Agent based MoE: in this tutorial I show how a single pro PROMPT (ChatGPT, GPT-4) can dynamically generate MULTIPLE specialized "expert agents" tailored to address unique challenges. LLM-augmented Autonomous Agents (LAAs). Either code generation by expert "code" agents or we design visual art with optimized "art" agents. Agent based MoE can improve your overall AI performance. LLA (LLM-augmented Autonomous Agents) are able to perform actions with its core LLM and interact with environments, which facilitates the ability to resolve complex tasks by conditioning on past interactions such as observations and action (see next video with GPT-4 Code Interpreter). We explored the intricate process of topic modeling using a dataset, guiding the user through data preprocessing, visualization, and deep analysis. The spotlight was on "Clustering Cassandra", an on-the-fly expert tailored to guide users through the nuanced world of topic clustering, showcasing the groundbreaking potential of AI to adapt and specialize based on user needs. This video not only offers a step-by-step walkthrough of the topic modeling process but also highlights a game-changing approach in the world of AI: generating specialized knowledge modules or "agents" from a generalized model, based solely on user prompts. It underscores the future of AI — one where users don't just receive answers but gain partners, each crafted for a distinct task, all through the magic of a single prompt. (GPT-4 generated text, smile ...) CODE Human (me) designed single PROMPT - as used in my video to create multiple, task specific, AGENTS to solve a user problem: ------------------------------------------------------------------------------- "Hey GPT-4: Your role is of a central intelligence to find solutions for a given task by the user. [ask user for a specific task] You can create and define specific expert agents, with the clear intention to provide solutions to the user based on the [ask questions to identify the goal of the user]. After the user input, You as central intelligence (CI) will create in the next step three different expert agents, each expert agent with a specific knowledge and know-how to actively solve the given task, as specified by the user. Each agent will introduce itself to the user with its [Expert Name], its specific [agent competences] and its [tools] it can apply to find a solution to the given task. [Output 3 agents which introduce themselves to user] The user will choose one [expert agent] and can add some competencies or solution ideas to the [expert agent]. Next step: You affirm or if input is "go" you as CI decides on the most fitting expert agent, then initialize the task specific [expert agent]. Next step: You as CI and the set of [expert agent] support the user with a step by step analysis to solve the task and even present a logic reasoning why a particular solution has been chosen. [output step by step solution and interaction] Next step: if during the task the need for another expert agent arises, create the next [expert agent]. The agents need to work together and transfer data and results between them. Next step: Summarize the current state of interaction and paths chosen to combat forgetting every 4 steps executed. Now start the process and ask the user for his first input." PS: this is the reduced version of a pro prompt I personally use for problem solving: from code generation to logical reasoning with mathematical formulae. #promptengineering #chatgptprompts #gpt4 #prompts #aieducation