As Andrew Ng recently noted, "AI agent workflows will drive massive AI progress this year — perhaps even more than the next generation of foundation models."
In line with this pivotal trend, we have organized a series of tools, prompt engineering, and workflow lessons to help you build and implement AI agents through hands-on interaction. These lessons will also allow you to gain experience with leading frameworks like crewAI, AutoGen, Dify, fastGPT, LongChain, LangGraph, Coze, and Agent Universe. Many of these are beginner-friendly, requiring only basic Python knowledge.
Multi AI Agent Systems with crewAI
Taught by João Moura, founder and CEO of crewAI, this course will cover key components of AI agents and how to assign specialized roles to agents and coordinate their efforts for optimal performance.
Using crewAI, an open-source library for building multi-agent systems, you will gain hands-on experience in creating agent teams for processes such as tailoring resumes and preparing for job interviews, researching, writing, and editing technical articles, conducting customer outreach campaigns, performing financial analysis, planning events, and more.
You will design and prompt a team of agents through natural language to automate your business workflows, surpassing the performance of prompting a single LLM.
AI Agents in LangGraph
LangGraph enables developers to create highly controllable agents. In this course, you will learn to build an agent from scratch using Python and an LLM, then rebuild it using LangGraph, understanding its components and how to combine them to build flow-based applications.
Additionally, you will explore agentic search, which returns multiple answers in an agent-friendly format, enhancing the agent’s built-in knowledge. This course will demonstrate how to use agentic search in your applications to provide better data for agents, improving their output.
Building Agentic RAG with LlamaIndex
This course, created in collaboration with LlamaIndex and taught by its co-founder and CEO Jerry Liu, will guide you in building agents capable of intelligently navigating, summarizing, and comparing information across multiple research papers from arXiv. You will also learn how to debug these agents, ensuring you can effectively guide their actions.
Unlike the standard retrieval augmented generation (RAG) pipeline—suitable for simple queries across a few documents—agentic RAG adapts based on initial findings to enhance further data retrieval. In this course, you will use this framework to build research agents skilled in tool use, reasoning, and decision-making with your data.
AI Agentic Design Patterns with AutoGen
This short course, developed in collaboration with Microsoft and Penn State University, is taught by AutoGen creators Chi Wang, Principal Researcher at Microsoft Research, and Qingyun Wu, Assistant Professor at Penn State University.
In this course, you will learn how to build and customize multi-agent systems, enabling agents to take on different roles and collaborate to accomplish complex tasks using AutoGen. AutoGen is a framework that facilitates the development of LLM applications using multi-agents, implementing four agentic design patterns: Reflection, Tool Use, Planning, and Multi-agent Collaboration.
These courses will help you delve deeply into AI agent technology, enhancing your skills in business process automation and intelligent agent development.
TAGS
AI agent workflows, AI progress 2024, Andrew Ng AI predictions, multi-agent systems, AI agent frameworks, crewAI tutorial, LangGraph agents, agentic search technology, LlamaIndex research agents, AutoGen design patterns, Python for AI agents, hands-on AI lessons, business process automation AI, intelligent agent development, prompt engineering AI
Related topic:
The Key Role of Knowledge Management in Enterprises and the Breakthrough Solution HaxiTAG EiKM
Unlocking Enterprise Intelligence: HaxiTAG Smart Solutions Empowering Knowledge Management Innovation
Organizational Culture and Knowledge Sharing: The Key to Building a Learning Organization
HaxiTAG EiKM System: The Ultimate Strategy for Accelerating Enterprise Knowledge Management and Innovation