Artificial intelligence · self-study course
Generative AI, RAG and practical evaluation
Practise clear prompting, retrieval-grounded workflows, evidence checking and permission-aware deployment.
Your learning path
- 01
Generative models, tokens and useful prompts
An autoregressive language model predicts successive tokens from context. A token may be a word piece, punctuation or another encoded unit.
Grades 9–12 · Notes · 8 questions - 02
Retrieval-augmented generation and evidence grounding
Retrieval-augmented generation first retrieves relevant source material, then conditions generation on selected context. It does not automatically make every answer correct.
University · Notes · 8 questions - 03
Evaluating generated answers and retrieval systems
Use representative tasks with clear expected behaviour and deliberately include failure cases. Keep an evaluation set separate from prompt tuning.
University · Notes · 8 questions - 04
AI system design, monitoring and safe tool boundaries
A useful AI application includes data handling, retrieval or model calls, validation, error handling and a user interface. The model is one component.
University · Notes · 8 questions