---
name: al-192-check-a-support-case-s-real-reason-and-draft-a-reply-in-t
description: "Have an agent summarize each incoming case, confirm what the customer is actually asking for, draft the reply in the voice of the brand they contacted, and flag a mismatched case reason before the case is closed. L'Oréal's consumer care advisors use Agentforce this way across 25 brands and handle cases up to 64% faster. Use when the user wants help with multi-brand case handling (customer support) for a small business."
---

# Check a support case's real reason and draft a reply in the right brand voice

Have an agent summarize each incoming case, confirm what the customer is actually asking for, draft the reply in the voice of the brand they contacted, and flag a mismatched case reason before the case is closed. L'Oréal's consumer care advisors use Agentforce this way across 25 brands and handle cases up to 64% faster.

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

- Brand name
- 3-5 bullets, e.g. warm, expert, no slang
- Or 'none'
- Reason
- Your own material (text, notes or data)

## Instructions

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

You are helping a customer care advisor. Brand the customer contacted: [brand name]. Brand voice notes: [3-5 bullets, e.g. warm, expert, no slang]. Approved help articles/policies: [paste]. Customer's order/history: [paste or 'none']. Conversation so far: [paste]. Case reason the advisor picked: [reason]. Step 1: summarize the conversation in 3 bullets. Step 2: state in one sentence what the customer actually wants, and say whether it matches the picked case reason; if not, suggest the better reason. Step 3: draft a reply email in the brand voice using only the approved articles and history above. Step 4: list anything you could not confirm as 'needs advisor check'. Do not invent policies, discounts, or order details, and do not promise refunds or codes the advisor has not approved.

## Safety checks (share these with the user)

- 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.
- Read and edit the draft before it reaches a customer or goes public. If you later automate this prompt, start with "draft and notify me", not "send automatically".
- Check names, dates, numbers and any claim against your own source material before you use the answer. AI can misread or invent details.
- Say clearly which parts need a person to review or approve before anything is sent, paid, posted or filed.

## About this skill

- Works with: Salesforce Agentforce, ChatGPT, Claude, Gemini
- Based on this real-world example: https://www.salesforce.com/customer-stories/loreal/agentic-service-advisor-assistance/
- Free prompt from AgentPlaybook Real Estate: https://agentic-library.netlify.app/prompt/al-192-check-a-support-case-s-real-reason-and-draft-a-reply-in-the/
- 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/