Learn Generative AI and AI agents through 66 focused lessons, arranged in 10 ordered modules. The course moves from AI foundations to prompt engineering, model APIs, retrieval-augmented generation, agent systems and deployment. It is designed for software developers, aspiring AI engineers and people preparing to explain these concepts in technical interviews. Begin with the differences between AI, machine learning and deep learning, then understand generative models, model providers and responsible use. Explore prompt structure, zero-shot and few-shot techniques, reasoning patterns, output validation, conversation memory and API security. Learn how to handle JSON responses, streaming, errors and evaluation.
The NLP and RAG lessons explain tokenization, embeddings, semantic search, chunking, vector databases and retrieval strategies. Follow the retrieval-and-generation workflow, compare dense, sparse and hybrid search, and examine query rewriting, hallucination reduction, advanced RAG and evaluation metrics. The agent modules cover architectures, tool calling, planning, multi-agent coordination and common frameworks. Compare LangChain, LlamaIndex, AutoGen, CrewAI and LangGraph, then explore MCP, agent-to-agent communication, agentic RAG, tracing, latency and cost.
Finish with API fundamentals, FastAPI, OpenAPI, Docker, CI/CD, Kubernetes basics, modular system design, frontend integration, security and monitoring. The lessons use visual explanations, examples and recaps to help you understand why a design works and how its trade-offs affect an AI application.
