---
name: al-683-give-appliance-support-reps-an-in-service-cloud-ai-assist
description: "Salesforce's Nov 3, 2026 Fisher & Paykel customer story describes Arthur, an internal Agentforce assistant inside Service Cloud. When a customer calls about something like a dishwasher that won't drain, the rep asks Arthur instead of leaving the case: it uses the exact model for step-by-step troubleshooting, identifies spare parts and pricing, and can summarise recent cases, appointments, orders and sentiment. Arthur searches more than 100 million CRM records in Data 360, 10,000-plus Knowledge articles and 100GB+ of manuals in Amazon S3 with hybrid RAG, only from approved sources, and can draft personalised follow-up emails. Reps gave it 75% positive feedback; hold times and transfers fell. Use when the user wants help with in-crm appliance expertise agent for reps (customer support) for a small business."
---

# Give appliance support reps an in-Service-Cloud AI assistant that pulls model-specific manuals, customer history and spare-part numbers so they stop putting callers on hold

Salesforce's Nov 3, 2026 Fisher & Paykel customer story describes Arthur, an internal Agentforce assistant inside Service Cloud. When a customer calls about something like a dishwasher that won't drain, the rep asks Arthur instead of leaving the case: it uses the exact model for step-by-step troubleshooting, identifies spare parts and pricing, and can summarise recent cases, appointments, orders and sentiment. Arthur searches more than 100 million CRM records in Data 360, 10,000-plus Knowledge articles and 100GB+ of manuals in Amazon S3 with hybrid RAG, only from approved sources, and can draft personalised follow-up emails. Reps gave it 75% positive feedback; hold times and transfers fell.

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

- Appliance / hardware / product
- CRM cases, Knowledge articles, S3/PDF manuals
- Your own material (text, notes or data)

## Instructions

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

Design an internal Agentforce-style assistant for [appliance / hardware / product] support reps inside our CRM. Product lines: [list]. Knowledge sources: [CRM cases, Knowledge articles, S3/PDF manuals]. Hard rules: search only approved sources; always ground answers in the customer's exact model/serial; never invent a part number; escalate to Technical Advisory when confidence is low; draft follow-up emails for the rep to edit, never send without approval. 1) List the top 8 questions reps ask mid-call. 2) For each, write the retrieval plan (which systems, what filters). 3) Draft the agent system prompt and three example dialogues (drain issue, spare part, warranty). 4) Define success metrics (hold time, transfer rate, thumbs-up). Output as a one-page build brief I can hand to our CRM admin.

## 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.
- 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.
- 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".
- 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, Service Cloud, Data 360, Amazon S3, ChatGPT, Claude
- Based on this real-world example: https://www.salesforce.com/eu/customer-stories/fisher-and-paykel/agentic-service-rep-assistance/
- Free prompt from AgentPlaybook Real Estate: https://agentic-library.netlify.app/prompt/al-683-give-appliance-support-reps-an-in-service-cloud-ai-assistant/
- 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/