{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/2bc96c7d096e49ecb84f2702f9ccba94\" 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/2bc96c7d096e49ecb84f2702f9ccba94-14a56d19d005a37e.gif","duration":221.929,"title":"Autonomous Agentic Research Framework: High-Fidelity Synthesis &amp; Factual Grounding - 23 January 2025","description":"Developed a sophisticated Planner-Synthesizer Agentic Workflow in Langflow designed for high-fidelity data retrieval.\nLogic: Implemented a dual-node LLM architecture where the primary model acts as a \"Strategic Planner,\" decomposing user prompts into optimized search queries.\nFact-Grounding: Utilized Tavily AI for real-time RAG (Retrieval-Augmented Generation), forcing the agent to ground all claims in live web data and academic sources.\nOutput: Engineered a final synthesis layer that transforms raw search data into professional reports with clickable citations, effectively eliminating LLM hallucinations."}