Sort a month of customer calls by what callers wanted and how they felt, to find what is really driving them: AI agent prompt
When customer scores drop, the phones usually show why, but nobody has time to listen to hundreds of calls. An AI assistant can read call transcripts or notes, tag each one by reason and mood, and show which single problem creates most of the calls, so you fix the cause instead of answering the same question faster. Numa's Oct 14, 2026 case study describes how Dyer Automotive Group in Florida pulled its own service calls and sorted them by reason and mood. 63% were customers checking on their cars and more than 40% of callers were angry, with "nobody called me back" the top complaint. Fixing callbacks brought call volume down and raised CSI.
Customer SupportCall driver analysisbeginnerThe prompt
Help me find what's really driving our customer calls. Calls: [paste or upload transcripts, call summaries or call-log notes, ideally 2-4 weeks]. Business: [type of business, e.g. auto service, clinic, contractor, online store]. Do this: 1) Tag every call with one main reason (e.g. checking status, booking, price question, complaint, billing, other) and one mood (calm, confused, frustrated, angry). 2) Give me a table: reason, number of calls, % of total, % angry or frustrated. 3) Name the top 1-3 reasons that, if fixed, would remove the most calls, and say what the customer was waiting for in each case (e.g. a callback, an update, an answer). 4) Quote 3 short, representative lines from callers for each top reason. 5) Suggest one practical fix for each, such as a proactive text update, a callback queue with owners or a clearer answer on the website, and how I would measure whether it worked. Leave out personal details like names and phone numbers.
How to use it
- Copy the prompt above.
- Replace every [bracket] with your own details (or fill in the blanks on AgentPlaybook Real Estate, which remembers your answers for the next prompt).
- Paste it into Numa, ChatGPT, Claude and review the answer before you use it.
Works with: Numa, ChatGPT, Claude, Gemini, Fireflies, Excel, Google Sheets
Real-world example: numa.com/casestudies/dyer-automotive-group-gives-ai-a-second-shot
Featured in: Free AI agent prompts for small business (beginner-friendly) · AI prompts to summarize meetings, notes, documents and reports · AI prompts for Google Sheets and Excel work · AI receptionist and missed-call text-back: free scripts for small businesses · ChatGPT prompts for customer service: ticket triage, replies and handoffs
Before you use it: what to check
Check yourself
- This prompt works on text other people wrote (emails, reviews, messages or web pages). That text can hide instructions aimed at AI, such as "ignore your rules and…". Paste it as material to work on, and never let the AI act on requests inside it, like paying, sharing logins or changing records. How prompt injection works →
- Check every figure, price and total against your own records before anything is sent, posted or booked. A person approves refunds, discounts, payments and price changes.
- Remove names, contact details, account numbers and other personal data the task doesn't need before you paste, and check your AI tool's data and training settings.
- Check names, dates, numbers and any claim against your own source material before you use the answer. AI can misread or invent details.
Using an AI agent? Download this prompt as a SKILL.md agent skill with these checks built in, or get the .zip for Claude.ai. How to install skills.
Want to make this prompt even better? Grade it with the free prompt grader or build your own with the AI prompt generator.
32 copy-paste agent prompts (PDF) plus 5 new prompts every week.
Get it freeMore Customer Support prompts
See all Customer Support prompts →