Free course · 6 lessons · Intermediate
Native AI Engineering: LLMs, RAG & Agents
A practical introduction to building applications with large language models, retrieval, and agents, drawing on widely used open guides.
1. Foundations of Native AI Engineering
How LLMs, embeddings, and retrieval work together
- How LLMs Work and Prompting Basics — The mental model behind prompting large language models
- Embeddings and Vector Databases — Represent meaning as vectors and search by similarity
- Retrieval-Augmented Generation (RAG) Explained — Ground LLM answers in your own data
2. Building & Operating AI Applications
Prompt engineering, agents, and evaluation in practice
- Prompt Engineering Techniques — Patterns that reliably improve model output
- AI Agents and Tool Use — Let models take actions, not just generate text
- Evaluating, Guardrails, and Deploying LLM Apps — Ship AI features responsibly