<?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/56158b09dc4046d2b4894e7837b7612d&quot; frameborder=&quot;0&quot; width=&quot;1078&quot; height=&quot;808&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>808</height><width>1078</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>808</thumbnail_height><thumbnail_width>1078</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/56158b09dc4046d2b4894e7837b7612d-66083ef6251d6f5e.gif</thumbnail_url><duration>158.2678</duration><title>Antler pitch : RAG with LLM ( gemini) Debate between AI and human</title><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.
	•	The agent is trained on my professional identity dataset to reflect my expertise, communication style, and decision-making patterns.
	•	It 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.
	•	The 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.</description></oembed>