video1.0<iframe src="https://www.loom.com/embed/392466d4a2974f8e9008a1104f644c0e" frameborder="0" width="1728" height="1296" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>12961728Loomhttps://www.loom.com12961728https://cdn.loom.com/sessions/thumbnails/392466d4a2974f8e9008a1104f644c0e-1a1dc68faf37ed62.gif176.09This Loom shows how to use Copilot to generate and run simulated end to end test cases for an AI quote intake assistant. In the Test cases tab, Copilot generates four full call path test cases with detailed success criteria, which you can run directly in the tab or ask Copilot to run within the same session. The simulations pass about half, handling existing policy and the full quote flow but failing when the agent reaches the wrong person or transfers to a specialist. Copilot then suggests fixes, updates the agent draft, and reruns simulations to confirm improved specialist transfer, with further iterations as needed.