{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/d23b0bcba54b460ca5924752a40aeb2d\" frameborder=\"0\" width=\"1908\" height=\"1431\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1431,"width":1908,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1431,"thumbnail_width":1908,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/d23b0bcba54b460ca5924752a40aeb2d-56a976dc34536fb5.gif","duration":366.699,"title":"AI Pet Scheduling Assistant Fixes Conflicts 🐾","description":"Hi, I am Simon, and I am demoing my final project POPL plus, an AI powered pet scheduling assistant. I extended the original POPL project with an agentic workflow that detects scheduled conflicts and calls an LLM to propose fixes, deciding whether to auto apply or ask the owner first based on risk. I show multiple scenarios, including one with no scheduling conflicts and others that trigger medication and walk changes. I also mention a test harness script that passed eight tests across conflict detection, risk scoring, and auto fix decisions. No action is requested from viewers."}