<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/03949c1aea5d42e5b111a560a797fdaf&quot; frameborder=&quot;0&quot; width=&quot;1096&quot; height=&quot;822&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>822</height><width>1096</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>822</thumbnail_height><thumbnail_width>1096</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/03949c1aea5d42e5b111a560a797fdaf-225ae8869009af00.gif</thumbnail_url><duration>311.169</duration><title>Visual Studio Code - llm_patient.py - Pretty-GoodAI-Chatbot - Visual Studio Code - 26 February 2026</title><description>In this video, I walk you through how I built an automated patient caller using FastAPI and Twilio for the PrettyGoodAI chatbot assessment. I demonstrate the application setup, including making test calls and handling conversation flow to avoid confusion between my bot and the demo bot. I also explain how I implemented a prompt script for OpenAI to facilitate more natural conversations based on different scenarios. Additionally, I address call status management to prevent looping calls. Please take a look at the implementation details and let me know if you have any questions!</description></oembed>