DAIR.AI

COURSE OVERVIEW

This course focuses on building effective and complex AI agents. Students will learn the fundamental building blocks for creating AI agents and the best practices for constructing advanced agent-based workflows. The course also covers advanced concepts such as building multi-agent and hierarchical multi-agent systems. 

After completing the course, students will have a solid understanding of AI agents and how to develop an effective framework for building advanced agentic AI systems for different domains and problems. 

PREREQUISITES

This course doesn't have any prerequisites and doesn't require programming. If you are not familiar with prompting techniques for LLMs, we strongly recommend completing both the Introduction to Prompt Engineering and Advanced Prompt Engineering courses (also available to all Pro members).

The main tool you will use is Flowise AI (a no-code tool to build chat flows and agentic workflows), therefore, no programming is required. More details and instructions about how to access and install Flowise AI are provided in the course.

TOPICS

Throughout the course, students will utilize Flowise AI, a no-code tool that simplifies the process of developing complex agent-based workflows. 

Key concepts covered in the course include:

• AI Agent Definitions: AI agents are LLM-powered systems capable of performing tasks on a user's behalf. They excel at resolving broad and complex problems by leveraging planning, reflection, tool access, and memory.
• Agent Components: AI agents consist of tools, memory, and planning components to effectively execute tasks. They are especially valuable for solving complex tasks that involve multiple steps, looping, or numerous iterations. Students will learn about the different components and how to build effectively with them. 
• ReAct Agent: An important concept for building powerful AI agents is known as ReAct. Students will learn the key ideas behind ReAct and how to build a simple ReAct agent. 
• Agentic Workflows: Agentic workflows employ AI agents to automate complex tasks such as scientific discovery, research, coding, marketing, content design, and planning. The LLM serves as the agent's central operator, referred to as the agent's "brain." 
• Flowise AI Agentic workflows: Flowise AI, a no-code tool, offers a sophisticated framework for building advanced agent-based workflows. It integrates features from LangChain and LlamaIndex, enabling seamless prototyping and module iteration. Students will use Flowise AI to build their first search agent that can retrieve real-time information from the web.
• Web Scraping Agent: Involves an example of an agent that leverages information scraped from the web using a retrieval tool. 
• Multi-Agent Systems: Involving different specialized agents to tackle various tasks for a comprehensive solution. The course demonstrates this with a marketing copywriter agentic system. 
• Hierarchical Agents: Involves supervisor/worker agents who communicate and collaborate with each other to perform complex and advanced tasks. The course demonstrates this with a course planner agent.

Here's a subset of companies whose employees have benefited from our courses:

Accrete, Airbnb, Alston & Bird, Amazon, Apple, Arm, Asana, Bank of America, Belong For Me, Biogen, Brilliant, Carebound, CDM, CentralReach, Centric Software, Chime, Coinbase, Digital Green, DoHQ, Elekta, Fidelity Investments, Fivecast, Fulcrum Labs, Google, Guru, Gretel, Harrison Insights, Intel, Intuit, Jina AI, JPMorgan Chase & Co, Khan Academy, KnowBe4, Lawyer.com, LinkedIn, LionSentry, MagmaLabs, MasterClass, Meta, Metopio, Microsoft, Moneta Health, Oracle, OpenAI, Rechat AI, RingCentral, Salesforce, Scale AI, Scribd, Space-O Technologies, Sun Life, TD Bank, TELUS Corporations, Trilogy, TTEC Digital, UniCredit, VaxCalc Labs, Vendr, Walmart, Wolfram Alpha, Zemoso Technologies, Zeplin 

Reach out to [email protected] with any questions and for team/student discounts.