video1.0<iframe src="https://www.loom.com/embed/ed62ee967f4b4fae96a3f97773e6df4e" frameborder="0" width="1920" height="1440" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>14401920Loomhttps://www.loom.com14401920https://cdn.loom.com/sessions/thumbnails/ed62ee967f4b4fae96a3f97773e6df4e-841adbdd798dcc69.gif729.157I’m presenting my PowPal AI powered Pit Care Planner. It started as a Python class model for an Owner Pit Task Scheduler, then I added agentic workflow so the system can validate, rank, schedule, explain tasks, and assign a confidence level. The architecture uses app, agent, schedule, evaluation, and testing layers, and it detects conflicts against owner availability and constraints. In the demo I created an owner with availability from 8 to 12 p.m, entered multiple pits and tasks, then generated a daily schedule with 55 unit tests passing, edge case handling, and performance metrics. I did not request any action from viewers.