Suggested Response Generation

AI drafts suggested replies and conversation summaries for customer support agents.

Business impact

• Turnaround time — Merck reports that the workflow reduces turnaround time.
• Effort required per case — Fujitsu reports a vendor-published test result of about 80% effort reduction.

Data requirements

• Customer conversation data (text) — Fujitsu uses translated support-desk data and processes from its Japanese Salesforce support desk.
• Support desk process content (text) — The system works from prior support interactions and response content.
• Unsolicited questions from healthcare professionals (text) — Merck's workflow handles questions about Merck products.

AI methods and techniques

• Suggested response generation — The system drafts reply text for an agent to review and use.
• Conversation summarization — It produces summaries of customer conversations for faster context transfer.
• Multi-agent workflow orchestration — Merck describes a multi-agent web application that supports drafting and updating response documents.

Industries

Real-world evidence

2 documented case studies on record.

Companies using this: Fujitsu, Merck.