Our online interactions include audio, video, and sensor data, but most AI applications are still focused on text. This episode of Utilizing Tech considers how we can integrate multimodal data with agentic applications with Vishakha Gupta, founder and CEO of ApertureData, Frederic Van Haren of HighFens, and Stephen Foskett of Tech Field Day. After decades of developing AI models to process spoken word, images, video, and other multimodal data, the ascendance of large language models has largely focused on text. This is changing, as AI applications are increasingly leveraging multimodal data, including text, audio, video, and sensors. Many agentic applications still pass data as structured or unstructured text, but it is possible to use multimedia data as well, for example passing a clip of a video from agent to agent if the system has true multimodal understanding. Enterprise applications are moving beyond text to include voice and video, data in PDFs like charts and diagrams, medical sensors and images, and more.

Guest:
Vishakha Gupta, CEO and Founder, ApertureData