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: AI agent prompt
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.
The prompt
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.
Fill in the blanks, then copy
This prompt has 3 [bracket]s to fill in. Type your details below and the prompt updates as you go. Your answers stay in this browser and are reused on other prompts with the same blanks. Nothing is sent to us.
Example values are fictional, just to show how a filled-in prompt reads. Replace them with your real details.How to use it
- Copy the prompt above.
- Replace every [bracket] with your own details (use the fill-in-the-blanks box above, which remembers your answers for the next prompt).
- Paste it into Salesforce Agentforce, Service Cloud, Data 360 and review the answer before you use it.
Works with: Salesforce Agentforce, Service Cloud, Data 360, Amazon S3, ChatGPT, Claude
Real-world example: salesforce.com/eu/customer-stories/fisher-and-paykel/agentic-service-r
Featured in: ChatGPT prompts for business email, replies and follow-ups · AI prompts to summarize meetings, notes, documents and reports
Before you use it: what to check
Check yourself
- 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".
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 →