Skill Course
RAG, Agentic AI & Context Engineering
Ground models in organizational knowledge and connect them safely to tools and workflows.
Learning objectives
Build and evaluate a production-style RAG pipeline
Choose chunking, indexing and retrieval strategies
Design reliable tool-calling workflows
Use agents only when the task benefits from autonomy
Manage context, state, memory and human approval
Course coverage
RAG architecture, document ingestion, parsing, cleaning, chunking and metadata
Embeddings, vector databases, similarity search, filtering, hybrid search and reranking
Retrieval strategies, query transformation, context construction, citations and grounded generation
RAG evaluation, retrieval quality, answer quality, failure analysis and optimization
Function and tool calling, tool design, external APIs, databases and application actions
Agentic workflows: planning, routing, state, memory, checkpoints and human-in-the-loop controls
LangChain, LangGraph, LlamaIndex and custom orchestration patterns
Model Context Protocol concepts, tools, resources and AI-to-system integration patterns
Context engineering: selection, compression, memory, permissions and context management
Multi-agent concepts, deterministic workflows versus agents, and failure recovery
Agent and RAG security, prompt injection, tool permissions and data boundaries
Building production-style RAG and agentic applications
Next recommended Skill Course
Production AI Engineering & LLMOps
Deploy, evaluate, observe, secure, and improve AI systems in production.