{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/13c148d5d6b04905a5d80b3a46f57664\" 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/13c148d5d6b04905a5d80b3a46f57664-e38974d97ecfe711.gif","duration":82.997,"title":"Personal Presentation","description":"This Loom describes Norman’s work building an AI agent platform for automated lead outreach across phone calls, text, and email. He focuses on keeping voice latency low so live phone calls feel natural, using Node.js, TypeScript, React, and LiveKit for streaming. He says the team reduced response times to under 2 seconds, eliminating the need for mono follow-ups. He also mentions previously refactoring a legacy XML data pipeline over PostgreSQL JSONB to simplify the setup and save $1,500 per month in third-party tooling."}