AI Agents
LLMs, Agentic Workflows, and Tool Use
Preface
his is a collection of lecture notes and practical guides on AI Agents, focusing on large language models (LLMs), agentic workflows, and tool integration.
The materials consolidate insights from research and practice, covering the design, orchestration, and evaluation of LLM-powered agents across different domains.
Each section begins with learning objectives, core concepts, and references, followed by examples and hands-on frameworks.
The notes emphasize AI design patterns, retrieval-augmented generation (RAG), and multi-agent systems, offering both conceptual depth and implementation strategies. They are not intended to replace formal textbooks, but to complement them with practical, framework-driven guidance in building scalable, trustworthy, and adaptive LLM agents.
The intended audience is expected to be familiar with programming and the following LLM-focused concepts and frameworks:
- AI/LLM design patterns, including:
- retrieval-augmented generation (RAG)
- agent orchestration workflows
- memory and context management
- self-reflective and hierarchical agents
- Frameworks and libraries:
- LangChain for composable pipelines
- LangGraph for graph-based orchestration
- CrewAI for multi-agent collaboration
- MCP (Model Context Protocol) for interoperability
- Evaluation: methods, metrics, and benchmarks for LLMs and AI agents
- MultiModal AI: integrating vision, text, and speech into agentic workflows
- Tool Use & Integration: connecting APIs, databases, and external environments
- Safety & Alignment: robustness, trustworthiness, and ethical constraints for agentic systems
Citation
Kumar, K. (2025). AI Agents: LLMs, Agentic Workflows, and Tool Use. Edition 2025-09.
License
This work is licensed under the MIT License.