How this AI Agent Uses LangGraph & Prompt Engineering to Challenge Perplexity (Deep Dive)

How this AI Agent Uses LangGraph & Prompt Engineering to Challenge Perplexity (Deep Dive) Jar3d is an open-source AI agent that rivals Perplexity and other search agents in conducting deep research tasks. This agent leverages advanced AI engineering techniques, including: Meta-prompting, Retrieval-Augmented Generation (RAG), Sophisticated prompt engineering, and LangGraph for orchestration. These techniques enable Jar3d to perform complex, research-intensive tasks that require gathering and synthesizing information from the internet over extended periods. This video provides a technical deep dive into Jar3d's inner workings. We'll explore how the combination of LangGraph and advanced prompt engineering empowers this versatile agent to challenge established search agents like Perplexity. By the end of this presentation, you'll have a comprehensive understanding of how Jar3d pushes the boundaries of AI-driven research capabilities. Need to develop some AI? Let's chat: https://calendly.com/john-brainqub3/30min Register your interest in the AI Engineering Take-off course: https://www.data-centric-solutions.com/course Hands-on project (build a basic RAG app): https://www.educative.io/projects/build-an-llm-powered-wikipedia-chat-assistant-with-rag Stay updated on AI, Data Science, and Large Language Models by following me on Medium: https://medium.com/@johnadeojo GitHub repo for Jar3d: https://github.com/brainqub3/meta_expert Runpod Template for Llama 3.1:https://runpod.io/console/deploy?template=rl059hhfas&ref=x5fziojy Meta Prompting Research Paper: https://arxiv.black/pdf/2401.12954 Check out professor synapse for the original chain of reasoning implementation. GitHub Repo: https://github.com/ProfSynapse/Synapse_CoR Chapters Introduction: 00:00 Architecture: 00:01:58 Prompt Engineering: 00:12:58 Code Run-through: 00:33:21 Agent Demo: 01:05:37 Reflections: 01:39:23