video1.0<iframe src="https://www.loom.com/embed/643e28a7ffea4392a9a512ad41907f7b" frameborder="0" width="1670" height="1252" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>12521670Loomhttps://www.loom.com12521670https://cdn.loom.com/sessions/thumbnails/643e28a7ffea4392a9a512ad41907f7b-878ef4e18310df67.gif283.92This Loom explains how Emmanuel Gauch applies production experience in building AI and automation systems. He discusses the difficulty of moving AI prototypes to production due to changing real-world scenarios, such as different PDF structures and table formats. He highlights his work as head of AI at UNO and his experience building systems in production, including creating mechanisms for Juno, a payment orchestrator that integrates with many providers with varying and inconsistent documentation. He notes that this experience is relevant to the viewer’s similar challenge and mentions building multiple agents and enterprise AI platforms, including in OpenCloud and Hermes.