Eight detailed chapters on language-model behavior, prompt design, embeddings, retrieval-augmented generation, grounding, evaluation, privacy and prompt-injection risk. Learn to distinguish model output from verified fact and to test retrieval separately from answer generation. Examples are conceptual and require no paid API. Lifetime online access; study notes only, no internship certificate.
What you’ll study
4 sections · 8 detailed chapters · about 40 minutes of reading · lifetime access. Chapter text is available online and as a downloadable PDF after purchase.
01 · Generative Models and Prompting
What a language model does and does not know5 min read
Prompt structure, examples and output checks5 min read
02 · Retrieval-Augmented Generation
Embeddings, chunking and retrieval5 min read
Grounded answers, citations and abstention5 min read
03 · Evaluation, Privacy and Safety
Design an evaluation set and compare versions5 min read
Privacy, prompt injection and operational limits5 min read
04 · Practice and Review
Guided lab: evaluate retrieval before generation5 min read
Mini project: a cited knowledge assistant5 min read