{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/e224390511394ccba92d204606c114a5\" frameborder=\"0\" width=\"1920\" height=\"1440\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1440,"width":1920,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1440,"thumbnail_width":1920,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/e224390511394ccba92d204606c114a5-5576e4e310b05974.gif","duration":905.104,"title":"Part 1","description":"Hi everyone, I'm Srikar, and in this video, I'm demonstrating the AI wash scheduling agent I built for my assignment. I decoupled the architecture into a voice layer using WAPI with DeepGram for transcription and GPT-4 for NLP, and a FastAPI back-end deployed on Render. Key features include slot-filling and rescheduling options, which I showcase in a demo where I book and then reschedule a meeting. You can find the full source code and more details on my GitHub repository. I appreciate your time and look forward to connecting with the team soon!"}