Intercom, a customer support platform provider, today launche Fin AI Copilot, an artificial intelligence assistant for customer service agents.
Intercom Fin AI Copilot uses retrieval augmented generation (RAG) and semantic search to generate answers for support agents via internal knowledge and internal and external sources like help centers, public URLs, conversation history, and more. It includes strong guardrails against hallucinations and can be configured to ensure that only select content and conversations are used to generate answers. Agents can expand replies, rephrase answers, or change the tone of answers, and Fin AI Copilot retains the context from the entire conversation with so the agent can ask Fin follow-up questions later
Initial beta testing has shown a 31 percent efficiency gain for agents, who previously spent up to 73 percent of their time sifting through internal content to find answers, according to Intercom data.
Fin AI Copilot follows the launch of Intercom's Fin AI Agent, which has already handled more than 8 million customer queries in 45 languages, saved 670,000 hours of work for support teams, and is resolving up to 80 percent of customer queries, according to the company.