Free account
Read this concept with a free account
Read this concept at no cost by signing in with Google.
no card needed
Core
Human Handoffs: Escalating From AI to People Without Losing the Customer
Handoffs from AI to people decide much of how customers remember AI-assisted experiences. This guide covers escalation triggers, the trade-off between missed and unnecessary escalations, the structured context a human should receive, the customer-facing experience, and how to measure and tune handoffs.
CONCEPT / DESIGNING FOR UNCERTAINTY
RELATED CONCEPTS
PRACTISE THIS CONCEPT
Agentic ProductsWhen should our banking agent hand a conversation to a human, and what should the human receive?→AI UX & Human-in-the-LoopOur agent proposes 40 changes to a customer's CRM records at once. Design approval so people review carefully without it becoming a chore.→Agentic ProductsOur agent currently needs human approval for every action. How do you decide when to let it act on its own?→Evals & Launch DecisionsYour support agent completes 82% of tasks in testing. Is it ready to launch?→Agentic ProductsYour team wants to build an AI agent to onboard new suppliers. Should it be an agent, or something simpler?→Agentic ProductsWhat's the difference between a chatbot, an AI workflow and an AI agent?→