Customer serviceWorks with ChatGPT, Claude, Gemini
Help centre FAQs from support tickets
Turn a ticket export into the FAQ articles customers actually need (and that AI agents can use).
What you need
- Ticket export (subject and first message) for 1-3 months
- Current FAQ page
- Policies
The prompt
Here is an export of [NUMBER] customer support tickets for [BRAND] and our current FAQ. Tickets: [PASTE] Current FAQ: [PASTE] Policies: [PASTE] 1. Group tickets into intents and rank by volume. 2. For the top 15 intents, say whether the current FAQ answers it well, poorly or not at all. 3. Write new or improved FAQ articles for the gaps: question as customers phrase it, a direct answer first, then details, in UK English, max 150 words each. 4. List policy gaps or contradictions you found. Remove personal data from any examples.
Replace everything in [BRACKETS]. Use a business or team account with training on your data switched off, and remove customer personal data before pasting.
What you get
Ranked ticket intents, an FAQ coverage audit, new FAQ articles and a list of policy gaps.
Tips
- Better FAQs directly improve AI agent accuracy, since most agents answer from your help centre.
The fortnightly brief
Get the brief
New AI tools worth a look, price changes, fresh deals and a real brand use case, for UK consumer brand teams. No spam, unsubscribe any time.