{"slug":"pandora-builds-ai-shopping-agent-gemma-and-service-agent-clara-with-agentforce","url":"https://findausecase.com/use-cases/pandora-builds-ai-shopping-agent-gemma-and-service-agent-clara-with-agentforce","title":"Pandora Builds AI Shopping Agent Gemma and Service Agent Clara with Agentforce","description":"Jewelry brand Pandora built two Agentforce AI agents: Gemma, a personal shopper that reasons across Commerce Cloud order history, Bloomreach recommendation data and Databricks insights via Data 360 to make tailored jewelry recommendations in a warm, in-store-like tone, and Clara, a customer service agent built with Salesforce Professional Services and Publicis Sapient that answers \"Where is my order?\" requests and FAQs, deflecting 60% of cases.","company":"Pandora","industry":"Retail","country":"Denmark","aiCapabilities":["Conversational AI","Agentic AI","Generative AI"],"businessFunctions":["Customer Service & Support","Sales"],"technology":["Agentforce","Data 360","Commerce Cloud","Service Cloud","MuleSoft"],"deployment":"Public Cloud","problemStatement":"In 2024, Pandora's team of 500-600 service specialists managed a considerable volume of inquiries via email, web and live chat; manually responding could slow response times and lead to longer queues, and peak holiday demand overwhelmed capacity even with seasonal support staff. A traditional chatbot could assist with \"Where is my order?\" requests but its rigid, transactional conversation style didn't match Pandora's warm, personalized service.","solutionApproach":"Pandora built Gemma, a personal shopper agent on Agentforce, which asks shoppers about the occasion, recipient and budget, then draws on customer order history and product information from Commerce Cloud, recommendation data from Bloomreach, and unstructured insights like mystery shopping and UX research stored in Databricks via Data 360 to surface tailored, story-driven recommendations in Pandora's distinctive tone. Separately, built in collaboration with Salesforce Professional Services and Publicis Sapient, Clara is a customer service agent that taps order information from Service Cloud and Commerce Cloud (fed by Pandora's IBM Sterling order management system via MuleSoft) to answer order-status and FAQ requests in conversational language, handing off to a human rep with a conversation summary when a request goes beyond what it can handle.","businessValue":"Clara is already handling 45K conversations a month, deflecting 60% of cases, and a net promoter score increase of 10% indicates that customers are more satisfied with the service they're receiving. Commerce Cloud handles 22% of Pandora's total sales.","evidence":{"band":"high"},"sourceUrl":"https://www.salesforce.com/customer-stories/pandora/","dates":{"publishedAt":"2026-10-08T05:45:55.899Z","publishedAtSource":"pipeline","updatedAt":"2026-10-08T05:45:55.899Z"},"license":"Open for reading and citing with a link to https://findausecase.com/use-cases/pandora-builds-ai-shopping-agent-gemma-and-service-agent-clara-with-agentforce. Bulk republication requires permission."}