return a table with Topic, Views, Tickets, Reading and Action, a score from 1 to 10 for self-service health, and a plan to improve the three worst topics. Also suggest how to ask customers after reading an article whether it solved their problem, and how to treat a drop in tickets cautiously when the cause might be a hidden contact link. Add a quarterly review of the ten topics with the worst combination of views and tickets. Then plan a content programme to reduce avoidable contacts without hiding the contact route. List the top ten contact reasons by volume and, for each, define the article or tool that could answer it, the owner, the date, and the measure of success such as fewer contacts and a higher resolved rating. Provide a template for a help article designed to answer a specific ticket reason, with title, summary, steps, troubleshooting and next step. Design a contact form that suggests relevant articles as the customer types, while keeping a clear route to a person. Describe how to test articles with five customers or colleagues. Add a monthly dashboard with article views, searches without results, contacts per topic and satisfaction. Explain how to avoid counting customers who gave up as deflected, for example by surveying them. Customer privacy rules for survey and analytics are [VERIFY]. End with advice on how to communicate the findings kindly to the people responsible, focusing on the work and not the individual, and on what support they may need.
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.