---
name: al-122-spot-product-complaints-hidden-in-collection-calls
description: "Transcribe payment-collection calls and replies, pull out anything a team should act on (a defective product, a warranty claim) and send it to that team, like the two Make agents a Bemol collections analyst built that now cover 100,000+ calls a month. Use when the user wants help with voice of the customer (customer support) for a small business."
---

# Spot product complaints hidden in collection calls

Transcribe payment-collection calls and replies, pull out anything a team should act on (a defective product, a warranty claim) and send it to that team, like the two Make agents a Bemol collections analyst built that now cover 100,000+ calls a month.

## Inputs to collect first
Ask the user for anything below that they haven't already given you. Don't guess missing facts.

- Or connect transcripts
- Warranty / delivery / support / collections

## Instructions

Do the task below with the user's inputs in place of each [bracket].

You review our payment-collection conversations. Here are today's call transcripts and customer text replies: [paste or connect transcripts]. For each one, find anything another team should act on, for example a product defect, a warranty issue, a delivery problem, or a customer who needs a human reply. For each issue give: customer name/ID, a one-line summary, a short quote from the customer, which team should handle it ([warranty / delivery / support / collections]) and how urgent it is. Skip conversations with nothing to act on. Put the results in a table I can forward to each team. Don't contact customers yourself.

## Safety checks (share these with the user)

- 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.
- 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.
- Anything legal, tax or compliance-related is a first draft for a qualified person to check. It is not professional advice, and clause references and deadlines must be checked against the source.
- 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.
- Say clearly which parts need a person to review or approve before anything is sent, paid, posted or filed.

## About this skill

- Works with: Make, Whisper, ChatGPT
- Based on this real-world example: https://www.make.com/success-stories/make-bemol
- Free prompt from AgentPlaybook Real Estate: https://agentic-library.netlify.app/prompt/al-122-spot-product-complaints-hidden-in-collection-calls/
- To install in an agent that supports Agent Skills, save this file as SKILL.md in a folder with the same name as `name` above (for example in your skills directory). Install steps for Claude.ai, Claude Code, Cursor and Codex: https://agentic-library.netlify.app/skills/