By combining prompt engineering techniques such as chain-of-reasoning and meta-prompting with retrieval-augmented generation (RAG) on the fly, I was able to develop a powerful agent for long-winded, research-intensive tasks. Jar3d has Internet access and makes tasks such as creating newsletters, writing literature reviews, planning vacations, and other research-intensive activities much easier. I will demonstrate Jar3d and explain how it works at a high level. Jar3d is orchestrated using LangGraph.

Need to develop AI? Let's chat: https://www.brainqub3.com/book-online

Register your interest in the AI Engineering Take-off course: https://www.data-centric-solutions.com/course

Hands-on project (building a simple RAG app): https://www.educative.io/projects/build-an-llm-powered-wikipedia-chat-assistant-with-rag

Stay up to date on AI, data science, and large language models by following me on Medium: https://medium.com/@johnadeojo

Jar3d GitHub repository: https://github.com/brainqub3/meta_expert

Research report on meta-prompting: https://arxiv.black/pdf/2401.12954

Professor Synapse: https://github.com/ProfSynapse/Synapse_CoR

Chapter
Introduction: 00:00
Jr3d Demo 02:49
Jar3d Architecture: 18:27
Overview of the Jar3d code: 23:39
Prompt Engineering: 31:45
Jar3d Newsletter Review: 44:20
Strengths & Weaknesses: 58:43

Please take the opportunity to connect with your friends and family and share this video with them if you find it useful.