Designing LLM Agents and Agentic Workflows

Artificial intelligence is moving beyond static chat prompts toward autonomous systems that can plan, use tools, and make decisions. Understanding how these LLM agents operate is essential for anyone looking to build or work with modern AI workflows. This text-based course guides you through the core concepts of agentic design. You will transition from writing simple prompts to understanding how autonomous agents perceive information, reason through complex problems, and act using external tools. By studying clear explanations and written architecture patterns, you will gain the skills to conceptualize and design your own intelligent systems. What you'll learn: - Understand the fundamental difference between standard linear chains and autonomous agentic workflows. - Explore the perceive-reason-act loop that drives autonomous AI decision-making. - Learn how agents utilize tool calling and external APIs to interact with databases and web services. - Design planning and memory architectures that allow agents to retain context and solve multi-step problems. - Apply modern patterns like Retrieval-Augmented Generation (RAG) within agentic workflows. - Discover basic evaluation and observability techniques to monitor and refine agent behavior. You will start with foundational AI agent definitions and key terminology before exploring practical architecture patterns, memory management, and tool integration. The material progresses logically from theoretical concepts to structured written walkthroughs of agent design patterns. This course is designed for beginners, developers, and AI enthusiasts who want to understand the next wave of AI automation. No prior experience with agentic frameworks is required. Start reading today to master the architecture of autonomous AI agents.