Crocs shoppers get a chat agent for returns and checkout
Crocs built Rivet, a retail agent on Agentforce, from concept to customer-ready in five months. It launched with five use cases: product discovery, FAQs, order tracking, returns and conversational checkout.
- Agent or tool
- Rivet (Agentforce)
- Topic
- Shopping
- Reported on
- Case study (Salesforce)
- Added
- 2026-10-29
Why it matters
Comparing products, prices and delivery options is slow work for a human and fast work for an agent. Cases like this show agents doing the legwork before anything gets bought. It is one of 67 sightings filed under Shopping on Agent Sightings (number 60 by interest), and one of 1 involving Rivet (Agentforce).
How you could try it
Here is a reusable prompt, written by us in our own words, that captures the task. Paste it into Rivet (Agentforce) or any similar agent and adjust the details to your situation.
Act as a shop assistant on our store. Help visitors find a product, answer FAQs, check where an order is, start a return, and check out in chat. Hand over to a person when you are unsure.
The prompt breaks down into 3 steps you can check as the agent works:
- Act as a shop assistant on our store.
- Help visitors find a product, answer FAQs, check where an order is, start a return, and check out in chat.
- Hand over to a person when you are unsure.
Tip: Ask the agent to stop before checkout and show you the final basket, price and delivery date before you confirm.
Source
Read the original first-hand account on Case study (Salesforce): https://www.salesforce.com/customer-stories/crocs/building-ai-agents/. Our summary is a paraphrase; details are in the source.
Featured in these guides
Built an AI agent? Feature your agent on Agent Sightings, free submission or a featured spot.