{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/88aa0ccfabb04b74bc20fa098a20aeb2\" 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/88aa0ccfabb04b74bc20fa098a20aeb2-d66db46ceef7e188.gif","duration":133.712,"title":"Clawback AI Fraud Investigator Copilot for Medicaid","description":"Hi everyone, I’m Vazha and I’m sharing Clawback AI, a fraud investigator co pilot that bridges messy evidence with spending patterns. We parse unstructured PDF evidence instantly using NVIDIA NIM, extracting provider NPI and suspicious billing codes. Then we use DuckDB to run analytical queries against the 3.7 GB Medicaid dataset and compute z scores versus national averages to flag statistical outliers. Our goal is to cut manual Medicaid audits from months to seconds. No direct viewer action was requested in this message."}