Find the top ticket drivers and how to reduce them
A contact-driver analysis that shows why customers write in and which tickets to prevent, deflect, or automate.
The prompt
Help me analyze why customers contact support and which contacts we can eliminate.
Ticket data: [PASTE an export or summary: category/tag, count, handle time, channel - or a sample of ticket subjects]
Time period: [DATES]
Total volume and team size: [NUMBERS]
Self-service we already have: [help center, chatbot, in-app guides, status page]
Known tagging problems: [e.g. "30% tagged 'other'"]
Do this:
1. Group tickets into contact drivers: the underlying reason the customer needed help, not just the tag. Re-categorize "other" or vague tags from subjects if I provided them.
2. For each driver, show volume, share of total, and estimated agent hours (volume x handle time).
3. Classify each driver as:
- Prevent: a product, billing, or process fix would remove the need to contact us.
- Deflect: a better help article, in-app message, or proactive notice would answer it.
- Automate: a bot, form, or self-serve action could handle it end to end.
- Keep: it genuinely needs a human.
4. Estimate the hours saved for the top 5 opportunities, with assumptions stated.
Return a table (Driver | Volume | % | Agent hours | Action type | Specific fix | Owner team), then the top 3 recommendations with a one-paragraph case for each. Flag where the data is too thin to trust.
Highlighted [brackets] are blanks to replace with your own details.
Fill in the blanks and use this promptMore Customer Support prompts
What to fill in
- DATES
- NUMBERS
- help center, chatbot, in-app guides, status page
- e.g. "30% tagged 'other'"
How this prompt is built
This prompt follows the RTF structure (Role, Task, Format). RTF tells the model who to be, what to do and what shape the answer should take. It is the quickest structure that still gives noticeably better results than a bare request.
Related prompts
- Respond to an angry customer and de-escalateDe-escalates an upset customer, owns the issue, and offers a concrete resolution.
- Improve my customer service operationA plan to improve service quality, speed, and efficiency across channels.
- Respond to a guest who reports food poisoning or illnessA careful response, internal investigation checklist, and record-keeping steps after a foodborne illness complaint.
- Update support and chatbot content for a product changeFind every answer, article, and macro a product change affects, and get the rewritten content and a rollout checklist.