Introduction
Welcome to The Horizon. The field of AI is rapidly transitioning from passive chatbots to active, autonomous agents. In this course, you will learn how to build systems where AI doesn't just answer questions, but takes actions to solve complex problems.
An autonomous agent uses an LLM as its "brain" to reason, plan, and interact with external environments via tools and APIs. Instead of you breaking down a task into step-by-step code, you provide the agent with a high-level goal, and it figures out how to achieve it.
The path ahead
This course covers the cutting edge of AI development:
- First, we explore the conceptual foundation of Agentic Workflows: planning, memory, and reflection.
- Next, we dive into LangChain and learn how to give our LLMs tools (Function Calling).
- Then, we scale up to Multi-Agent Systems, where multiple specialized AIs collaborate.
- Finally, you will use crewAI to build a fully autonomous AI software engineering team.
Assignment
- Read Andrew Ng's article on "Agentic Design Patterns" to understand why this is the next frontier of AI.
- Review the concepts of APIs and REST architecture from previous courses, as agents rely heavily on them to interact with the world.