{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/635fa15ee7dc43a3a2207c79c7e12837\" frameborder=\"0\" width=\"1662\" height=\"1246\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1246,"width":1662,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1246,"thumbnail_width":1662,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/635fa15ee7dc43a3a2207c79c7e12837-45daf1a0e9f2f69a.gif","duration":1126.4161,"title":"Tax Strategy Proof of Concept","description":"In this video, Farhan and I present a proof of concept for a multi-agent architecture designed to assist with tax strategy recommendations based on client scenarios. We demonstrate how the first agent refines natural language inputs to extract relevant artifacts, which are then used to evaluate various tax strategies. I encourage you to provide feedback on the demo, especially regarding the model's ability to ask pertinent questions and the strategies it suggests. Your insights will be invaluable as we refine this tool for production use."}