{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/279b8ee6b075456f9ed247bfe6aa682d\" 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/279b8ee6b075456f9ed247bfe6aa682d-4806168af081a8c0.gif","duration":803.238,"title":"Pet Scheduling AI Assistant Project Demo","description":"In my final project, I built a paid scheduling assistant for pet owners that generates daily pet care plans based on task priority, available time, and conflict checks across multiple pets. Users enter pet and owner info plus tasks like breakfast, lunch, grooming, snacks, and walks, then click Generate Schedule to produce timed tasks and AI care insights. I used Gemini 2.0 Flash for the advisor and a Llama 3.3 fallback, with guardrails and logging. I wrote 42 test cases. I did not request any specific viewer action."}