Admissions are open for the October cohort. Explore Tracks
TTabflux

Skill Course

RAG, Agentic AI & Context Engineering

Ground models in organizational knowledge and connect them safely to tools and workflows.

30 Hours + 12 Hours
View objectives

Learning objectives

01

Build and evaluate a production-style RAG pipeline

02

Choose chunking, indexing and retrieval strategies

03

Design reliable tool-calling workflows

04

Use agents only when the task benefits from autonomy

05

Manage context, state, memory and human approval

Course coverage

01

RAG architecture, document ingestion, parsing, cleaning, chunking and metadata

02

Embeddings, vector databases, similarity search, filtering, hybrid search and reranking

03

Retrieval strategies, query transformation, context construction, citations and grounded generation

04

RAG evaluation, retrieval quality, answer quality, failure analysis and optimization

05

Function and tool calling, tool design, external APIs, databases and application actions

06

Agentic workflows: planning, routing, state, memory, checkpoints and human-in-the-loop controls

07

LangChain, LangGraph, LlamaIndex and custom orchestration patterns

08

Model Context Protocol concepts, tools, resources and AI-to-system integration patterns

09

Context engineering: selection, compression, memory, permissions and context management

10

Multi-agent concepts, deterministic workflows versus agents, and failure recovery

11

Agent and RAG security, prompt injection, tool permissions and data boundaries

12

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.