Description: Human-Driven Multimodal Systems are technological platforms that integrate multiple forms of interaction, such as text, voice, images, and gestures, prioritizing human input and feedback in their processes. These systems are designed to enhance user experience by allowing for more natural and fluid communication, adapting to individual preferences and needs. Their architecture is based on the combination of different modalities, enabling users to interact in a more intuitive and effective manner. The relevance of these systems lies in their ability to facilitate the understanding and processing of complex information, as well as their potential to be applied in various fields, from education to healthcare and customer service. By focusing on human interaction, these systems aim not only to optimize functionality but also to enrich the user experience, fostering more effective collaboration between humans and machines.