{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/56158b09dc4046d2b4894e7837b7612d\" frameborder=\"0\" width=\"1078\" height=\"808\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":808,"width":1078,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":808,"thumbnail_width":1078,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/56158b09dc4046d2b4894e7837b7612d-66083ef6251d6f5e.gif","duration":158.2678,"title":"Antler pitch : RAG with LLM ( gemini) Debate between AI and human","description":"I’m building an AI-powered personal agent that combines LLM fine-tuning, Retrieval-Augmented Generation (RAG), and real-time multimodal interfaces to create an interactive, human-like knowledge companion.\n\t•\tThe agent is trained on my professional identity dataset to reflect my expertise, communication style, and decision-making patterns.\n\t•\tIt is RAG-enabled with curated datasets from the battery electric vehicle (EV) and automotive industry, making it highly domain-aware and capable of delivering context-rich insights.\n\t•\tThe interaction layer uses voice synthesis (via ElevenLabs) and real-time avatar animation, enabling the agent to converse naturally with humans, presenting knowledge and insights as if you were engaging with me directly."}