video1.0<iframe src="https://www.loom.com/embed/5b9e27b7ef714b50a56305cb84430b84" frameborder="0" width="1280" height="960" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>9601280Loomhttps://www.loom.com9601280https://cdn.loom.com/sessions/thumbnails/5b9e27b7ef714b50a56305cb84430b84-fe10adebf60b7dbb.gif162.366667This Loom explains why every dynamic variable in an agent prompt should include a fallback mechanism. It contrasts prompt A, where unresolved placeholders for current date and time, next appointment, and account balance cause the agent to read variable names, making the conversation sound robotic. It then shows prompt B with fallback responses for each dynamic variable so the agent says something else when values fail. The video demonstrates the improved spoken flow when current time, next appointment, and account balance cannot be resolved at runtime.