Technique
Context engineering
Choosing what goes into a model's context window and in what order.
What should you learn before Context engineering?
- Tokens and tokenizationSplitting text into the units a language model reads and is billed by.
- TransformersThe attention-based neural network architecture behind modern language models.
- Large language models (LLMs)Transformer models trained on large amounts of text to predict the next token.
- Prompt engineeringWriting instructions and examples that get reliable output from a model.
What to learn after Context engineering
- Cache-augmented generation (CAG)Loading a fixed knowledge set into the model's context and cache instead of retrieving per question.
Practise Context engineering
- Advanced Generative AI Interview Questions1 question on Context engineering