Build a retail shopping-and-service superagent: one orchestrator routes customers to specialist shopper and service agents for discovery, sizing, orders, returns and checkout: AI agent prompt
Salesforce's Nov 3, 2026 customer story describes how Crocs, with Rosetree Solutions and Salesforce forward-deployed engineers, shipped Rivet—an Agentforce retail superagent—in five months. A single orchestrator coordinates specialist shopper and service agents across five launch use cases: product discovery, FAQs, order tracking, returns and conversational checkout, with real-time order/return data from IBM Sterling. The same service actions were reused to launch Agentforce Voice in seven weeks. Federated Data 360 spaces keep Crocs and HEYDUDE brand data separate while supporting shared reporting.
The prompt
Design a retail superagent for [brand] like Crocs Rivet. Channels: [web chat / voice]. First release use cases only: product discovery, FAQs, order tracking, returns, conversational checkout. Architecture: one Orchestrator + Shopper agent + Service agent; list tools each owns (catalog, sizing/fit KB, OMS APIs for status/returns). Guardrails: never invent inventory or refund eligibility; hand off to human when [criteria]. 5-month build plan with a 7-week voice reuse path. Analytics: autonomous resolution rate and FAQ accuracy. Do not claim live production metrics we have not measured.
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, Commerce Cloud and review the answer before you use it.
Works with: Salesforce Agentforce, Service Cloud, Commerce Cloud, Data 360, IBM Sterling OMS
Real-world example: salesforce.com/uk/customer-stories/crocs/building-ai-agents/
Before you use it: what to check
Already built into this prompt
- Do not claim live production metrics we have not measured.
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.
- 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 free